Intelligent anti-collision method and device between personnel and equipment on drilling platform

Abstract

The invention provides an intelligent anti-collision method between personnel and equipment on a drilling platform. The intelligent anti-collision method comprises the following steps: S1, acquiring image data acquired by a wide-angle camera and point cloud data acquired by a laser radar at each moment; wherein the view angle fields of the wide-angle camera and the laser radar cover the area of the drilling platform surface of the drilling platform; s2, inputting the image data and the point cloud data at the current moment into a pre-trained 3D personnel position detection model to obtain position information of personnel on the drill floor surface; the position information of the personnel comprises coordinates of eight vertexes of a cuboid-shaped 3D frame containing the personnel in a world coordinate system; and S3, according to the position information of the personnel on the drill floor surface, whether the personnel on the drill floor surface enter a pre-defined drill floor surface dangerous area or not is judged, and if the personnel enter the pre-defined drill floor surface dangerous area, the control system gives an alarm. Threats can be found in time, and operators can be automatically informed to pay attention to safety.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic safety of drilling platforms, and in particular to an intelligent anti-collision method and device between personnel and equipment on a drilling platform. Background Art

[0002] When working on an oil rig, safety is always paramount. Workers on the rig must strictly adhere to safety regulations and operating procedures, wear necessary protective equipment, and ensure the safety of themselves and others. Currently, drilling platforms rely primarily on manual labor to reduce and prevent accident risks. During operations, multiple personnel assist in monitoring the drilling process. If any dangerous conditions are detected, personnel in the affected area are manually alerted to safety. This approach requires everyone involved in the drilling operation to be on high alert, but human energy and vision are limited, making carelessness and safety issues inevitable.

[0003] Therefore, it is urgent to propose an intelligent anti-collision method and device between personnel and equipment on a drilling platform. Summary of the Invention

[0004] (1) Technical issues to be resolved

[0005] In view of the problems existing in the above technologies, the present invention aims to solve them to at least some extent. To this end, the present invention aims to provide an intelligent collision avoidance method and device between personnel and equipment on a drilling platform, which can detect threats in a timely manner and automatically inform operators to pay attention to safety.

[0006] (2) Technical solution

[0007] In order to achieve the above objectives, the main technical solutions adopted by the present invention include:

[0008] In a first aspect, the present invention provides an intelligent collision avoidance method between personnel and equipment on a drilling platform, comprising the following steps:

[0009] S1. Obtain image data collected by a wide-angle camera and point cloud data collected by a lidar at each moment; wherein the viewing angles of the wide-angle camera and the lidar both cover the drilling floor area of the drilling platform;

[0010] S2. Input the current image data and point cloud data into a pre-trained 3D personnel position detection model to obtain the position information of the personnel on the drilling floor; the personnel position information includes the coordinates of the eight vertices of the rectangular 3D box containing the personnel in the world coordinate system;

[0011] In the 3D personnel location detection model, a convolutional neural network receives image data and extracts 2D features from the image, while a point cloud network receives point cloud data and extracts 3D features. Based on a pre-calibrated extrinsic parameter matrix, the 2D features are mapped to the world coordinate system and converted into a first BEV feature map. The 3D features are converted into a second BEV feature map. The first and second BEV feature maps are fused using a cross-attention mechanism, and the fused features are output. The detection head receives the fused features and outputs the location information of the personnel on the drilling floor.

[0012] S3. Based on the position information of the personnel on the drilling floor, it is determined whether the personnel on the drilling floor have entered a pre-defined dangerous area of the drilling floor. If so, the control system generates an alarm.

[0013] Optionally, image data collected by the wide-angle camera and point cloud data collected by the lidar are obtained at each moment, including: obtaining image data collected by the wide-angle camera and point cloud data collected by the lidar at each moment according to the PTP precision time protocol or the NTP network time protocol.

[0014] Optionally, before S1, it also includes:

[0015] S01. Using the four vertices of the turntable base outline in a bird's-eye view as reference points, determine the X-axis and Y-axis directions of the world coordinate system, and establish a world coordinate system with the center point of the wellhead as the origin of the coordinate system. Calibrate the world coordinate system and the camera coordinate system of the wide-angle camera to obtain an extrinsic parameter matrix.

[0016] Optionally, in S2, the image data and point cloud data at the current moment and within a preset time period before the current moment are input into a pre-trained 3D personnel position detection model to obtain the position information, speed information and movement trajectory of the personnel on the drilling floor.

[0017] Optionally, S3 also includes: judging whether a collision will occur between the personnel and the equipment based on the position information, speed information and movement trajectory of the personnel on the drilling floor, as well as the operating status of the equipment on the drilling floor; if a collision occurs, the control system controls the equipment to perform an emergency stop in advance.

[0018] Optionally, the intelligent anti-collision method between personnel and equipment on the drilling platform further includes the following steps:

[0019] S4. Map the position information of the personnel on the drilling floor into the image and display it according to the pre-calibrated external parameter matrix and the internal parameter matrix of the wide-angle camera.

[0020] Optionally, the position information of the person includes the coordinates of eight vertices of a minimum 3D box containing the person.

[0021] In a second aspect, the present invention provides an intelligent anti-collision device between personnel and equipment on a drilling platform, comprising:

[0022] An acquisition module is used to acquire image data collected by the wide-angle camera and point cloud data collected by the lidar at each moment; wherein the viewing angles of the wide-angle camera and the lidar both cover the drilling floor area of the drilling platform;

[0023] A detection module is used to input the current image data and point cloud data into a pre-trained 3D personnel location detection model to obtain the location information of the personnel on the drilling floor; the personnel location information includes the coordinates of the eight vertices of the 3D rectangular box containing the personnel in the world coordinate system;

[0024] In the 3D personnel location detection model, a convolutional neural network receives image data and extracts 2D features from the image, while a point cloud network receives point cloud data and extracts 3D features. Based on a pre-calibrated extrinsic parameter matrix, the 2D features are mapped to the world coordinate system and converted into a first BEV feature map. The 3D features are converted into a second BEV feature map. The first and second BEV feature maps are fused using a cross-attention mechanism, and the fused features are output. The detection head receives the fused features and outputs the location information of the personnel on the drilling floor.

[0025] A judgment module is used to judge whether the personnel on the drilling floor have entered a pre-defined dangerous area of the drilling floor according to the position information of the personnel on the drilling floor;

[0026] The control system is used to receive the judgment result and issue an alarm when the judgment result is that the personnel on the drilling floor have entered the pre-defined dangerous area of the drilling floor.

[0027] Optionally, a detection module is configured to input image data and point cloud data at a current moment and within a preset time period before the current moment into a pre-trained 3D personnel position detection model to obtain position information, speed information, and movement trajectory of personnel on the drilling floor;

[0028] The judgment module is also used to judge whether a collision will occur between personnel and equipment based on the position information, speed information and movement trajectory of personnel on the drilling floor and the operating status of equipment on the drilling floor;

[0029] The control system is also used to control the equipment to perform an emergency stop in advance when it is determined that a collision between a person and the equipment will occur.

[0030] Optionally, the intelligent anti-collision device between personnel and equipment on the drilling platform further includes: a display module, which is used to map the position information of personnel on the drilling platform into an image and display it based on a pre-calibrated external parameter matrix and an internal parameter matrix of the wide-angle camera.

[0031] (3) Beneficial effects

[0032] The beneficial effects of the present invention are:

[0033] The intelligent collision avoidance method and device between personnel and equipment on a drilling platform provided by the present invention combines a wide-angle camera and a lidar to obtain information on the drilling surface, and uses the Bevfusion algorithm to process image data collected by the wide-angle camera and point cloud data collected by the lidar. It can accurately detect the position of personnel on the drilling surface, and then make collision avoidance judgments based on the position of personnel on the drilling surface and pre-defined danger areas, so that the control system can detect threats in a timely manner, automatically inform operators to pay attention to safety, and ensure personnel safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The present invention is described with the aid of the following drawings:

[0035] Figure 1 Schematic diagram of the process of the intelligent anti-collision method between personnel and equipment on a drilling platform according to Example 1;

[0036] Figure 2 Schematic top view of the turntable on the drilling floor according to Example 1.

[0037] Reference numerals

[0038] 1: Turntable; 2: Base; 3: Wellhead; 4: Rathole. DETAILED DESCRIPTION

[0039] In order to better explain the present invention and facilitate understanding, the present invention is described in detail below through specific implementation methods in conjunction with the accompanying drawings.

[0040] Example 1

[0041] like Figure 1 As shown, this embodiment provides an intelligent collision avoidance method between personnel and equipment on a drilling platform, comprising the following steps:

[0042] S1. Obtain image data collected by a wide-angle camera and point cloud data collected by a lidar at each moment; wherein the viewing angles of the wide-angle camera and the lidar both cover the drilling floor area of the drilling platform.

[0043] Among them, the timestamps of the image data collected by the wide-angle camera and the point cloud data collected by the lidar are aligned.

[0044] Preferably, obtaining the image data captured by the wide-angle camera and the point cloud data collected by the lidar at each moment includes obtaining the image data captured by the wide-angle camera and the point cloud data collected by the lidar at each moment according to the PTP precision time protocol or the NTP network time protocol. This ensures that the timestamps of the acquired image data captured by the wide-angle camera and the point cloud data collected by the lidar are aligned.

[0045] By combining wide-angle cameras and lidar, the entire drilling floor can be covered, providing a data basis for accurate detection of the position of personnel on the drilling floor, and reducing the number of sensors and the failure rate of sensors in the later stage.

[0046] S2. Input the current image data and point cloud data into a pre-trained 3D personnel position detection model to obtain the position information of the personnel on the drilling floor; the personnel position information includes the coordinates of the eight vertices of the rectangular 3D box containing the personnel in the world coordinate system.

[0047] Specifically, in the 3D personnel location detection model, a convolutional neural network receives image data and extracts 2D features from the image, while a point cloud network receives point cloud data and extracts 3D features. Based on a pre-calibrated extrinsic parameter matrix, the 2D features are mapped to the world coordinate system and converted into a first BEV feature map. The 3D features are converted into a second BEV feature map. The first and second BEV feature maps are fused using a cross-attention mechanism, outputting a fused feature. The detection head receives the fused feature and outputs the position information of the personnel on the drilling floor. In this way, the Bevfusion algorithm, which fuses image data and point cloud data, can accurately identify the position information of personnel on the drilling floor.

[0048] Preferably, in S2, the image data and point cloud data from the current moment and a preset time period before the current moment are input into a pre-trained 3D personnel location detection model to obtain the position information, speed information, and movement trajectory of the personnel on the drilling floor. This provides a data basis for the collision avoidance judgment in S3.

[0049] Preferably, the position information of the person includes the coordinates of eight vertices of a minimum 3D box containing the person.

[0050] S3. Based on the position information of the personnel on the drilling floor, it is determined whether the personnel on the drilling floor have entered a pre-defined dangerous area of the drilling floor. If so, the control system generates an alarm.

[0051] In this way, threats can be discovered in a timely manner and operators can be automatically informed to pay attention to safety without the need for manual notification, thus ensuring the safety of personnel on the drilling platform.

[0052] Preferably, S3 further includes: determining whether a collision between the personnel and the equipment will occur based on the personnel's position information, speed information, and movement trajectory, as well as the operating status of the equipment on the drilling floor. If a collision is likely, the control system controls the equipment to perform an emergency stop in advance, thereby further ensuring the safety of the personnel on the drilling floor.

[0053] S4. Map the position information of the personnel on the drilling floor into the image and display it according to the pre-calibrated external parameter matrix and the internal parameter matrix of the wide-angle camera.

[0054] Preferably, before S1, the method further includes:

[0055] S01. Using the four vertices of the turntable base outline from a bird's-eye view as reference points, determine the X- and Y-axis directions of the world coordinate system. Establish a world coordinate system with the wellhead center as the origin. Calibrate the world coordinate system and the wide-angle camera's camera coordinate system to obtain the extrinsic parameter matrix. This allows calibration by simply selecting the four vertices of the turntable base, eliminating the need for an additional calibration plate.

[0056] It should be noted that selecting the inherent points on the turntable for calibration is only an optimization. It can be imagined that selecting the inherent points on the wellhead or rat hole can also calibrate the world coordinate system and the camera coordinate system.

[0057] Among them, such as Figure 2 As shown, the turntable includes a turntable for driving the drill string and a base for supporting the turntable. The base is fixed to the drill floor and has a rectangular outline when viewed from above. The turntable is a conventional structure on the drill floor and is a prior art, so it will not be described in detail here.

[0058] The intelligent collision avoidance method between personnel and equipment on a drilling platform provided in this embodiment combines a wide-angle camera and a lidar to obtain information on the drill floor, and uses the Bevfusion algorithm to process image data collected by the wide-angle camera and point cloud data collected by the lidar. This method can accurately detect the position, speed, and movement trajectory of personnel on the drill floor, and then make collision avoidance judgments based on the position, speed, and movement trajectory of personnel on the drill floor. This enables the control system to detect threats in a timely manner, automatically inform operators to pay attention to safety, and automatically control the equipment on the drill floor to make an emergency stop in advance to ensure personnel safety.

[0059] Example 2

[0060] This embodiment provides an intelligent anti-collision device between personnel and equipment on a drilling platform, comprising:

[0061] The acquisition module is used to obtain the image data collected by the wide-angle camera and the point cloud data collected by the lidar at each moment; wherein the viewing angles of the wide-angle camera and the lidar both cover the drill floor area of the drilling platform.

[0062] The detection module is used to input the current image data and point cloud data into a pre-trained 3D personnel location detection model to obtain the location information of the personnel on the drilling floor; the personnel location information includes the coordinates of the eight vertices of the rectangular 3D box containing the personnel in the world coordinate system.

[0063] In the 3D personnel position detection model, the convolutional neural network receives image data to extract 2D features of the image, and the point cloud network receives point cloud data to extract 3D features. According to the pre-calibrated external parameter matrix, the 2D features are mapped to the world coordinate system and converted into the first BEV feature map, and the 3D features are converted into the second BEV feature map. The first BEV feature map and the second BEV feature map are fused according to the cross-attention mechanism, and the fused features are output. The detection head receives the fused features and outputs the position information of the personnel on the drilling platform.

[0064] The judgment module is used to judge whether the personnel on the drilling floor have entered a pre-defined dangerous area of the drilling floor according to the position information of the personnel on the drilling floor.

[0065] The control system is used to receive the judgment result and issue an alarm when the judgment result is that the personnel on the drilling floor have entered the pre-defined dangerous area of the drilling floor.

[0066] The intelligent anti-collision device between personnel and equipment on the drilling platform provided in this embodiment combines a wide-angle camera and a lidar to obtain information on the drilling floor, and uses the Bevfusion algorithm to process image data collected by the wide-angle camera and point cloud data collected by the lidar. It can accurately detect the position of personnel on the drilling floor, and then make collision avoidance judgments based on the position of personnel on the drilling floor and pre-defined danger zones. This enables the control system to detect threats in a timely manner, automatically inform operators to pay attention to safety, and ensure personnel safety.

[0067] Preferably, the detection module is configured to input image data and point cloud data from the current moment and a preset time period before the current moment into a pre-trained 3D personnel location detection model to obtain the position, speed, and movement trajectory of the personnel on the drilling floor. The judgment module is further configured to determine whether a collision between the personnel and the equipment will occur based on the personnel's position, speed, and movement trajectory, as well as the operating status of the equipment on the drilling floor. The control system is further configured to control the equipment to perform an emergency stop in advance if the judgment result indicates a collision between the personnel and the equipment is positive. This further ensures the safety of personnel on the drilling floor.

[0068] Preferably, the intelligent anti-collision device between personnel and equipment on the drilling platform further includes: a display module for mapping the position information of personnel on the drilling platform into an image and displaying it according to a pre-calibrated external parameter matrix and an internal parameter matrix of the wide-angle camera.

[0069] Preferably, the intelligent collision avoidance system for personnel and equipment on the drilling platform also includes a wide-angle camera and a lidar. The wide-angle camera and lidar are installed at a suitable location on the drill floor and adjusted to a suitable angle so that their fields of view uniformly cover the entire drill floor area. For example, the wide-angle camera is installed somewhere on the derrick or driller's cabin above the wellhead.

[0070] It should be noted that the specific functions of each module in the intelligent anti-collision method between personnel and equipment on a drilling platform provided in this embodiment, and the processing flow of the intelligent anti-collision method between personnel and equipment on a drilling platform, can be referred to the detailed description of the intelligent anti-collision method between personnel and equipment on a drilling platform provided in the above embodiment 1, and will not be repeated here.

[0071] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0072] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions.

[0073] It should be noted that, in the claims, any reference signs placed between brackets shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention may be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In claims enumerating several means, several of these means may be embodied by one and the same hardware. The use of the words first, second, third etc. is for convenience only and does not indicate any order. These words may be understood as part of the component name.

[0074] In addition, it should be noted that, in the description of this specification, the description of the terms "one embodiment", "some embodiments", "embodiment", "example", "specific example" or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0075] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments after learning the basic creative concept. Therefore, the claims should be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0076] Obviously, those skilled in the art may make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if such modifications and variations fall within the scope of the claims and their equivalents, the present invention shall also include such modifications and variations.

Claims

1. An intelligent anti-collision method between personnel and equipment on a drilling platform, characterized in that: The following steps are involved: S1. Obtain image data collected by a wide-angle camera and point cloud data collected by a lidar at each moment; wherein the viewing angles of the wide-angle camera and the lidar both cover the drilling floor area of the drilling platform; S2. Input the current image data and point cloud data into a pre-trained 3D personnel position detection model to obtain the position information of the personnel on the drilling floor; the personnel position information includes the coordinates of the eight vertices of the rectangular 3D box containing the personnel in the world coordinate system; In the 3D personnel location detection model, a convolutional neural network receives image data and extracts 2D features from the image, while a point cloud network receives point cloud data and extracts 3D features. Based on a pre-calibrated extrinsic parameter matrix, the 2D features are mapped to the world coordinate system and converted into a first BEV feature map. The 3D features are converted into a second BEV feature map. The first and second BEV feature maps are fused using a cross-attention mechanism, and the fused features are output. The detection head receives the fused features and outputs the location information of the personnel on the drilling floor. S3. Based on the position information of the personnel on the drilling floor, it is determined whether the personnel on the drilling floor have entered a pre-defined dangerous area of the drilling floor. If so, the control system generates an alarm.

2. The intelligent anti-collision method between personnel and equipment on a drilling platform according to claim 1, characterized in that: Obtain image data collected by the wide-angle camera and point cloud data collected by the lidar at each moment, including: According to the PTP precision time protocol or the NTP network time protocol, the image data collected by the wide-angle camera and the point cloud data collected by the lidar are obtained at each moment.

3. The intelligent anti-collision method between personnel and equipment on a drilling platform according to claim 1, characterized in that: Before S1, it also included: S01. Using the four vertices of the turntable base outline in a bird's-eye view as reference points, determine the X-axis and Y-axis directions of the world coordinate system, and establish a world coordinate system with the center point of the wellhead as the origin of the coordinate system. Calibrate the world coordinate system and the camera coordinate system of the wide-angle camera to obtain an extrinsic parameter matrix.

4. The intelligent anti-collision method between personnel and equipment on a drilling platform according to claim 1, characterized in that: In S2, the image data and point cloud data at the current moment and within a preset time period before the current moment are input into a pre-trained 3D personnel position detection model to obtain the position information, speed information and movement trajectory of the personnel on the drilling floor.

5. The intelligent anti-collision method between personnel and equipment on a drilling platform according to claim 4, characterized in that: S3 also includes: Based on the position information, speed information and movement trajectory of the personnel on the drilling floor, as well as the operating status of the equipment on the drilling floor, it is determined whether the personnel and equipment will collide. If a collision occurs, the control system will control the equipment to perform an emergency stop in advance.

6. The intelligent anti-collision method between personnel and equipment on a drilling platform according to claim 1, characterized in that: The following steps are also included: S4. Map the position information of the personnel on the drilling floor into the image and display it according to the pre-calibrated external parameter matrix and the internal parameter matrix of the wide-angle camera.

7. The intelligent anti-collision method between personnel and equipment on a drilling platform according to claim 1, characterized in that: The position information of a person includes the coordinates of eight vertices of the smallest 3D box that contains the person.

8. An intelligent anti-collision device between personnel and equipment on a drilling platform, characterized in that: include: An acquisition module is used to acquire image data collected by the wide-angle camera and point cloud data collected by the lidar at each moment; wherein the viewing angles of the wide-angle camera and the lidar both cover the drilling floor area of the drilling platform; A detection module is used to input the current image data and point cloud data into a pre-trained 3D personnel location detection model to obtain the location information of the personnel on the drilling floor; the personnel location information includes the coordinates of the eight vertices of the 3D rectangular box containing the personnel in the world coordinate system; In the 3D personnel location detection model, a convolutional neural network receives image data and extracts 2D features from the image, while a point cloud network receives point cloud data and extracts 3D features. Based on a pre-calibrated extrinsic parameter matrix, the 2D features are mapped to the world coordinate system and converted into a first BEV feature map. The 3D features are converted into a second BEV feature map. The first and second BEV feature maps are fused using a cross-attention mechanism, and the fused features are output. The detection head receives the fused features and outputs the location information of the personnel on the drilling floor. A judgment module is used to judge whether the personnel on the drilling floor have entered a pre-defined dangerous area of the drilling floor according to the position information of the personnel on the drilling floor; The control system is used to receive the judgment result and issue an alarm when the judgment result is that the personnel on the drilling floor have entered the pre-defined dangerous area of the drilling floor.

9. The intelligent anti-collision device between personnel and equipment on a drilling platform according to claim 8, characterized in that: A detection module is used to input image data and point cloud data from the current moment and a preset time period before the current moment into a pre-trained 3D personnel position detection model to obtain the position information, speed information and movement trajectory of the personnel on the drilling floor; The judgment module is also used to judge whether a collision will occur between personnel and equipment based on the position information, speed information and movement trajectory of personnel on the drilling floor and the operating status of equipment on the drilling floor; The control system is also used to control the equipment to perform an emergency stop in advance when it is determined that a collision between a person and the equipment will occur.

10. The intelligent anti-collision device between personnel and equipment on a drilling platform according to claim 8, characterized in that: Also includes, The display module is used to map the position information of the personnel on the drilling floor into the image and display it according to the pre-calibrated external parameter matrix and the internal parameter matrix of the wide-angle camera.

Images