Blowout preventer surface treatment method, system and equipment capable of identifying classification decision

Abstract

The invention belongs to the field of blowout preventer cleaning, relates to a blowout preventer surface treatment method capable of identifying classification decision, and aims to solve the problems that the blowout preventer is not completely cleaned and is not pertinently cleaned. The method comprises the following steps: acquiring a surface image of the blowout preventer, and identifying the surface image of the blowout preventer to obtain features of the blowout preventer and a dirty area identification result; comparing the shadow gray value with a set gray value interval, classifying the dirty area, and determining the cleaning intensity according to a classification result; establishing a virtual blowout preventer model according to the characteristics of the blowout preventer, and performing planarization processing on the virtual blowout preventer model to obtain a blowout preventer planarization image; dividing the planarized image of the blowout preventer into a plurality of cleaning area blocks, wherein the sum of the edges of the plurality of cleaning area blocks is the cleaning path of the surface of the blowout preventer; selecting a nozzle according to the distance from the idle nozzle to the blowout preventer; and the control system cleans the blowout preventer. The surface of the blowout preventer can be cleaned comprehensively and specifically.

Description

Background Art

[0002] At present, the blowout preventer is a key equipment for the oil industry to effectively control the wellhead pressure and prevent blowout accidents during drilling, well repair, and oil testing. It weighs up to 20 tons, is large in size, complex in structure, and has an irregular shape. During the on-site use of the blowout preventer, due to the harsh drilling conditions and complex process, when the blowout preventer is returned to the factory for maintenance after use, the surface and inner cavity are often attached with high-viscosity crude oil and mud. If it is not cleaned, subsequent maintenance and inspection work will not be possible. In order to ensure the normal maintenance and pressure test of the blowout preventer, the crude oil and mud attached to the surface and cavity of the blowout preventer are cleaned manually. Because the crude oil and mud are very viscous and adhere for a long time, they are very firmly attached to the surface and cavity of the blowout preventer, making manual cleaning extremely difficult. The use of high-pressure water guns for flushing has a small flushing area and a long time, and the cleaning efficiency is very low. In addition, the key inner cavity parts cannot be cleaned, and there are certain unsafe factors, which seriously affect the maintenance and pressure test of the blowout preventer.

[0003] The existing methods and devices for cleaning the surface of the blowout preventer are not comprehensive enough and not targeted enough, and the cleaning of the blowout preventer is not thorough enough, which affects the cleaning effect and cleaning efficiency. Summary of the invention

[0004] In order to solve the above-mentioned problems in the prior art, that is, the existing methods and devices for cleaning the surface of the blowout preventer are not comprehensive and targeted enough, and the cleaning of the blowout preventer is not thorough enough, which affects the cleaning effect and cleaning efficiency, the present invention provides a blowout preventer surface treatment method with identification classification decision, the method comprising:

[0005] Acquire a surface image of the blowout preventer, identify the surface image of the blowout preventer, and obtain features of the blowout preventer, a dirty area identification result, and a dirty area identification image; the dirty area identification result includes a position of the dirty area and a shadow grayscale value of the dirty area;

[0006] Setting multiple grayscale value intervals according to the type of dirty area, determining the classification of the dirty area according to the grayscale value interval in which the shadow grayscale value is located, and determining the cleaning intensity according to the dirty area classification result;

[0007] A virtual BOP model is established in the simulation interface according to the characteristics of the BOP, and the virtual BOP model is planarized to obtain a planar image of the BOP; the planar image of the BOP is divided into a plurality of cleaning area grids, and the grid lines of the plurality of cleaning area grids are cleaning paths on the surface of the BOP;

[0008] Based on the relative positions from the data recognition point behind the idle nozzles to each idle nozzle, the relative positions from the data recognition point behind the idle nozzles to the blowout preventer, and the laser propagation speed of the data recognition point, calculate the distance from each idle nozzle to the surface of the blowout preventer; wherein, each idle nozzle is on the cleaning device;

[0009] Select the nozzle with the shortest distance according to the distance from the idle nozzle to the blowout preventer;

[0010] The control system controls the selected nozzle on the cleaning device to clean the blowout preventer according to the cleaning path and cleaning intensity. During the cleaning process, the balance amplitude value of the cleaning device is monitored in real time. Calculate the balance threshold according to the balance amplitude value and the normal amplitude value of the cleaning device. Determine whether to adjust the cleaning device according to the balance threshold. The calculation method of the balance threshold is:

[0011]

[0012] wherein, Y m is the balance threshold of the cleaning device, is the balance amplitude value of the cleaning device, is the normal amplitude value of the cleaning device;

[0013] If Y m is a positive value, perform normal cleaning; if Y m is a non-positive value, adjust the balance of the cleaning device.

[0014] According to the surface treatment method of the blowout preventer, it is characterized in that the method for determining the shadow gray value is:

[0015] g = α × (Max(w1 × w2 × (u1 - u2) × (u1 - u2)));

[0016] wherein, g represents the shadow gray value, α represents the adjustment coefficient, which represents the influence of noise and interference on the image; w1 represents the proportion of the number of foreground points in the image to the image; w2 represents the proportion of the number of background points; u1 represents the average gray value of the foreground; u2 represents the average gray value of the background.

[0017] According to the above surface treatment method of the blowout preventer, set multiple gray value intervals according to the type of the dirty area. According to the gray value interval where the shadow gray value is located, determine the classification of the dirty area. The specific steps for determining the cleaning intensity according to the classification result of the dirty area include:

[0018] If 0 < g < a, when the shadow gray value g is greater than zero and lower than the set threshold a, the dirty area is a non-dirty area, and fine treatment with a water pump is adopted;

[0019] If a < g < b, when the shadow gray value g is greater than the set threshold a and lower than the set threshold b, the dirty area is a lightly dirty area, and fine treatment with a water pump and adding medicine are adopted;

[0020] If b < g, when the shadow gray value g is greater than the set threshold b, the soiled area is a heavily soiled area, and fine treatment with a water pump, chemical addition, and sandblasting are adopted;

[0021] g represents the shadow gray value, and both a and b are set values.

[0022] For each idle nozzle, the method for calculating the distance from each idle nozzle to the surface of the blowout preventer is as follows:

[0023]

[0024] is the straight-line distance from the idle nozzle to the blowout preventer; V 激光 is the speed of the laser of the data identifier propagating in the air, is the total time taken for the laser of the data identifier to be projected onto the surface of the blowout preventer and the laser to feedback, is the total time taken for the laser to be projected onto the idle nozzle and the laser to feedback, ζ is the angle formed between the ray of the laser projected from the data identification point to the blowout preventer and the ray of the laser projected onto the idle nozzle;

[0025] S 距离n = S 识别n sinα n ;

[0026] S 距离n is the horizontal distance from the data identification point to the idle nozzle, and α is the angle formed between the direct position and the horizontal position of the data identification point;

[0027]

[0028] is the horizontal distance from the idle nozzle to the surface of the blowout preventer, is the horizontal distance from the data identification point to the idle nozzle, is the horizontal distance from the data identification point to the surface of the blowout preventer;

[0029]

[0030] L 距离 is the actual distance from the nth idle nozzle to the surface of the blowout preventer, and β is the inclination angle formed by the nth idle nozzle and the surface of the blowout preventer;

[0031] Select the nozzle with the shortest distance according to the distance from the idle nozzle to the blowout preventer, mainly including:

[0032] The formula for the bubble sort algorithm is: Compare them in pairs, arrange them in order from small to large, and select the idle nozzle corresponding to the smallest distance to clean the BOP;

[0033] in, is the distance from the first idle nozzle to the surface of the BOP; is the distance from the second idle nozzle to the surface of the BOP; is the distance from the third idle nozzle to the surface of the BOP; is the distance from the nth idle nozzle to the surface of the BOP.

[0034] The above-mentioned blowout preventer surface treatment method with identifiable classification decision-making also includes combining the idle nozzles according to the dirty area identification result of the blowout preventer, and adjusting the spray angle and strength of the nozzle according to the dirty area identification result.

[0035] Another aspect of the present invention provides a system for surface treatment of a blowout preventer capable of identifiable classification decisions, the system comprising:

[0036] The data acquisition module is used to acquire the surface image of the blowout preventer, identify the surface image of the blowout preventer, and obtain the characteristics of the blowout preventer and the dirty area recognition result; the dirty area recognition result includes the position of the dirty area and the shadow gray value of the dirty area;

[0037] An intensity determination module is used to compare the shadow gray value with the set gray value interval, classify the dirty area according to the comparison result, and determine the cleaning intensity according to the dirty area classification result;

[0038] A cleaning path determination module is used to establish a virtual BOP model in a simulation interface according to the characteristics of the BOP, and to planarize the virtual BOP model to obtain a planar image of the BOP; the planar image of the BOP is divided into a plurality of cleaning area blocks, and the sum of the edges of the plurality of cleaning area blocks is the cleaning path of the BOP surface;

[0039] a distance determination module, for calculating the distance from each idle nozzle to the surface of the blowout preventer according to the relative position of the data identification point behind the idle nozzle to each idle nozzle, the relative position of the data identification point behind the idle nozzle to the blowout preventer, and the laser propagation speed of the data identification point; wherein each nozzle is on the cleaning device;

[0040] The nozzle selection module is used to select the optimal nozzle according to the distance from the idle nozzle to the blowout preventer;

[0041] The cleaning control module is used to control the system to control the selected nozzles on the cleaning equipment to clean the BOP according to the cleaning path and cleaning intensity. During the cleaning process, the balance amplitude value of the cleaning equipment is monitored in real time. The balance threshold is calculated according to the balance amplitude value and the normal amplitude value of the cleaning equipment. Whether to adjust the cleaning equipment is determined according to the balance threshold. Specifically:

[0042]

[0043] Among them, Y m is the balance threshold of the cleaning equipment, is the balance amplitude value of the cleaning equipment, is the normal amplitude value of the cleaning equipment;

[0044] If Y m If Y is positive, the cleaning is normal; m If it is a non-positive value, adjust the balance of the cleaning equipment.

[0045] In a third aspect of the present invention, an electronic device is proposed, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the processor, the instructions being executed by the processor to implement the above-mentioned method for surface treatment of a blowout preventer based on identifiable classification decisions.

[0046] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by a computer to implement the above-mentioned method for surface treatment of a blowout preventer with identifiable classification decision.

[0047] Beneficial effects of the present invention:

[0048] (1) The blowout preventer surface treatment method, system and equipment capable of identifiable classification decision-making of the present invention can comprehensively and specifically clean the blowout preventer surface, thereby improving the cleaning effect and cleaning efficiency.

[0049] (2) The present invention obtains the shadow grayscale value of the dirty area by identifying the surface image of the blowout preventer, compares the shadow grayscale value with the set grayscale value interval, classifies the dirty area according to the comparison result, and determines the cleaning intensity according to the dirty area classification result, so as to clean the blowout preventer in a targeted manner and improve the cleaning efficiency.

[0050] (3) The present invention selects the nozzle with the shortest distance through a bubbling algorithm, and can also combine idle nozzles and adjust the spray angle and strength of the nozzles, so as to clean the blowout preventer in an all-round way and improve the cleaning efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0052] Figure 1 The present invention is a flow chart of a method for surface treatment of a blowout preventer that can identify and classify decisions;

[0053] Figure 2 It is a schematic diagram of the visual scanning acquisition system;

[0054] Figure 3 is a schematic diagram of a blowout preventer with sludge;

[0055] Figure 4 A schematic diagram of using a nozzle to clean the sludge on the surface of the blowout preventer;

[0056] Figure 5 A schematic diagram of dividing a planar image of a blowout preventer into a plurality of cleaning area blocks;

[0057] Figure 6 It is a schematic diagram that the cleaning area is a square;

[0058] Figure 7 It is a schematic diagram of combining and switching the idle nozzles;

[0059] Figure 8 This is a schematic diagram of the structure of a computer system of a server for implementing the method, system, and device embodiments of the present application. DETAILED DESCRIPTION

[0060] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0061] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0062] The first embodiment of the present invention provides a method for surface treatment of a blowout preventer capable of identifiable classification decision making, such as Figure 1 , the method comprises the following steps:

[0063] S100, acquiring a surface image of the blowout preventer, identifying the surface image of the blowout preventer, and obtaining the characteristics of the blowout preventer and the dirty area identification result;

[0064] The dirty area recognition result includes the position of the dirty area and the shadow gray value of the dirty area;

[0065] Specifically, the process of image recognition of the BOP surface by the visual scanning acquisition system of the control system is divided into the following steps: image acquisition, preprocessing, feature extraction and selection, classifier design and classification decision. Figure 2 , which is a schematic diagram of the visual scanning acquisition system; the image is mainly acquired by scanning the visual scanning acquisition system to obtain the overall image of the blowout preventer and determine the position and status of the blowout preventer. Figure 3 , for a blowout preventer with sludge. Preprocessing mainly refers to the operations of denoising, smoothing, transformation, etc. in image processing, so as to enhance the important features of the image; the corresponding processed image is obtained by preprocessing the acquired blowout preventer image. Feature extraction and selection refer to the need to extract and select features in pattern recognition. The simple understanding is that the images we study are of various types. If we want to use a certain method to distinguish them, we must identify them through the characteristics of these images themselves, and the process of obtaining these features is feature extraction. The features obtained in feature extraction may not all be useful for this recognition. At this time, useful features must be extracted, which is feature selection. Feature extraction and selection is one of the most critical technologies in the image recognition process. When performing specific feature extraction, the main thing is to extract and identify the dirt on the blowout preventer.

[0066] S200, setting a plurality of gray value intervals according to the type of the dirty area, determining the classification of the dirty area according to the gray value interval in which the shadow gray value is located, and determining the cleaning intensity according to the classification result of the dirty area;

[0067] S300, establishing a virtual BOP model on a simulation interface according to the characteristics of the BOP, performing planarization processing on the virtual BOP model to obtain a planarized image of the BOP; dividing the planarized image of the BOP into a plurality of cleaning area grids;

[0068] The grid lines of the multiple cleaning area grids are the cleaning paths on the surface of the BOP;

[0069] Specifically, after the blowout preventer is scanned and multiple feature information is obtained, a virtual blowout preventer model with the same shape and size as the blowout preventer surface is established in the simulation interface, and different model parts are extracted from the obtained virtual blowout preventer model, that is, multiple model parts that need to set the moving path of the cleaning equipment are extracted from a virtual blowout preventer model, and these model parts correspond to the surface of the blowout preventer with a large amount of impurities attached. After obtaining each model part, each model part is then converted, that is, since each model part may contain a model part with a curved surface shape, it is difficult to set the moving path of the cleaning equipment for the curved surface model part, so each model part needs to be converted into an image of a plane perspective, that is, a planarized image of the blowout preventer, which is convenient for setting the moving path of the cleaning equipment in the subsequent process. For example, the shape of the blowout preventer surface includes a large number of curved surface structures. After obtaining the virtual blowout preventer model, the virtual blowout preventer model is then converted and each model part is unfolded into a plane image to obtain the plane perspective of different model parts of the physical model, that is, the planarized image of the blowout preventer in the plane perspective.

[0070] S400, calculating the distance from each idle nozzle to the surface of the blowout preventer according to the relative position of the data identification point behind the idle nozzle to each idle nozzle, the relative position of the data identification point behind the idle nozzle to the blowout preventer, and the laser propagation speed of the data identification point; wherein each idle nozzle is on the cleaning device;

[0071] S500, selecting the nozzle with the shortest distance from the idle nozzle to the blowout preventer;

[0072] S600, the control system controls the selected nozzles on the cleaning equipment to clean the blowout preventer according to the cleaning path and cleaning intensity.

[0073] like Figure 4 The schematic diagram of using a nozzle to clean the sludge on the surface of the blowout preventer is shown in Figure 1. The control system monitors the balance amplitude value of the cleaning equipment in real time during the cleaning process, calculates the balance threshold value based on the balance amplitude value and the normal amplitude value of the cleaning equipment, and determines whether to adjust the cleaning equipment based on the balance threshold value. The calculation method of the balance valve value is: Among them, Y m is the balance threshold of the cleaning equipment, is the balance amplitude value of the cleaning equipment, is the normal amplitude value of the cleaning equipment; if Y m If Y is positive, the cleaning is normal; m If it is a non-positive value, adjust the balance state of the cleaning equipment. The balance of the cleaning equipment mainly refers to the balance state of the cleaning equipment. This step is to prevent the cleaning equipment from tilting and falling.

[0074] Based on the above surface treatment method for blowout preventers with recognizable classification decisions, the method for determining the shadow gray value is as follows:

[0075] g = α × (Max(w1 × w2 × (u1 - u2) × (u1 - u2))) (Formula 1)

[0076] Wherein, g represents the shadow gray value, α represents the adjustment coefficient, which represents the influence of noise and interference on the image; w1 represents the proportion of foreground points in the image; w2 represents the proportion of background points in the image; u1 represents the average gray value of the foreground; u2 represents the average gray value of the background.

[0077] Comparing the shadow gray value with the set gray value interval, classifying the dirty area according to the comparison result, and determining the cleaning intensity according to the classification result of the dirty area specifically includes:

[0078] If 0 < g < a, when the shadow gray value g is greater than zero and lower than the set threshold a, the dirty area is a non-dirty area, and fine treatment with a water pump is adopted; if a < g < b, when the shadow gray value g is greater than the set threshold a and lower than the set threshold b, the dirty area is a lightly dirty area, and fine treatment with a water pump and adding medicine are adopted; if b < g, when the shadow gray value g is greater than the set threshold b, the dirty area is a heavily dirty area, and fine treatment with a water pump, adding medicine, and sandblasting are adopted; g represents the shadow gray value, and a and b are both set values.

[0079] As Figure 5 shown, the planarized image of the blowout preventer is divided into multiple cleaning area grids. Specifically, since the shape structure of most blowout preventers is an irregular polygon, multiple cleaning area grids are formulated for the obtained blowout preventer image, that is, multiple cleaning area grids are formed by dividing the blowout preventer image, and each cleaning area represents an area adhered with impurities. In addition, the sizes of the cleaning area grids can be the same or different, and the shapes of the cleaning area grids can be polygons or various geometric shapes. The cleaning area grids in the embodiments of the present invention are specifically squares, and the square cleaning area grids are convenient for making the cleaning effect of the cleaning component on the impurities in the cleaning area better after setting the cleaning path information.

[0080] Specifically, the specific shape of the cleaning area grid can be set to different shapes. In the embodiments of the present invention, the set image is a square, as Figure 6As shown, since the length of each side in the square cleaning area is consistent, and the length of each side in each square cleaning area is used as the cleaning path, when the cleaning device moves along each side in the square cleaning area, the cleaning component can achieve a better cleaning effect on large-area impurities. The preset condition specifically refers to a complete large path composed of each determined path marking point, which can achieve cleaning processing for the entire cleaning area. If one of the path marking points causes the cleaning device to deviate from the range of the cleaning area when moving, then cancel the path marking point to ensure that the range surrounded by each path marking point is not larger than the range of the cleaning area. For example, since the specific shape of the cleaning area is set to a square image shape, the four corner positions of the square cleaning area are all used as path marking points, that is, the square cleaning area has a total of 4 path marking points. After connecting each path marking point with the adjacent path marking point, the side of the square cleaning area can be obtained. Each side in each square cleaning area is used as a small path, so that the subsequent cleaning equipment moves along each small path first, and each small path forms a complete large path. When the cleaning equipment moves along each small path, the cleaning process of the entire cleaning area is completed.

[0081] Each path marking point is connected in series in sequence to obtain the cleaning path information. Specifically, after the path marking points on each side of the cleaning area are determined, each path marking point is connected in series with the adjacent path marking points to form a cleaning path information. If the specific shape of the cleaning area is set to a square shape, the four corner positions of the cleaning area are set as path marking points, and then the path marking points corresponding to the four corner positions of the cleaning area are connected in series with the adjacent path marking points in sequence, and then the cleaning device moves in the order marked by the path marking points, thereby driving the cleaning component to clean the cleaning area. For example, after the path marking point is determined at one end of each side of the square cleaning area, the cleaning areas of the four corners are formed, and then each path marking point of each cleaning area is marked in order, for example, the first path marking point 11, the second path marking point 12, the third path marking point 13 and the fourth path marking point 14 are marked in the square cleaning area, and then the first path marking point 11 is connected in series with the second path marking point 12, the second path marking point 12 is connected in series with the third path marking point 13, and the third path marking point 13 is connected in series with the fourth path marking point 14, so as to form the cleaning path information. In the process of cleaning impurities, the cleaning device first moves to the first path marking point 11, moves from the first path marking point 11 to the second path marking point 12, then moves from the second path marking point 12 to the third path marking point 13, and then moves from the third path marking point 13 to the fourth path marking point 14, and completes the cleaning of the entire cleaning area in this order.

[0082] Optionally, for each idle nozzle, the method for calculating the distance from each idle nozzle to the surface of the blowout preventer is:

[0083]

[0084] V is the straight-line distance from the idle nozzle to the blowout preventer; 激光 is the speed at which the laser of the data identifier propagates in the air, It is the total time taken for the laser of the data identifier to be projected onto the surface of the BOP and for the laser to be fed back. is the total time taken for the laser to be projected to the idle nozzle and the laser to be fed back, ζ is the angle formed between the ray projected from the data identification point by the laser to the blowout preventer and the ray projected by the laser to the idle nozzle;

[0085] S 距离n =S 识别n sinα n (Formula 3)

[0086] S 距离nis the horizontal distance from the data identification point to the idle nozzle, and α is the angle between the direct position of the data identification point and the horizontal position;

[0087]

[0088] is the horizontal distance from the idle nozzle to the surface of the BOP, is the horizontal distance from the data identification point to the idle nozzle, It is the horizontal distance from the data identification point to the surface of the BOP;

[0089]

[0090] L 距离 is the actual distance from the nth idle nozzle to the surface of the BOP, and β is the inclination angle formed by the nth idle nozzle and the surface of the BOP.

[0091] Optional, such as Figure 7 , the idle nozzles can be combined and switched according to the dirty area recognition result of the blowout preventer, and further, the spray angle and strength of the nozzles can be adjusted according to the location of the dirty area. Specifically, in this embodiment, the idle nozzles are combined by combining multiple idle nozzles according to the category or level of the recognition result; the spray angle and strength of the nozzles are adjusted according to the location of the dirty area and the classification of the dirty area.

[0092] Although the various steps in the above embodiment are described in the above-mentioned order, those skilled in the art can understand that in order to achieve the effect of this embodiment, different steps do not have to be executed in such an order. They can be executed simultaneously (in parallel) or in a reverse order. These simple changes are within the scope of protection of the present invention.

[0093] The second embodiment of the present invention provides a blowout preventer surface treatment system capable of identifiable classification decision making, the system comprising:

[0094] A data acquisition module is used to acquire a surface image of the blowout preventer, identify the surface image of the blowout preventer, and obtain the characteristics of the blowout preventer, a dirty area recognition result, and a dirty area recognition image; the dirty area recognition result includes the position of the dirty area and the shadow gray value of the dirty area;

[0095] An intensity determination module is used to set a plurality of gray value intervals according to the type of dirty area, determine the classification of the dirty area according to the gray value interval in which the shadow gray value is located, and determine the cleaning intensity according to the dirty area classification result;

[0096] A cleaning path determination module is used to establish a virtual BOP model in a simulation interface according to the characteristics of the BOP, and to planarize the virtual BOP model to obtain a planar image of the BOP; the planar image of the BOP is divided into a plurality of cleaning area grids, and the grid lines of the plurality of cleaning area grids are cleaning paths on the surface of the BOP;

[0097] a distance determination module, for calculating the distance from each idle nozzle to the surface of the blowout preventer according to the relative position of the data identification point behind the idle nozzle to each idle nozzle, the relative position of the data identification point behind the idle nozzle to the blowout preventer, and the laser propagation speed of the data identification point; wherein each idle nozzle is on the cleaning device;

[0098] A nozzle selection module is used to select the nozzle with the shortest distance from the idle nozzle to the blowout preventer;

[0099] The cleaning control module is used to control the system to control the selected nozzles on the cleaning equipment to clean the blowout preventer according to the cleaning path and cleaning intensity. During the cleaning process, the balance amplitude value of the cleaning equipment is monitored in real time, and the balance threshold is calculated according to the balance amplitude value and the normal amplitude value of the cleaning equipment. According to the balance threshold, it is determined whether to adjust the cleaning equipment. The calculation method of the balance threshold is:

[0100]

[0101] Among them, Y m is the balance threshold of the cleaning equipment, is the balance amplitude value of the cleaning equipment, is the normal amplitude value of the cleaning equipment;

[0102] If Y m If Y is positive, the cleaning is normal; m If it is a non-positive value, adjust the balance of the cleaning equipment.

[0103] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0104] It should be noted that the system for surface treatment of a blowout preventer with identifiable classification decision-making provided in the above embodiment is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be decomposed or combined. For example, the modules in the above embodiment can be combined into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not regarded as improper limitations of the present invention.

[0105] An electronic device according to a third embodiment of the present invention includes:

[0106] At least one processor; and a memory in communication with the at least one processor; wherein the memory stores instructions executable by the processor, the instructions being executed by the processor to implement the above-mentioned blowout preventer surface treatment method with identifiable classification decision.

[0107] A fourth embodiment of the present invention is a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by a computer to implement the above-mentioned blowout preventer surface treatment method with identifiable classification decision.

[0108] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the storage device and processing device described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0109] Reference below Figure 8 , which shows a schematic diagram of the structure of a computer system of a server for implementing the method, system, and device embodiments of the present application. Figure 8 The server shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0110] like Figure 8As shown, the computer system includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 602 or the program loaded from the storage part 608 to the random access memory (RAM) 603. Various programs and data required for system operation are also stored in the RAM 603. The CPU 601, ROM 602 and RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0111] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed so that a computer program read therefrom is installed into the storage section 608 as needed.

[0112] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the method of the present application are executed. It should be noted that the above-mentioned computer-readable medium of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, an apparatus or a device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, an apparatus or a device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0113] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0114] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0115] The terms "first", "second", etc. are used to distinguish similar objects rather than to describe or indicate a particular order or sequence.

[0116] The term "comprise" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus / device.

[0117] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A blowout preventer surface treatment method capable of identifiable classification decision making, characterized in that: The method includes: Obtain the surface image of the blowout preventer, identify the surface image of the blowout preventer, and obtain the characteristics of the blowout preventer and the recognition result of the dirty area; The recognition result of the dirty area includes the position of the dirty area and the shadow gray value of the dirty area; Set multiple gray value intervals according to the type of the dirty area, determine the classification of the dirty area according to the gray value interval where the shadow gray value is located, and determine the cleaning intensity according to the classification result of the dirty area; Establish a virtual blowout preventer model on the simulation interface according to the characteristics of the blowout preventer, perform planarization processing on the virtual blowout preventer model to obtain a planarized image of the blowout preventer; divide the planarized image of the blowout preventer into multiple cleaning area grids, and the grid lines of the multiple cleaning area grids are the cleaning paths on the surface of the blowout preventer; Calculate the distance from each idle nozzle to the surface of the blowout preventer according to the relative position from the data recognition point behind the idle nozzle to each idle nozzle, the relative position from the data recognition point behind the idle nozzle to the blowout preventer, and the laser propagation speed of the data recognition point; wherein, each idle nozzle is on the cleaning device; Select the nozzle with the shortest distance according to the distance from the idle nozzle to the blowout preventer; The control system controls the selected nozzle on the cleaning device to clean the blowout preventer according to the cleaning path and the cleaning intensity. During the cleaning process, the balance amplitude value of the cleaning device is monitored in real time, the balance threshold is calculated according to the balance amplitude value and the normal amplitude value of the cleaning device, and it is determined whether to adjust the cleaning device according to the balance threshold. The calculation method of the balance threshold is: Among them, Y m is the balance threshold of the cleaning equipment, is the balance amplitude value of the cleaning equipment, is the normal amplitude value of the cleaning equipment; If Y m If Y is positive, the cleaning is normal; m If it is a non-positive value, adjust the balance state of the cleaning equipment.

2. The blowout preventer surface treatment method with identifiable classification decision according to claim 1 is characterized in that: The method for determining the shadow gray value is: g = α × (Max(w1 × w2 × (u1 - u2) × (u1 - u2))); Wherein, g represents the shadow gray value, α represents the adjustment coefficient, which represents the influence of noise and interference on the image; w1 represents the proportion of the number of foreground points in the image to the image; w2 represents the proportion of the number of background points; u1 represents the average gray value of the foreground; u2 represents the average gray value of the background.

3. The blowout preventer surface treatment method with identifiable classification decision according to claim 1 is characterized in that: Setting multiple gray value intervals according to the type of the dirty area, determining the classification of the dirty area according to the gray value interval where the shadow gray value is located, and determining the cleaning intensity according to the classification result of the dirty area specifically includes: If 0 < g < a, when the shadow gray value g is greater than zero and lower than the set threshold a, the dirty area is a non-dirty area, and fine processing by the water pump is adopted; If a < g < b, when the shadow gray value g is greater than the set threshold a and lower than the set threshold b, the dirty area is a lightly dirty area, and fine processing by the water pump and adding medicine are adopted; If b < g, when the shadow gray value g is greater than the set threshold b, the dirty area is a heavily dirty area, and fine processing by the water pump, adding medicine, and sandblasting are adopted; g represents the shadow gray value, and a and b are both set values.

4. The blowout preventer surface treatment method with identifiable classification decision according to claim 1 is characterized in that: For each idle nozzle, the method for calculating the distance from each idle nozzle to the surface of the blowout preventer is: V is the straight-line distance from the idle nozzle to the blowout preventer; 激光 is the speed at which the laser of the data identifier propagates in the air, It is the total time taken for the laser of the data identifier to be projected onto the surface of the BOP and for the laser to be fed back. is the total time taken for the laser to be projected to the idle nozzle and the laser to be fed back, ζ is the angle formed between the ray projected from the data identification point by the laser to the blowout preventer and the ray projected by the laser to the idle nozzle; S 距离n =S 识别n sinα n ; S 距离n is the horizontal distance from the data identification point to the idle nozzle, and α is the angle between the direct position of the data identification point and the horizontal position; is the horizontal distance from the idle nozzle to the surface of the BOP, is the horizontal distance from the data identification point to the idle nozzle, It is the horizontal distance from the data identification point to the surface of the BOP; L 距离 is the actual distance from the nth idle nozzle to the surface of the BOP, and β is the inclination angle formed by the nth idle nozzle and the surface of the BOP.

5. The blowout preventer surface treatment method with identifiable classification decision according to claim 1 is characterized in that: Selecting the nozzle with the shortest distance according to the distance from the idle nozzle to the blowout preventer mainly includes: Select the optimal nozzle through the bubble algorithm; The formula for the bubbling algorithm is: Compare them in pairs, arrange them in order from small to large, and select the idle nozzle corresponding to the smallest distance to clean the BOP; in, is the distance from the first idle nozzle to the surface of the BOP; is the distance from the second idle nozzle to the surface of the BOP; is the distance from the third idle nozzle to the surface of the BOP; is the distance from the nth idle nozzle to the surface of the BOP.

6. The blowout preventer surface treatment method with identifiable classification decision according to claim 5 is characterized in that: According to the recognition result of the dirty area of the blowout preventer, combine the idle nozzles and adjust the spraying angle and strength of the nozzles.

7. A blowout preventer surface treatment system capable of identifiable classification decision making, characterized in that: The system includes: A data acquisition module, which is used to obtain the surface image of the blowout preventer, identify the surface image of the blowout preventer, and obtain the characteristics of the blowout preventer and the recognition result of the dirty area; The dirty area recognition result includes the position of the dirty area and the shadow gray value of the dirty area; An intensity determination module is used to set a plurality of gray value intervals according to the type of dirty area, determine the classification of the dirty area according to the gray value interval in which the shadow gray value is located, and determine the cleaning intensity according to the dirty area classification result; A cleaning path determination module is used to establish a virtual BOP model in a simulation interface according to the characteristics of the BOP, and to planarize the virtual BOP model to obtain a planar image of the BOP; the planar image of the BOP is divided into a plurality of cleaning area grids, and the grid lines of the plurality of cleaning area grids are cleaning paths on the surface of the BOP; a distance determination module, for calculating the distance from each idle nozzle to the surface of the blowout preventer according to the relative position of the data identification point behind the idle nozzle to each idle nozzle, the relative position of the data identification point behind the idle nozzle to the blowout preventer, and the laser propagation speed of the data identification point; wherein each idle nozzle is on the cleaning device; A nozzle selection module is used to select the nozzle with the shortest distance from the idle nozzle to the blowout preventer; The cleaning control module is used to control the system to control the selected nozzles on the cleaning equipment to clean the blowout preventer according to the cleaning path and cleaning intensity. During the cleaning process, the balance amplitude value of the cleaning equipment is monitored in real time, and the balance threshold is calculated according to the balance amplitude value and the normal amplitude value of the cleaning equipment. According to the balance threshold, it is determined whether to adjust the cleaning equipment. The calculation method of the balance threshold is: Among them, Y m is the balance threshold of the cleaning equipment, is the balance amplitude value of the cleaning equipment, is the normal amplitude value of the cleaning equipment; If Y m If Y is positive, the cleaning is normal; m If it is a non-positive value, adjust the balance of the cleaning equipment.

8. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to at least one processor; wherein, The memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the method for surface treatment of a blowout preventer with identifiable classification decision as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by a computer to implement the method for surface treatment of a blowout preventer with identifiable classification decision as described in any one of claims 1-7.

Images