Marine operation towing obstacle avoidance method and device, electronic equipment and storage medium

Abstract

The invention discloses a marine operation drag cable obstacle avoidance method and device, electronic equipment and a storage medium. The method comprises the following steps: determining obstacle state information of a target sea area, first state data of an earthquake acquisition system and environmental data; matching a target control instruction generation strategy from the candidate control instruction generation strategies according to the obstacle state information; determining a target control instruction through a target control instruction generation strategy according to the obstacle state information, the first state data of the seismic acquisition system and the environment data; and controlling the transverse control bird and / or the compass bird according to the target control instruction, and driving the operation towing cable to avoid the obstacle. According to the method, different control instruction generation strategies are matched according to different obstacle types, the control instruction is generated according to the control instruction generation strategies, the transverse control bird and / or the compass bird are / is controlled, the operation towing cable is driven to avoid the obstacle, the operation efficiency of the operation towing cable is improved, and meanwhile, the operation cost is reduced. And the obstacle avoidance accuracy of the marine workboat is also improved.

Description

Technical Field

[0001] The present invention relates to the field of marine exploration technology, and in particular to a method, device, electronic equipment and storage medium for marine operation towing and obstacle avoidance. Background Art

[0002] During the offshore towing operation, especially during the offshore three-dimensional seismic towing operation, it is common to encounter interference from obstacles such as drilling platforms, fishing boats, cargo ships, and offshore buoys. The presence of offshore obstacles will not only interfere with the normal operation of the seismic operation ship along the planned survey line, but also affect the quality of the collected data. In order to avoid obstacles during the operation, the existing technology obtains an obstacle avoidance plan based on artificial experience after detecting the existence of obstacles. The obstacle avoidance plan obtained based on artificial experience usually gives an operation towing sinking depth based on artificial experience, and controls the compass bird to sink the operation towing to the sinking depth, or the seismic operation ship tows the operation towing to bypass the obstacles at a long distance, thereby directly abandoning the collection of the current survey line. This will not only waste the precious offshore operation window period, but also cause a waste of resources. Summary of the invention

[0003] The present invention provides a method, device, electronic equipment and storage medium for avoiding obstacles in marine towing operations, so as to solve the problem of waste of resources caused by untimely avoidance when encountering obstacles.

[0004] According to one aspect of the present invention, there is provided a method for avoiding obstacles during towing in marine operations, comprising:

[0005] Determine the obstacle status information, first status data of the seismic acquisition system and environmental data of the target sea area; the obstacle status information is used to characterize the type of obstacles in the target sea area and the corresponding operating status of the obstacles; the first status data of the seismic acquisition system is used to characterize the operating status data of the seismic acquisition system in the target sea area; the environmental data is used to characterize the data of the natural environment in which the target sea area is located; the seismic acquisition system includes: a seismic operation ship and an operation tug; the seismic operation ship is equipped with the operation tug; the operation tug is equipped with a lateral control bird and a compass bird;

[0006] Matching a target control instruction generation strategy from candidate control instruction generation strategies according to the obstacle state information; the target control instruction generation strategy is used to generate target control instructions for the lateral control bird and / or compass bird; the target control instruction is used to control the lateral control bird and / or compass bird to drive the work tow truck to avoid obstacles; the target control instruction includes at least one of a first target control instruction, a second target control instruction and a third target control instruction; the first target control instruction is used to control the lateral control bird to drive the work tow truck to avoid fixed-position objects; the second target control instruction is used to control the lateral control bird to drive the work tow truck to avoid floating objects; the third target control instruction is used to control the lateral control bird and the compass bird to drive the work tow truck to avoid fast-moving objects;

[0007] Determining a target control instruction through the target control instruction generation strategy according to the obstacle state information, the first state data of the seismic acquisition system and the environmental data;

[0008] The lateral control bird and / or the compass bird are controlled according to the target control instruction to drive the working tractor to avoid obstacles.

[0009] According to another aspect of the present invention, there is provided a marine operation towing obstacle avoidance device, comprising:

[0010] A data determination module is used to determine obstacle status information, first state data of the seismic acquisition system and environmental data of the target sea area; the obstacle status information is used to characterize the types of obstacles in the target sea area and the corresponding operating states of the obstacles; the first state data of the seismic acquisition system is used to characterize the operating state data of the seismic acquisition system in the target sea area; the environmental data is used to characterize the data of the natural environment in which the target sea area is located; the seismic acquisition system includes: a seismic operation ship and an operation tug; the seismic operation ship is equipped with the operation tug; the operation tug is equipped with a lateral control bird and a compass bird;

[0011] a target control instruction generation strategy determination module, used for matching a target control instruction generation strategy from candidate control instruction generation strategies according to the obstacle state information; the target control instruction generation strategy is used to generate a target control instruction for the lateral control bird and / or the compass bird; the target control instruction is used to control the lateral control bird and / or the compass bird to drive the work tow truck to avoid obstacles; the target control instruction includes at least one of a first target control instruction, a second target control instruction and a third target control instruction; the first target control instruction is used to control the lateral control bird to drive the work tow truck to avoid fixed position objects; the second target control instruction is used to control the lateral control bird to drive the work tow truck to avoid floating objects; the third target control instruction is used to control the lateral control bird and the compass bird to drive the work tow truck to avoid fast-moving objects;

[0012] A target control instruction determination module, configured to determine a target control instruction through the target control instruction generation strategy according to the obstacle state information, the first state data of the seismic acquisition system and the environmental data;

[0013] A control module is used to control the lateral control bird and / or the compass bird according to the target control instruction, so as to drive the working tractor to avoid obstacles.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the marine operation towing obstacle avoidance method described in any embodiment of the present invention.

[0018] According to another 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 enable a processor to implement the marine operation towing obstacle avoidance method described in any embodiment of the present invention when executed.

[0019] The technical solution of the embodiment of the present invention determines the obstacle status information, the first state data of the seismic acquisition system and the environmental data of the target sea area; matches the target control instruction generation strategy from the candidate control instruction generation strategies according to the obstacle status information, so as to realize matching the corresponding control instruction generation strategy according to the specific obstacle type, thereby avoiding the problem that only a single control instruction generation strategy is used, resulting in the generated control instructions being unable to accurately avoid obstacles; determines the target control instruction through the target control instruction generation strategy according to the obstacle status information, the first state data of the seismic acquisition system and the environmental data, so as to ensure that the control instruction is generated using the control instruction generation strategy exclusive to the current obstacle type, thereby greatly improving the generation efficiency of the control instruction; controls the lateral control bird and / or the compass bird according to the target control instruction, drives the operation towing to avoid obstacles, reduces manual participation, makes the obtained avoidance plan more in line with the objective environment, effectively utilizes the marine operation window period, and improves the operation efficiency of the marine lateral control bird and the compass bird. The method matches different control instruction generation strategies according to different obstacle types, generates control instructions according to the control instruction generation strategies, and controls the lateral control bird and / or the compass bird to drive the operating towing vessel to avoid obstacles, thereby improving the operating towing efficiency and the accuracy of the marine operating vessel in avoiding obstacles.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 A flow chart of a method for towing and avoiding obstacles in marine operations provided by an embodiment of the present invention;

[0023] Figure 2 A flow chart for generating a first target control instruction provided by an embodiment of the present invention;

[0024] Figure 3 A flow chart of generating a second target control instruction provided by an embodiment of the present invention;

[0025] Figure 4 A flowchart of generating a third target control instruction provided by an embodiment of the present invention;

[0026] Figure 5 A schematic diagram of the structure of a towing obstacle avoidance device for marine operations provided by an embodiment of the present invention;

[0027] Figure 6 A schematic diagram of the structure of an electronic device for implementing the marine operation towing obstacle avoidance method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Figure 1 This is a flow chart of a method for avoiding obstacles in a towing vessel for marine operation provided by an embodiment of the present invention. This embodiment can be applied to the case where a towing vessel for marine operation encounters obstacles and avoids obstacles by matching different avoidance modes to different obstacles. This method can be executed by an obstacle avoidance device for a towing vessel for marine operation. The obstacle avoidance device for a towing vessel for marine operation can be implemented in the form of hardware and / or software. The obstacle avoidance device for a towing vessel for marine operation can be configured in any electronic device with network communication function. Figure 1 As shown, the method includes:

[0031] S110, determining obstacle status information of the target sea area, first status data of the seismic acquisition system, and environmental data.

[0032] Among them, the obstacle status information is used to characterize the type of obstacles in the target sea area and the corresponding operating status of the obstacles.

[0033] Furthermore, the obstacle status information includes: obstacle type and operation status data corresponding to the obstacle. Among them, obstacle types include: fixed position objects, floating objects and fast-moving objects. Solid position objects usually include fixed operating ships, drilling platforms, fishing nets, etc. Floating objects are usually buoys. Fast-moving objects usually include fast-moving cargo ships or passenger ships.

[0034] Furthermore, the running status data corresponding to the obstacle includes at least: the obstacle position and the obstacle size. Different obstacle types have different obstacle status information. When the obstacle type is a fixed-position object, the running status data corresponding to the obstacle includes at least the position and size of the fixed-position object; when the obstacle type is a floating object, the running status data corresponding to the obstacle includes at least the position, moving speed and moving direction of the floating object; when the obstacle type is a fast-moving object, the running status data corresponding to the obstacle includes at least the position, moving speed and moving direction of the fast-moving object.

[0035] The above steps classify obstacles because the stern of the seismic operation ship tows at least one long operation towboat. Fixed objects, floating objects and fast-moving objects at sea greatly interfere with offshore seismic operations, and different obstacles move at different speeds. Therefore, using the same method to generate avoidance plans will not only affect the quality of collected data, but also affect the data collection of the seismic acquisition system along the planned survey line. In addition, it may also cause the operation towboat to fail to avoid obstacles in time.

[0036] The first state data of the seismic acquisition system is used to characterize the operating state data of the seismic acquisition system in the target sea area.

[0037] Furthermore, the first state data of the seismic acquisition system at least includes the current position, moving direction and moving speed of the seismic operation vessel, as well as the state information of the depth-fixing orienteering device and the operation towing structure diagram. The depth-fixing orienteering device includes a compass bird and a lateral control bird, and the depth-fixing orienteering device is configured on the operation towing. The state information of the depth-fixing orienteering device is the current wing angle of the compass bird and the lateral control bird. The operation towing structure diagram, that is, the distribution of the lateral control bird and the compass bird, the towing structure data is the connection structure of each acquisition section in the towing cable and the interface point of the compass bird and the lateral control bird.

[0038] The seismic acquisition system includes: a seismic operation ship and an operation tug. The seismic operation ship is equipped with an operation tug. The operation tug is equipped with a lateral control bird and a compass bird.

[0039] Furthermore, the seismic acquisition system is usually composed of a seismic operation vessel, a seismic data acquisition system, a navigation and positioning system, and an operation tow. When performing marine seismic exploration operations, at least one operation tow and at least one group of seismic sources are usually towed at the stern of the seismic operation vessel. Each operation tow is equipped with multiple compass birds and multiple lateral control birds to control the posture of the operation tow. Among them, the compass bird is used to control the depth of the operation tow. By receiving control instructions, the angle of the compass bird's wings is adjusted, and the operation tow is sunk to a preset depth; the lateral control bird is used to control the lateral offset of the operation tow. By receiving control instructions, the angle of the lateral control bird's wings is adjusted, and the operation tow is kept on the preset survey line. At the same time, head and tail marks are also arranged on the operation tow to locate the operation tow.

[0040] Among them, environmental data is used to characterize the natural environment of the target sea area.

[0041] Specifically, the radar data obtained by the radar sensor is used to determine whether there are obstacles in the target sea area where the seismic operation ship is operating. If there are obstacles, the obstacle status information is determined based on the radar data. The operating environment data such as sea current, tide, wind force, etc. in the target sea area of ​​the operation are mined through meteorological data. The first state data of the seismic acquisition system is obtained through the sensor configured on the acquisition system.

[0042] S120 . Match a target control instruction generation strategy from candidate control instruction generation strategies according to obstacle state information.

[0043] Among them, the target control instruction generation strategy is used to generate target control instructions for the lateral control bird and / or the compass bird.

[0044] The target control instruction is used to control the lateral control bird and / or the compass bird to drive the working tractor to avoid obstacles. The target control instruction includes at least one of the first target control instruction, the second target control instruction and the third target control instruction.

[0045] Among them, the first target control instruction is used to control the lateral control bird to drive the working towing to avoid fixed-position objects. The second target control instruction is used to control the lateral control bird to drive the working towing to avoid floating objects. The third target control instruction is used to control the lateral control bird and the compass bird to drive the working towing to avoid fast-moving objects.

[0046] Specifically, when receiving the obstacle state information, the server matches the target control instruction generation strategy from the candidate control instruction generation strategies according to the obstacle type included in the obstacle state information.

[0047] Furthermore, when the obstacle type label is a fixed-position object, the first target control instruction generation strategy is matched; when the obstacle type is a floating object, the second target control instruction generation strategy is matched; when the obstacle type is a fast-moving object, the third target control instruction generation strategy is matched.

[0048] Furthermore, a mapping relationship between obstacle types and candidate control instruction generation strategies is pre-set in the server, as shown in Table 1:

[0049] Table 1 Mapping relationship between obstacle types and candidate control instruction generation strategies

[0050] Obstacle Type Candidate control instruction generation strategy Fixed position objects The first target control instruction generation strategy Floating Objects Second target control instruction generation strategy Fast moving objects The third target control instruction generation strategy

[0051] In the above steps, the construction of the candidate control instruction generation strategy not only takes into account the obstacle state information and the first state data of the seismic acquisition system, but also takes into account the environmental information of the seismic acquisition system, which further makes the obtained avoidance plan conform to the objective environment and improves the accuracy of obstacle avoidance.

[0052] S130, determining a target control instruction through a target control instruction generation strategy according to the obstacle state information, the first state data of the seismic acquisition system and the environmental data.

[0053] Specifically, according to the target control instruction generation strategy, corresponding data is selected from the obstacle state information, the first state data of the seismic acquisition system and the environmental data, and the selected data is calculated through the target control instruction to obtain the target control instruction.

[0054] Furthermore, since there may be simultaneous operations, that is, there may be not only cargo ships but also fishing boats and fishing nets in the target sea area, or there may be drilling platforms in the target sea area, which may cause different types of fault objects to be encountered near the survey line of the seismic operation ship at the same time. Therefore, the target control instruction may include one or more of the first target control instruction, the second target control instruction and the third target control instruction.

[0055] In the above steps, different control instruction generation strategies are designed according to different types of obstacles, and control instructions for avoiding corresponding obstacles are generated according to the control instruction generation strategies, so that obstacle avoidance instructions can be quickly obtained.

[0056] S140. Control the lateral control bird and / or the compass bird according to the target control instruction to drive the working tractor to avoid obstacles.

[0057] Specifically, the target control instruction adjusts the wing angles of each lateral control bird and / or compass bird configured on the work trailer to drive the work trailer away from obstacles.

[0058] The above steps obtain target control instructions, so that the lateral control bird and / or the compass bird control the operating tow cable to avoid obstacles according to the target control instructions. Since human participation is reduced, the obtained avoidance plan is more in line with the objective environment, the marine operation window period is effectively utilized, the efficiency of marine seismic operations is improved, and the waste of manpower, material resources and financial resources is greatly saved.

[0059] Optionally, determining obstacle status information of the target sea area includes steps A1-A3:

[0060] Step A1: Acquire radar data in the target sea area.

[0061] Specifically, radar data within the target sea area is obtained by performing real-time scanning within the radar scanning fence.

[0062] Furthermore, the range of the radar scanning fence can be set manually or automatically. That is, when the radar scanning fence is set manually, a user interface is provided for inputting the fence size; when the radar scanning fence is set automatically, the fence size is calculated by the calculation model and the fence size value is automatically filled in.

[0063] Furthermore, the setting of the scanning fence needs to comprehensively consider the length, width, and width of the source group of the towline.

[0064] Step A2: Determine whether there are obstacles in the target sea area based on radar data.

[0065] Specifically, the recognition algorithm is used to determine in real time whether there are suspected obstacles in the fence based on radar data.

[0066] Among them, the recognition algorithm can adopt support vector machine (SVM), decision tree, random forest, neural network and other algorithms.

[0067] Step A3: If there is an obstacle, determine the obstacle status information according to the obstacle change data in the radar data.

[0068] Specifically, if there is an obstacle, an early warning is issued, and the obstacle status information is determined based on the changing state of the obstacle in the radar data.

[0069] Exemplarily, if an obstacle is detected and the radar data corresponding to the obstacle always remains within the corresponding range, the obstacle is considered to be a fixed-position object, and the location information of the fixed-position object is obtained; if an obstacle is detected and the position of the radar data corresponding to the obstacle is constantly changing in a certain direction, but the change is not fast, the obstacle is considered to be a floating object, and the position, moving speed and moving direction of the floating object are determined according to the changes in the radar data corresponding to the floating object; if an obstacle is detected and the position of the radar data corresponding to the obstacle is constantly changing in a certain direction, but the change is rapid, the obstacle is considered to be a fast-moving object, and the position, moving speed and moving direction of the fast-moving object are determined according to the changes in the radar data corresponding to the fast-moving object.

[0070] Furthermore, the type of obstacle can also be determined manually, that is, when it is determined that there is an obstacle, it is manually determined whether the obstacle is a real obstacle. That is, when there is an alarm prompt for an obstacle, it is manually determined whether the obstacle is a real obstacle through observation, high-frequency calling and other manual methods. Among them, observation is to observe the location of the obstacle through a telescope configured on the seismic operation ship to observe whether it is a real obstacle; high-frequency calling is to call a ship suspected of being an obstacle through a walkie-talkie, and determine whether it is a real obstacle through the replied location information. When it is a real obstacle, the obstacle type label is set, and the obstacle status information is collected.

[0071] Furthermore, the obstacle type may be set by selecting through a user interface or directly inputting the setting.

[0072] Among them, the real obstacles can be artificially constructed objects and configured in the target sea area.

[0073] Optionally, determining the target control instruction through a target control instruction generation strategy according to the obstacle state information, the first state data of the seismic acquisition system and the environmental data includes steps B1-B7:

[0074] Step B1, acquiring the angle data of the lateral control bird, the distribution and towing structure data of the lateral control bird and the compass bird, and the operation data of the seismic operation vessel from the first state data of the seismic acquisition system.

[0075] Specifically, if the obstacle is a fixed-position object, the angle data of the lateral control bird, the distribution and towing structure data of the lateral control bird and the compass bird, and the operation data of the seismic operation vessel are obtained from the first state data of the seismic acquisition system.

[0076] Exemplarily, when the obstacle type is a fixed-position object, the position and size of the fixed-position object are obtained from the obstacle status information; the ocean current velocity data is obtained from the operating environment information; and the position of the seismic operation ship, the moving direction of the seismic operation ship, and the moving speed of the seismic operation ship are obtained from the first state data of the seismic acquisition system.

[0077] Step B2: construct a first undirected graph according to the angle data of the lateral control bird and the distribution and dragging structure data of the lateral control bird and the compass bird.

[0078] Among them, the first undirected graph is used to represent the distribution of the wings of the lateral control bird.

[0079] Specifically, the adjacent lateral control birds in the distribution drag structure data of the lateral control bird and the compass bird are connected by edges, and the lateral control bird is used as the node V in the first undirected graph. (1) , adjacent nodes are connected into edges E (1) , horizontally controls the angle of the bird's wings and forms the node attribute X (1) , the distance between nodes constitutes the weight W (1) .

[0080] Step B3: Encode the operation data of the seismic operation vessel and the state data of the fixed position object through the first data encoding layer to obtain a first sub-feature vector.

[0081] The first data coding layer is used to construct the relationship between the first state data of the seismic acquisition system and the obstacle state information.

[0082] Furthermore, the first data encoding layer may adopt a domain dictionary model, which is obtained by training the BERT pre-trained language model using domain data, specifically by training the BERT pre-trained language model using historical domain data.

[0083] Exemplarily, the position and size of the fixed position object, as well as the position, moving direction and moving speed of the seismic operation ship are encoded through the first sub-coding layer to obtain the first sub-feature vector

[0084]

[0085] in, They respectively represent the position of the seismic operation ship, the moving direction of the seismic operation ship, the moving speed of the seismic operation ship, the position of the fixed-position object and the size of the fixed-position object; the position can be in the form of latitude and longitude data or geographic coordinate position data, and the size can be in the form of length, width and height data.

[0086] Step B4: Encode the first undirected graph through an image coding layer to obtain a second sub-feature vector.

[0087] The image coding layer is used to construct the distribution relationship between the lateral control birds and / or the compass birds in the undirected graph.

[0088] Specifically, the first undirected graph is input into the image coding layer for encoding to obtain the second sub-feature vector.

[0089] Furthermore, the second sub-eigenvector can be expressed by the following formula:

[0090]

[0091] Among them, σ represents the activation function; I represents the identity matrix; Indicates based on The corresponding degree matrix obtained; A (1) is the adjacency matrix constructed according to the first undirected graph.

[0092] Step B5: Encode the ocean current data through the second data encoding layer to obtain a third sub-feature vector.

[0093] The second data encoding layer is used to construct the relationship between environmental data.

[0094] Specifically, the ocean current velocity data is input into the second data encoding layer for encoding to obtain a third sub-eigenvector.

[0095] Furthermore, the third sub-eigenvector can be expressed by the following formula:

[0096]

[0097] in, Indicates the speed of ocean current.

[0098] Step B6: determine the first eigenvector according to the first sub-eigenvector, the second sub-eigenvector and the third sub-eigenvector.

[0099] Specifically, the first sub-feature vector, the second sub-feature vector and the third sub-feature vector are fused to obtain the first feature vector.

[0100] Step B7: Decode the first feature vector to obtain a first target control instruction.

[0101] Among them, the first target control instruction is used to control the lateral control bird to adjust the angle.

[0102] Specifically, the first feature vector is decoded by the first decoding layer to obtain the first target control instruction.

[0103] Among them, the first decoding layer adopts a bidirectional long short-term memory neural network, and decodes the first feature vector through the bidirectional long short-term memory neural network.

[0104] Furthermore, the first target control instruction can be expressed by the following formula:

[0105] ANGLE (1) =BI_LSTM(H (1) ).

[0106] For example, assuming ANGLE (1) =(6.0, 7.5, 12.5, 15, ...), which means that the angle that needs to be adjusted for the first lateral control bird is 6.5, the angle that needs to be adjusted for the second one is 7.5, and so on.

[0107] For example, Figure 3 As shown, when the obstacle type is a fixed-position object, the position and size of the fixed-position object are obtained from the obstacle state information, the ocean current velocity data is obtained from the operating environment information, and the position of the seismic operation ship, the moving direction of the seismic operation ship, and the moving speed of the seismic operation ship are obtained from the first state data of the seismic acquisition system. The position of the fixed-position object, the size of the fixed-position object, the position of the seismic operation ship, the moving direction of the seismic operation ship, and the moving speed of the seismic operation ship are input into the first data encoding layer for encoding to obtain the first sub-feature vector; the first undirected graph constructed according to the angle data of the lateral control bird, the distribution and towing structure data of the lateral control bird and the compass bird is input into the image encoding layer for encoding to obtain the second sub-feature vector; the ocean current velocity data is input into the second data encoding layer for encoding to obtain the third sub-feature vector. The first sub-feature vector, the second sub-feature vector, and the third sub-feature vector are fused to obtain the first feature vector, and the first feature vector is decoded by the first decoding layer to obtain the first target control instruction.

[0108] Optionally, determining the target control instruction through a target control instruction generation strategy according to the obstacle state information, the first state data of the seismic acquisition system and the environmental data includes steps C1-C7:

[0109] Step C1, acquiring angle data of the lateral control bird, distribution and towing structure data of the lateral control bird and the compass bird, and operation data of the seismic operation vessel from the first state data of the seismic acquisition system.

[0110] Specifically, if the obstacle is a floating object, the angle data of the lateral control bird, the distribution and towing structure data of the lateral control bird and the compass bird, and the operation data of the seismic operation vessel are obtained from the first state data of the seismic acquisition system.

[0111] Exemplarily, when the obstacle type is a floating object, the position of the floating object, the moving speed of the floating object and the moving direction of the floating object are obtained from the obstacle status information; the ocean current velocity data and wind data are obtained from the operating environment information; and the position of the seismic operation ship, the moving direction of the seismic operation ship and the moving speed of the seismic operation ship are obtained from the first status data of the seismic acquisition system.

[0112] Step C2: construct a second undirected graph according to the angle data of the lateral control bird and the distribution and dragging structure data of the lateral control bird and the compass bird.

[0113] Among them, the second undirected graph is used to represent the distribution of the wings of the lateral control bird.

[0114] Specifically, the adjacent lateral control birds in the distribution drag structure data of the lateral control birds and the compass birds are connected by edges, and the lateral control birds are used as nodes V in the undirected graph. (2) , adjacent nodes are connected into edges E (2) , horizontally controls the angle of the bird's wings and forms the node attribute X (2) , the distance between nodes constitutes the weight W (2) The construction method of the second undirected graph is the same as that of the first undirected graph.

[0115] Step C3: Encode the operation data of the seismic operation vessel and the state data of the floating object through the first data encoding layer to obtain a fourth sub-eigenvector.

[0116] Specifically, the position, moving speed and moving direction of the floating object, as well as the position, moving direction and moving speed of the seismic operation vessel are encoded through the first data encoding layer to obtain the fourth sub-eigenvector

[0117]

[0118] in, They respectively represent the position of the seismic operation ship, the moving direction of the seismic operation ship, the moving speed of the seismic operation ship, the position of the floating object, the moving direction of the floating object and the moving speed of the floating object.

[0119] Step C4: Encode the second undirected graph through an image coding layer to obtain a fifth sub-feature vector.

[0120] Specifically, the second undirected graph is input into the image coding layer for encoding to obtain the fifth sub-feature vector.

[0121] Furthermore, the fifth sub-eigenvector can be expressed by the following formula:

[0122]

[0123] Among them, σ represents the activation function; I represents the identity matrix; Indicates based on The corresponding degree matrix obtained; A (2) is the adjacency matrix constructed according to the second undirected graph.

[0124] Step C5: Encode the ocean current data and wind data through the second data encoding layer to obtain a sixth sub-eigenvector.

[0125] Specifically, the ocean current velocity data is input into the second data encoding layer for encoding to obtain the sixth sub-eigenvector.

[0126] Furthermore, the sixth sub-eigenvector can be expressed by the following formula:

[0127]

[0128] in, Indicates the speed of ocean current; Indicates wind speed.

[0129] Step C6: determine the second eigenvector according to the fourth sub-eigenvector, the fifth sub-eigenvector and the sixth sub-eigenvector.

[0130] Specifically, the fourth sub-eigenvector, the fifth sub-eigenvector and the sixth sub-eigenvector are fused to obtain the second eigenvector.

[0131] Step C7: decode the second feature vector to obtain a second target control instruction.

[0132] Among them, the second target control instruction is used to control the lateral control bird to adjust the angle.

[0133] Specifically, the second feature vector is decoded by the second decoding layer to obtain the second target control instruction.

[0134] Furthermore, the second target control instruction can be expressed by the following formula:

[0135] ANGLE (2) =BI_LSTM(H (2) ).

[0136] For example, assuming ANGLE (2) =(2.0, 3.5, 5.5, 7.0, ...), which means that the angle that needs to be adjusted for the first lateral control bird is 2.0, the angle that needs to be adjusted for the second one is 3.5, and so on.

[0137] For example, Figure 4As shown, when the obstacle type is a floating object, the position, moving speed and moving direction of the floating object are obtained from the obstacle state information, the ocean current velocity data and wind data are obtained from the operating environment information, and the position, moving direction and moving speed of the seismic operation ship are obtained from the first state data of the seismic acquisition system. The position, moving speed, moving direction of the floating object, the position, moving direction and moving speed of the seismic operation ship are input into the first data coding layer for encoding to obtain the fourth sub-eigenvector; the second undirected graph constructed according to the angle data of the lateral control bird, the distribution and towing structure data of the lateral control bird and the compass bird is input into the image coding layer for encoding to obtain the fifth sub-eigenvector; the ocean current velocity data and wind data are input into the second data coding layer for encoding to obtain the sixth sub-eigenvector. The fourth sub-eigenvector, the fifth sub-eigenvector and the sixth sub-eigenvector are fused to obtain the second eigenvector, and the second eigenvector is decoded by the second decoding layer to obtain the second target control instruction.

[0138] Optionally, determining the target control instruction through a target control instruction generation strategy according to the obstacle state information, the first state data of the seismic acquisition system and the environmental data includes steps D1-D7:

[0139] Step D1, obtaining the angle data of the compass bird, the angle data of the lateral control bird, the distribution and towing structure data of the lateral control bird and the compass bird, and the operation data of the seismic operation vessel from the first state data of the seismic acquisition system.

[0140] Specifically, if the obstacle is a fast-moving object, the angle data of the lateral control bird, the distribution and towing structure data of the lateral control bird and the compass bird, and the operation data of the seismic operation vessel are obtained from the first state data of the seismic acquisition system.

[0141] Exemplarily, when the obstacle type is a fast-moving object, the position, moving speed and moving direction of the fast-moving object are obtained from the obstacle status information; the ocean current velocity data and wind data are obtained from the operating environment information; and the position, moving direction and moving speed of the seismic operation ship are obtained from the first status data of the seismic acquisition system.

[0142] Step D2: construct a third undirected graph according to the angle data of the compass bird, the angle data of the lateral control bird, and the distribution and dragging structure data of the lateral control bird and the compass bird.

[0143] Among them, the third undirected graph is used to represent the wing distribution of the lateral control bird and the compass bird.

[0144] Specifically, all lateral control birds and compass birds in the distribution drag structure data of lateral control birds and compass birds are edge-connected, and the lateral control birds and compass birds are used as nodes V in the third undirected graph. (3) , adjacent nodes are connected into edges E (3) , the horizontal control bird angle and the compass bird angle constitute the node attribute X (3) , X (3) The wing angles of all lateral control birds and all compass birds are included, and the distance between nodes constitutes the weight W (3) .

[0145] Step D3: Encode the operation data of the seismic operation vessel and the state data of the fast-moving object through the first data encoding layer to obtain the seventh sub-eigenvector.

[0146] Specifically, the position, moving speed and moving direction of the fast-moving object, as well as the position, moving direction and moving speed of the seismic operation ship are input into the first data encoding layer for encoding to obtain the seventh sub-eigenvector

[0147]

[0148] in, They respectively represent the position of the seismic operation ship, the moving direction of the seismic operation ship, the moving speed of the seismic operation ship, the position of the fast-moving object, the moving direction of the fast-moving object, and the moving speed of the fast-moving object.

[0149] Step D4: Encode the third undirected graph through an image coding layer to obtain an eighth sub-eigenvector.

[0150] Specifically, the third undirected graph is input into the image coding layer for encoding to obtain the eighth sub-feature vector.

[0151] Furthermore, the eighth sub-eigenvector Specifically:

[0152]

[0153] Among them, σ represents the activation function; I represents the identity matrix, Indicates based on The corresponding degree matrix obtained; A (3) is the adjacency matrix constructed according to the third undirected graph.

[0154] Step D5: Encode the ocean current data and wind data through the second data encoding layer to obtain a ninth sub-eigenvector.

[0155] Specifically, the ocean current data and the wind data are input into the second data encoding layer for encoding to obtain a ninth sub-eigenvector.

[0156] Furthermore, the ninth sub-eigenvector It can be expressed by the following formula:

[0157]

[0158] in, represents the speed of the ocean current, Indicates wind speed.

[0159] Step D6, determining a third eigenvector according to the seventh sub-eigenvector, the eighth sub-eigenvector and the ninth sub-eigenvector.

[0160] Specifically, the seventh sub-eigenvector, the eighth sub-eigenvector and the ninth sub-eigenvector are fused to obtain the third eigenvector.

[0161] Furthermore, the third eigenvector can be expressed as follows:

[0162]

[0163] Step D7: decode the third characteristic vector to obtain a third target control instruction.

[0164] Among them, the third target control instruction is used to control the lateral control bird and the compass bird to adjust the angle.

[0165] Specifically, the third feature vector is decoded by the third decoding layer to obtain a third target control instruction.

[0166] Exemplarily, the third target control instruction can be expressed by the following formula:

[0167] ANGLE (3) =ATTENTION_BI_LSTM(H (3) ).

[0168] For example, assuming ANGLE (3) =(2.0, -2.1, 2.5, -3.0, 5, -5.5, 7.0, ...), which means that the angle that needs to be adjusted for the first lateral control bird is 2.0, the angle that needs to be adjusted for the first compass bird is -2.1, and so on.

[0169] For example, Figure 5As shown, when the obstacle type is a fast-moving object, the position, speed and direction of the fast-moving object are obtained from the obstacle state information, the ocean current velocity data and wind data are obtained from the operating environment information, and the position, direction and speed of the seismic operation ship are obtained from the first state data of the seismic acquisition system. The position, speed, direction, position, direction and speed of the seismic operation ship of the fast-moving object are input into the first data coding layer for encoding to obtain the seventh sub-eigenvector; the third undirected graph constructed according to the angle data of the lateral control bird, the distribution and towing structure data of the lateral control bird and the compass bird is input into the image coding layer for encoding to obtain the eighth sub-eigenvector; the ocean current velocity data and wind data are input into the second data coding layer for encoding to obtain the ninth sub-eigenvector. The seventh sub-eigenvector, the eighth sub-eigenvector and the ninth sub-eigenvector are fused to obtain the third eigenvector, and the third eigenvector is decoded by the third decoding layer to obtain the third target control instruction.

[0170] Optionally, the lateral control bird and / or the compass bird are controlled according to the target control instruction to drive the working tractor to avoid obstacles, including steps E1-E2:

[0171] Step E1, converting the acquired target control instruction into motor rotation angle information.

[0172] Specifically, after generating the adjustment angle of the lateral control bird and / or the compass bird, the server converts the adjustment angle into motor rotation angle information.

[0173] Step E2: adjusting the wing angles of the lateral control bird and / or the compass bird through the lateral control bird and compass bird control system according to the motor rotation angle information, so as to drive the working tractor to avoid obstacles.

[0174] Exemplarily, the server sends the motor rotation information to the PCS control system (lateral control bird and compass bird control system), and the PCS control system sends the motor rotation information to each lateral control bird and / or compass bird in the form of a protocol packet. After each lateral control bird and / or compass bird receives the protocol packet, it parses the protocol packet to obtain the motor rotation information, drives the motor to rotate according to the motor rotation information, thereby driving the wings of each lateral control bird and / or compass bird to move to adjust to the adjustment angle.

[0175] Optionally, after the lateral control bird and / or the compass bird are controlled according to the target control instruction to drive the working tractor to avoid obstacles, steps F1-F3 are included:

[0176] Step F1, obtaining the second state data of the seismic acquisition system.

[0177] Among them, the second state data of the seismic acquisition system is used to characterize the position and orientation of the seismic operation ship, the lateral control bird and the compass bird.

[0178] Furthermore, the second state data of the seismic acquisition system includes the location information and orientation information of the acquisition system. The location information of the acquisition system includes: the longitude and latitude coordinates of the seismic operation ship, the head mark, the tail mark, and the depth-determining direction finder; the orientation information includes: the orientation of the seismic operation ship, the head mark, the tail mark, and the depth-determining direction finder.

[0179] Furthermore, the acquisition system status information is expressed as:

[0180] S={(lon 0 ,lat 0 ,dir 0 ), (lon 1 ,lat 1 ,dir 1 ),……,(lon n ,lat n ,dir n )},

[0181] Among them, (lon 0 ,lat 0 ,dir 0 ) represents the longitude, latitude and azimuth of the seismic operation vessel; (lon 1 ,lat 1 ,dir 1 ) indicates the longitude, latitude and azimuth of the header; (lon n ,lat n ,dir n ) indicates the longitude, latitude and azimuth of the tail mark; the others indicate the longitude, latitude and azimuth of each lateral control bird and the compass bird.

[0182] Specifically, the second state data of the seismic acquisition system is obtained from a sensor configured on the seismic operation vessel.

[0183] Step F2: Determine the operation plan.

[0184] Among them, the operation plan refers to the operation survey line where data collection has not been completed.

[0185] Specifically, the operation plan is determined based on the predicted survey line and the survey line for which data collection has been completed.

[0186] The preset survey line is a linear measurement path that is pre-arranged according to the locations where data collection is required in the target sea area.

[0187] Furthermore, the target operation line is expressed as:

[0188]

[0189] in, They respectively represent the starting point longitude, starting point latitude, ending point longitude, ending point latitude and survey line representation of the mth operating survey line for which data collection has not been completed.

[0190] Step F3: determine the operation adjustment plan according to the second state data of the seismic acquisition system and the operation plan, and display the operation adjustment plan.

[0191] Among them, the operation adjustment plan is the collection probability of each operation survey line.

[0192] Specifically, the second state data S of the seismic acquisition system and the operation plan LINE are input into the operation adjustment model, and the operation adjustment model is used to predict the acquisition probability of each operation line after avoiding obstacles, and each operation line is displayed differently according to the probability.

[0193] Exemplarily, the working survey line with the highest probability is displayed in red, and the other working survey lines are displayed in green, or the working survey lines with probabilities greater than a first threshold are displayed in red, the working survey lines with probabilities greater than a second threshold and less than the first threshold are displayed in yellow, and the working survey lines with probabilities less than the second threshold are displayed in green.

[0194] Among them, the job adjustment model adopts a deep neural network model.

[0195] In the above steps, after avoiding obstacles, an operation adjustment plan is generated in real time through the trained operation adjustment model and the second state data of the acquisition system, and the existing operation plan is updated according to the generated operation adjustment plan, thereby further improving the efficiency of offshore operations.

[0196] The technical solution of this embodiment determines the obstacle status information, the first state data of the seismic acquisition system and the environmental data of the target sea area; matches the target control instruction generation strategy from the candidate control instruction generation strategies according to the obstacle status information, so as to realize matching the corresponding control instruction generation strategy according to the specific obstacle type, thereby avoiding the problem that only a single control instruction generation strategy is used, resulting in the generated control instructions being unable to accurately avoid obstacles; determines the target control instruction through the target control instruction generation strategy according to the obstacle status information, the first state data of the seismic acquisition system and the environmental data, so as to ensure that the control instruction is generated using the control instruction generation strategy exclusive to the current obstacle type, thereby greatly improving the generation efficiency of the control instruction; controls the lateral control bird and / or the compass bird according to the target control instruction, drives the operation towing to avoid obstacles, reduces manual participation, makes the obtained avoidance plan more in line with the objective environment, effectively utilizes the marine operation window period, and improves the operation efficiency of the marine lateral control bird and the compass bird. The method matches different control instruction generation strategies according to different obstacle types, generates control instructions according to the control instruction generation strategies, and controls the lateral control bird and / or the compass bird to drive the operating towing vessel to avoid obstacles, thereby improving the operating towing efficiency and the accuracy of the marine operating vessel in avoiding obstacles.

[0197] Figure 5 The structure diagram of a marine operation towing obstacle avoidance device provided by an embodiment of the present invention. This embodiment can be applied to the situation where a marine operation towing device encounters an obstacle and avoids the obstacle according to different avoidance modes matched with different obstacles. The marine operation towing obstacle avoidance device can be implemented in the form of hardware and / or software, and the marine operation towing obstacle avoidance device can be configured in any electronic device with network communication function. Figure 5 As shown, the device includes: a data determination module 210, a target control instruction generation strategy determination module 220, a target control instruction determination module 230 and a control module 240, wherein:

[0198] Data determination module 210: used to determine obstacle status information, first state data of the seismic acquisition system and environmental data of the target sea area; the obstacle status information is used to characterize the types of obstacles in the target sea area and the corresponding operating states of the obstacles; the first state data of the seismic acquisition system is used to characterize the operating state data of the seismic acquisition system in the target sea area; the environmental data is used to characterize the data of the natural environment in which the target sea area is located; the seismic acquisition system includes: a seismic operation ship and an operation tug; the seismic operation ship is equipped with an operation tug; the operation tug is equipped with a lateral control bird and a compass bird;

[0199] The target control instruction generation strategy determination module 220 is used to match the target control instruction generation strategy from the candidate control instruction generation strategy according to the obstacle state information; the target control instruction generation strategy is used to generate the target control instruction of the lateral control bird and / or the compass bird; the target control instruction is used to control the lateral control bird and / or the compass bird to drive the working tow to avoid obstacles; the target control instruction includes at least one of the first target control instruction, the second target control instruction and the third target control instruction; the first target control instruction is used to control the lateral control bird to drive the working tow to avoid fixed position objects; the second target control instruction is used to control the lateral control bird to drive the working tow to avoid floating objects; the third target control instruction is used to control the lateral control bird and the compass bird to drive the working tow to avoid fast-moving objects;

[0200] The target control instruction determination module 230 is used to determine the target control instruction through the target control instruction generation strategy according to the obstacle state information, the first state data of the seismic acquisition system and the environmental data;

[0201] Control module 240: used to control the lateral control bird and / or the compass bird according to the target control instruction, so as to drive the working tractor to avoid obstacles.

[0202] Optionally, the data determination module 210 includes:

[0203] Radar data acquisition unit: used to acquire radar data in the target sea area;

[0204] Obstacle judgment unit: used to determine whether there are obstacles in the target sea area based on radar data;

[0205] Obstacle state information determination unit: used to determine the obstacle state information according to the obstacle change data in the radar data if there is an obstacle.

[0206] Optionally, the target control instruction determination module 230 includes:

[0207] Data determination unit: used for acquiring angle data of the lateral control bird, distribution and towing structure data of the lateral control bird and the compass bird, and operation data of the seismic operation vessel from the first state data of the seismic acquisition system;

[0208] A first undirected graph determining unit is used to construct a first undirected graph according to the angle data of the lateral control bird and the distribution dragging structure data of the lateral control bird and the compass bird, wherein the first undirected graph is used to represent the distribution of the wings of the lateral control bird;

[0209] A first sub-eigenvector determining unit is used to encode the operation data of the seismic operation vessel and the state data of the fixed position object through the first data encoding layer to obtain a first sub-eigenvector; the first data encoding layer is used to construct a relationship between the first state data of the seismic acquisition system and the obstacle state information;

[0210] A second sub-feature vector determination unit is used to encode the first undirected graph through an image coding layer to obtain a second sub-feature vector; the image coding layer is used to construct a distribution relationship between the lateral control birds and / or the compass birds in the undirected graph;

[0211] A third sub-eigenvector determining unit: used to encode the ocean velocity data through the second data encoding layer to obtain a third sub-eigenvector; the second data encoding layer is used to construct a relationship between environmental data;

[0212] A first feature vector determining unit: used for determining a first feature vector according to the first sub-feature vector, the second sub-feature vector and the third sub-feature vector;

[0213] The first target control instruction determining unit is used to decode the first characteristic vector to obtain the first target control instruction, and the first target control instruction is used to control the lateral control bird to adjust the angle.

[0214] Optionally, the target control instruction determination module 230 includes:

[0215] Data determination unit: used for acquiring angle data of the lateral control bird, distribution and towing structure data of the lateral control bird and the compass bird, and operation data of the seismic operation vessel from the first state data of the seismic acquisition system;

[0216] A second undirected graph determining unit is used to construct a second undirected graph according to the angle data of the lateral control bird and the distribution dragging structure data of the lateral control bird and the compass bird, wherein the second undirected graph is used to represent the distribution of the wings of the lateral control bird;

[0217] A fourth sub-eigenvector determining unit is used to encode the operation data of the seismic operation vessel and the state data of the floating object through the first data encoding layer to obtain a fourth sub-eigenvector;

[0218] A fifth sub-feature vector determining unit: configured to encode the second undirected graph through an image coding layer to obtain a fifth sub-feature vector;

[0219] A sixth sub-eigenvector determining unit: configured to encode the ocean current velocity data and the wind force data through the second data encoding layer to obtain a sixth sub-eigenvector;

[0220] A second eigenvector determining unit: configured to determine a second eigenvector according to the fourth sub-eigenvector, the fifth sub-eigenvector and the sixth sub-eigenvector;

[0221] The second target control instruction determination unit is used to decode the second characteristic vector to obtain the second target control instruction, and the second target control instruction is used to control the lateral control bird to adjust the angle.

[0222] Optionally, the target control instruction determination module 230 includes:

[0223] Data determination unit: used for acquiring angle data of the compass bird, angle data of the lateral control bird, distribution and towing structure data of the lateral control bird and the compass bird, and operation data of the seismic operation vessel from the first state data of the seismic acquisition system;

[0224] A third undirected graph determining unit is used to construct a third undirected graph according to the angle data of the compass bird, the angle data of the lateral control bird, and the distribution dragging structure data of the lateral control bird and the compass bird, wherein the third undirected graph is used to represent the wing distribution of the lateral control bird and the compass bird;

[0225] A seventh sub-eigenvector determining unit is used to encode the operation data of the seismic operation vessel and the state data of the fast-moving object through the first data encoding layer to obtain a seventh sub-eigenvector;

[0226] An eighth sub-eigenvector determining unit: configured to encode the third undirected graph through an image coding layer to obtain an eighth sub-eigenvector;

[0227] A ninth sub-eigenvector determining unit: configured to encode the ocean current velocity data and the wind force data through the second data encoding layer to obtain a ninth sub-eigenvector;

[0228] A third eigenvector determining unit: configured to determine a third eigenvector according to the seventh sub-eigenvector, the eighth sub-eigenvector and the ninth sub-eigenvector;

[0229] The third target control instruction determination unit is used to decode the third characteristic vector to obtain the third target control instruction, and the third target control instruction is used to control the lateral control bird and the compass bird to adjust the angle.

[0230] Optionally, the control module 240 includes:

[0231] A rotation angle information determination unit: used for converting the acquired target control instruction into motor rotation angle information;

[0232] Adjustment unit: used to adjust the wing angle of the lateral control bird and / or the compass bird through the lateral control bird and compass bird control system according to the motor rotation angle information, so as to drive the working tractor to avoid obstacles.

[0233] Optional, Ocean Lateral Control Bird and Compass Bird Avoidance Devices, including:

[0234] The second state data acquisition module is used to acquire the second state data of the seismic acquisition system, and the second state data of the seismic acquisition system is used to characterize the position and orientation of the seismic operation ship, the lateral control bird and the compass bird;

[0235] Operation plan determination module: used to determine the operation plan, which is the operation line for which data collection has not been completed;

[0236] Operation adjustment plan determination module: used to determine the operation adjustment plan according to the second state data of the seismic acquisition system and the operation plan, and display the operation adjustment plan. The operation adjustment plan is the acquisition probability of each operation survey line.

[0237] The marine operation towing obstacle avoidance device provided in the embodiment of the present invention can execute the marine operation towing obstacle avoidance method provided in any of the above-mentioned embodiments of the present invention, and has the corresponding functions and beneficial effects of executing the marine operation towing obstacle avoidance method. For detailed processes, please refer to the relevant operations of the marine operation towing obstacle avoidance method in the above-mentioned embodiments.

[0238] Figure 6 A schematic diagram of the structure of an electronic device for implementing the marine operation towing obstacle avoidance method of an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0239] like Figure 6 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0240] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0241] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning strategy algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the marine operation towing obstacle avoidance method.

[0242] In some embodiments, the marine operation towing obstacle avoidance method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the marine operation towing obstacle avoidance method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the marine operation towing obstacle avoidance method in any other appropriate manner (for example, by means of firmware).

[0243] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0244] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0245] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 foregoing.

[0246] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0247] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0248] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0249] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0250] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for towing and avoiding obstacles in marine operations, characterized in that: include: Determine the obstacle status information, first status data of the seismic acquisition system and environmental data of the target sea area; The obstacle status information is used to characterize the type of obstacles in the target sea area and the corresponding operating status of the obstacles; the first state data of the seismic acquisition system is used to characterize the operating status data of the seismic acquisition system in the target sea area; The environmental data is used to characterize the natural environment of the target sea area; The seismic acquisition system comprises: a seismic operation vessel and an operation towing vessel; the seismic operation vessel is equipped with the operation towing vessel; the operation towing vessel is equipped with a lateral control bird and a compass bird; Matching a target control instruction generation strategy from candidate control instruction generation strategies according to the obstacle state information; the target control instruction generation strategy is used to generate target control instructions for the lateral control bird and / or compass bird; the target control instruction is used to control the lateral control bird and / or compass bird to drive the work tow truck to avoid obstacles; the target control instruction includes at least one of a first target control instruction, a second target control instruction and a third target control instruction; the first target control instruction is used to control the lateral control bird to drive the work tow truck to avoid fixed-position objects; the second target control instruction is used to control the lateral control bird to drive the work tow truck to avoid floating objects; the third target control instruction is used to control the lateral control bird and the compass bird to drive the work tow truck to avoid fast-moving objects; Determining a target control instruction through the target control instruction generation strategy according to the obstacle state information, the first state data of the seismic acquisition system and the environmental data; The lateral control bird and / or the compass bird are controlled according to the target control instruction to drive the working tractor to avoid obstacles.

2. The method according to claim 1, characterized in that The determining of obstacle status information of the target sea area includes: Acquire radar data within the target sea area; Determine whether there are obstacles in the target sea area according to the radar data; If there is an obstacle, the obstacle state information is determined according to the change data of the obstacle in the radar data.

3. The method according to claim 1, characterized in that The determining the target control instruction through the target control instruction generation strategy according to the obstacle state information, the first state data of the seismic acquisition system and the environmental data comprises: Acquire angle data of the lateral control bird, distribution and towing structure data of the lateral control bird and the compass bird, and operation data of the seismic operation vessel from the first state data of the seismic acquisition system; Constructing a first undirected graph according to the angle data of the lateral control bird and the distribution drag structure data of the lateral control bird and the compass bird, wherein the first undirected graph is used to represent the distribution of the wings of the lateral control bird; The operation data of the seismic operation vessel and the state data of the object at the fixed position are encoded by the first data encoding layer to obtain a first sub-feature vector; the first data encoding layer is used to construct a relationship between the first state data of the seismic acquisition system and the obstacle state information; The first undirected graph is encoded by an image coding layer to obtain a second sub-feature vector; the image coding layer is used to construct a distribution relationship between the lateral control birds and / or the compass birds in the undirected graph; The ocean velocity data is encoded by a second data encoding layer to obtain a third sub-feature vector; the second data encoding layer is used to construct a relationship between environmental data; Determine a first eigenvector according to the first sub-eigenvector, the second sub-eigenvector and the third sub-eigenvector; The first characteristic vector is decoded to obtain a first target control instruction, where the first target control instruction is used to control the lateral control bird to adjust the angle.

4. The method according to claim 1, characterized in that: The determining the target control instruction through the target control instruction generation strategy according to the obstacle state information, the first state data of the seismic acquisition system and the environmental data comprises: Acquire angle data of the lateral control bird, distribution and towing structure data of the lateral control bird and the compass bird, and operation data of the seismic operation vessel from the first state data of the seismic acquisition system; constructing a second undirected graph according to the angle data of the lateral control bird and the distribution drag structure data of the lateral control bird and the compass bird, wherein the second undirected graph is used to represent the distribution of the wings of the lateral control bird; The operation data of the seismic operation vessel and the state data of the floating object are encoded by the first data encoding layer to obtain a fourth sub-eigenvector; Encoding the second undirected graph through an image coding layer to obtain a fifth sub-feature vector; The ocean current data and the wind data are encoded by the second data encoding layer to obtain a sixth sub-eigenvector; Determine a second eigenvector according to the fourth sub-eigenvector, the fifth sub-eigenvector and the sixth sub-eigenvector; The second characteristic vector is decoded to obtain a second target control instruction, where the second target control instruction is used to control the lateral control bird to adjust the angle.

5. The method according to claim 1, characterized in that The determining the target control instruction through the target control instruction generation strategy according to the obstacle state information, the first state data of the seismic acquisition system and the environmental data comprises: Acquire the angle data of the compass bird, the angle data of the lateral control bird, the distribution and towing structure data of the lateral control bird and the compass bird, and the operation data of the seismic operation vessel from the first state data of the seismic acquisition system; constructing a third undirected graph according to the angle data of the compass bird, the angle data of the lateral control bird, and the distribution drag structure data of the lateral control bird and the compass bird, wherein the third undirected graph is used to characterize the wing distribution of the lateral control bird and the compass bird; The operation data of the seismic operation vessel and the state data of the fast-moving object are encoded by the first data encoding layer to obtain a seventh sub-eigenvector; Encoding the third undirected graph through an image coding layer to obtain an eighth sub-eigenvector; The ocean current data and the wind data are encoded by the second data encoding layer to obtain a ninth sub-eigenvector; Determine a third eigenvector according to the seventh sub-eigenvector, the eighth sub-eigenvector and the ninth sub-eigenvector; The third characteristic vector is decoded to obtain a third target control instruction, and the third target control instruction is used to control the lateral control bird and the compass bird to adjust the angle.

6. The method according to claim 1, characterized in that The step of controlling the lateral control bird and / or the compass bird according to the target control instruction to drive the working tractor to avoid obstacles includes: Converting the acquired target control instruction into motor rotation angle information; According to the motor rotation angle information, the wing angles of the lateral control bird and / or the compass bird are adjusted through the lateral control bird and compass bird control system to drive the working tractor to avoid obstacles.

7. The method according to claim 6, characterized in that After the lateral control bird and / or the compass bird are controlled according to the target control instruction to drive the working tractor to avoid obstacles, the method includes: Acquire second state data of the seismic acquisition system, wherein the second state data of the seismic acquisition system is used to characterize the position and orientation of the seismic operation vessel, the lateral control bird, and the compass bird; Determine an operation plan, wherein the operation plan is an operation survey line for which data collection has not been completed; An operation adjustment plan is determined according to the second state data of the seismic acquisition system and the operation plan, and the operation adjustment plan is displayed. The operation adjustment plan is the acquisition probability of each operation survey line.

8. A towing obstacle avoidance device for marine operations, characterized in that: include: A data determination module, used to determine obstacle status information of the target sea area, first state data of the seismic acquisition system and environmental data; The obstacle status information is used to characterize the type of obstacles in the target sea area and the corresponding operating status of the obstacles; the first state data of the seismic acquisition system is used to characterize the operating status data of the seismic acquisition system in the target sea area; The environmental data is used to characterize the natural environment of the target sea area; The seismic acquisition system comprises: a seismic operation vessel and an operation towing vessel; the seismic operation vessel is equipped with the operation towing vessel; the operation towing vessel is equipped with a lateral control bird and a compass bird; a target control instruction generation strategy determination module, used for matching a target control instruction generation strategy from candidate control instruction generation strategies according to the obstacle state information; the target control instruction generation strategy is used to generate a target control instruction for the lateral control bird and / or the compass bird; the target control instruction is used to control the lateral control bird and / or the compass bird to drive the work tow truck to avoid obstacles; the target control instruction includes at least one of a first target control instruction, a second target control instruction and a third target control instruction; the first target control instruction is used to control the lateral control bird to drive the work tow truck to avoid fixed position objects; the second target control instruction is used to control the lateral control bird to drive the work tow truck to avoid floating objects; the third target control instruction is used to control the lateral control bird and the compass bird to drive the work tow truck to avoid fast-moving objects; A target control instruction determination module, configured to determine a target control instruction through the target control instruction generation strategy according to the obstacle state information, the first state data of the seismic acquisition system and the environmental data; A control module is used to control the lateral control bird and / or the compass bird according to the target control instruction, so as to drive the working tractor to avoid obstacles.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the marine operation towing obstacle avoidance method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the marine operation towing obstacle avoidance method according to any one of claims 1 to 7 when executed.

Images