Method, device and electronic equipment for determining offshore drilling path

Abstract

The application discloses a method and device for determining a drilling path at sea and an electronic device. The application relates to the field of ocean engineering automation. The method comprises: creating an ocean environment model; under the ocean environment model, path information of a plurality of target drilling paths of a drilling ship at sea is determined by using a plurality of path planning algorithms respectively, with the aim of minimizing a comprehensive cost, wherein the comprehensive cost is determined by a plurality of sub-costs and preset weights corresponding to each sub-cost, the plurality of sub-costs include an energy consumption cost, a time cost and a satisfaction cost, the satisfaction cost is determined according to a satisfaction index, and the satisfaction index is used to quantify at least an operation safety degree and a navigation comfort degree of the drilling ship at sea according to the drilling path; and the path information of the plurality of target drilling paths is output. The application solves the technical problem that it is difficult to simulate the complex changes of the ocean to plan the drilling path for the ship due to the fact that only a single index is considered when the drilling path is determined.

Description

Technical Field

[0001] This application relates to the field of marine engineering automation, and more specifically, to a method, apparatus, and electronic equipment for determining offshore drilling paths. Background Technology

[0002] Offshore drilling platform operations are a crucial link in marine resource development, and their efficiency directly impacts overall operating costs and safety. In multi-wellhead operations, path planning is a vital task to ensure efficient, economical, and safe navigation of the platform. However, related technologies often exhibit the following shortcomings when facing complex and ever-changing marine environments: Traditional path planning methods often treat the vessel as a point moving at a constant speed in an ideal, windless, and current-free marine environment, ignoring the dynamics and complexities of the real marine environment, such as the influence of wind speed, wind direction, and the intensity and direction of ocean currents. Furthermore, traditional path planning methods often rely on preset environmental parameters and fixed operational logic, focusing only on single indicators, such as shortest distance or shortest time, while neglecting the necessity of multi-objective optimization. This leads to problems such as excessive fuel consumption, excessively long voyage times, and higher operational risks in actual operations. They lack real-time adaptability to rapidly changing marine environments, making it difficult to simulate complex ocean conditions and plan drilling paths for vessels under such conditions.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a method, apparatus, and electronic device for determining offshore drilling paths, in order to at least solve the technical problem that focusing on only a single indicator when determining drilling paths makes it difficult to simulate the complex changes in the ocean for planning drilling paths for ships.

[0005] According to one aspect of the embodiments of this application, a method for determining offshore drilling paths is provided, comprising: creating a marine environment model, wherein the marine environment model is used to simulate the marine conditions under which an offshore drilling vessel performs offshore drilling operations, the marine conditions including at least the coordinate positions of multiple wellheads to be drilled, the position coordinates of marine obstacles, and marine environmental parameters, the marine environmental parameters including at least wind direction information and ocean current information; under the marine environment model, with the objective of minimizing the overall cost, using multiple path planning algorithms to determine the path information of multiple target drilling paths for the offshore drilling vessel, wherein the overall cost is determined by multiple sub-costs and a preset weight corresponding to each sub-cost, the multiple sub-costs including energy consumption cost, time cost, and satisfaction cost, the satisfaction cost being determined based on a satisfaction index, the satisfaction index being used at least to quantify the operational safety index and navigation comfort index of the offshore drilling vessel performing offshore drilling according to the drilling path; and outputting the path information of multiple target drilling paths.

[0006] Optionally, under the marine environment model, with the objective of minimizing the overall cost, multiple path planning algorithms are used to determine the path information of multiple target drilling paths for the offshore drilling vessel. This includes: with the objective of minimizing the overall cost, using multiple path planning algorithms under constraints in multiple dimensions of the marine environment model, traversing the position coordinates of multiple wellheads from the starting wellhead to the ending wellhead to determine the path information of multiple target drilling paths for the offshore drilling vessel. The multiple path planning algorithms include ant colony optimization algorithm, genetic algorithm, Prim algorithm, Kruskal algorithm, genetic Prim algorithm, and genetic Kruskal algorithm. The genetic Prim algorithm is a hybrid algorithm combining genetic algorithm and Prim algorithm, and the genetic Kruskal algorithm is a hybrid algorithm combining genetic algorithm and Kruskal algorithm.

[0007] Optionally, the path information for any target drilling path includes at least the target drilling path, the segment type of each target segment, and multiple indicator values ​​corresponding to the target drilling path. These multiple indicator values ​​include at least the comprehensive cost, time cost, energy cost, satisfaction cost, total travel distance, and total travel time corresponding to the target drilling path. The target drilling path is a path determined after the execution of the corresponding path planning algorithm, consisting of multiple target segments arranged in a fixed order, covering the coordinates of the starting wellhead among multiple wellheads as the starting point and the coordinates of the ending wellhead among multiple wellheads as the ending point, and traversing all third wellheads among the multiple wellheads without repetition. Each target segment is the travel distance between two different wellheads in the target drilling path, and the third wellhead is any wellhead other than the starting and ending wellheads among the multiple wellheads. The total travel time is the time required for the offshore drilling vessel to complete one full voyage from the starting wellhead to the ending wellhead according to the target drilling path.

[0008] Optionally, multiple target drilling paths are output, including: constructing a path comparison table and a path comparison diagram based on the multiple target drilling paths, wherein the path comparison table includes at least the algorithm name of each path planning algorithm, the target drilling path information corresponding to each path planning algorithm, and the execution time required for each algorithm to determine the target drilling path, and the path comparison diagram is used to visualize the multiple target drilling paths; and pushing the path comparison table and the path comparison diagram to the target object.

[0009] Optionally, the constraints of multiple dimensions include at least the speed constraint of the offshore drilling vessel, the turning constraint of the offshore drilling vessel during navigation, and the energy consumption constraint of the offshore drilling vessel during navigation. The speed constraint is used to constrain the actual speed of the offshore drilling vessel during navigation. The actual speed is determined based on a preset reference speed, wind direction influence factor, and current direction influence factor. Different wind direction angles correspond to different wind direction influence factors. The wind direction angle is the angle between the wind direction and the heading of the offshore drilling vessel. The current direction influence factor is determined at least based on the ocean current angle. The ocean current angle is the angle between the heading of the offshore drilling vessel and the direction of the ocean current. The energy consumption constraint is used to constrain the actual energy consumption of the offshore drilling vessel during navigation. The actual energy consumption is determined based on the reference energy consumption, the energy consumption coefficient of the first type of navigation segment, and the energy consumption coefficient of the second type of navigation segment.

[0010] Optionally, the path information of the target drilling path of the offshore drilling vessel is determined in the following way: when the path planning algorithm is the Prim algorithm, each wellhead is defined as a node, the edge between any two nodes is defined as a segment, and the segment cost of each segment is defined as the edge weight between the two nodes, where the segment cost is the sum of the segment's time cost, energy cost, and satisfaction cost; the Prim algorithm is used to traverse all wellheads based on the edge weights, starting from the starting wellhead and ending at the ending wellhead, to obtain the Prim algorithm spanning tree; the Prim algorithm spanning tree is traversed using depth-first traversal to obtain the path information of the target drilling path of the offshore drilling vessel corresponding to the Prim algorithm.

[0011] Optionally, the path information of the target drilling path of the offshore drilling vessel is determined in the following way: When the path planning algorithm is Kruskal's algorithm, each wellhead is defined as a node, the edge between any two nodes is defined as a segment, and the segment cost of each segment is defined as the edge weight between the two nodes, where the segment cost is the sum of the segment's time cost, energy cost, and satisfaction cost; the Kruskal's algorithm is used to traverse all wellheads based on the edge weights, starting from the starting wellhead and ending at the ending wellhead, to obtain the Kruskal's algorithm spanning tree; the Kruskal's algorithm spanning tree is then traversed using depth-first traversal to obtain the path information of the target drilling path of the offshore drilling vessel corresponding to the Kruskal's algorithm.

[0012] Optionally, each target segment is classified into either a Category I segment or a Category II segment. A Category I segment indicates that the offshore drilling vessel's navigation comfort and operational safety indices are both above corresponding thresholds when navigating the target segment. A Category II segment indicates that the offshore drilling vessel's navigation comfort and operational safety indices are both below corresponding thresholds when navigating the target segment. The rules for classifying each target segment into Category I and Category II segments are as follows: Determine the wind direction angle, ocean current angle, and turning angle corresponding to the offshore drilling vessel in the first target segment. The first target segment can be any one of multiple target segments. If the wind direction angle, ocean current angle, and turning angle are all less than the preset classification angles, the first target segment is designated as a Category I segment. If at least one of the wind direction angle, ocean current angle, and turning angle is greater than the preset classification angle, the first target segment is designated as a Category II segment.

[0013] Optionally, the satisfaction cost corresponding to any target drilling path is determined in the following way: determining the total number of target segments in the target drilling path, the total number of second-class segments among all target segments, and the total number of first-class segments among all target segments; determining the satisfaction value corresponding to the satisfaction index based on the total number of target segments, the total number of second-class segments, and the total number of first-class segments; determining the target satisfaction cost based on the satisfaction value and the preset weight corresponding to the satisfaction cost, wherein the target satisfaction cost is the satisfaction cost corresponding to the target drilling path.

[0014] Optionally, the comprehensive cost corresponding to any target drilling path is determined as follows: a weighted sum is obtained based on the target energy cost, target time cost, target satisfaction cost, and preset weights corresponding to the target energy cost, target time cost, and target satisfaction cost. The target energy cost, target time cost, and target satisfaction cost are respectively the energy cost, time cost, and satisfaction cost corresponding to the target drilling path. The target comprehensive cost is the comprehensive cost corresponding to the target drilling path. The target energy cost is determined based on a preset maximum energy consumption benchmark value and the total energy consumption required for the offshore drilling vessel to navigate the target drilling path. The total energy consumption is the sum of the energy consumption corresponding to all target segments in the target drilling path. The energy consumption corresponding to each target segment is determined at least based on a preset basic energy consumption value and an environmental penalty coefficient. The target time cost is determined based on the total navigation time corresponding to the target drilling path and a preset normalized time benchmark value. The preset normalized time benchmark value is used to normalize the total navigation time.

[0015] Optionally, the path information of the target drilling path of the offshore drilling vessel is determined in the following way: when the path planning algorithm is the genetic primum algorithm, with the goal of minimizing the overall cost, the primum algorithm traverses the position coordinates of multiple wellheads from the starting wellhead to the ending wellhead under the constraints of multiple dimensions of the marine environment model, generating a first initial population; the genetic algorithm uses the first initial population as input and performs multiple iterations on the first initial population under the constraints of multiple dimensions of the marine environment model to determine the path information of the target drilling path corresponding to the genetic primum algorithm.

[0016] Optionally, the path information of the target drilling path for the offshore drilling vessel is determined in the following manner: When the path planning algorithm is the genetic Kruskal algorithm, with the objective of minimizing the overall cost, the Kruskal algorithm traverses the position coordinates of multiple wellheads from the starting wellhead to the ending wellhead under constraints in multiple dimensions of the marine environment model, generating a second initial population; the genetic algorithm uses the second initial population as input and performs multiple iterations on the second initial population under constraints in multiple dimensions of the marine environment model to determine the path information of the target drilling path corresponding to the genetic Kruskal algorithm.

[0017] Optionally, the path information of the target drilling path for the offshore drilling vessel is determined as follows: When the path planning algorithm is an ant colony optimization algorithm, a pheromone matrix and a heuristic matrix are created and iteration parameters are configured. The pheromone matrix is ​​an n×n matrix, where n represents the total number of wellheads. In the ant colony optimization algorithm, the pheromone matrix guides the ants in path selection. Each element in the heuristic matrix represents the reciprocal of the relative distance between any two wellhead coordinates. The iteration parameters include at least the number of ants in the ant colony optimization algorithm, the number of iterations, the pheromone factor, and the heuristic factor. The following steps are repeated until the number of iterations is reached, then iteration is stopped. The ant path with the minimum overall cost after stopping iteration is determined as the path information of the target drilling path corresponding to the ant colony optimization algorithm: Each ant constructs an ant path based on the pheromone matrix, pheromone factor, and heuristic factor, where one ant path corresponds to one drilling path. The overall cost corresponding to the constructed ant path is calculated, and the pheromone matrix is ​​updated based on the time cost in the corresponding overall cost. The updated pheromone matrix is ​​then determined as the new pheromone matrix.

[0018] Optionally, the path information of the target drilling path for the offshore drilling vessel is determined in the following way: If the path planning algorithm is a genetic algorithm, initialize a population, where each individual in the population corresponds to a drilling path; repeat the following process until the maximum number of iterations is reached, stop the iteration, and determine the individual with the lowest overall cost in the population after stopping the iteration as the path information of the target drilling path for the offshore drilling vessel corresponding to the genetic algorithm: calculate the individual fitness for each individual in the population, where the individual fitness is the reciprocal of the overall cost corresponding to each individual; calculate the sum of the fitness of all individuals in the population, divide the individual fitness of each individual by the sum of fitness to obtain the fitness ratio of each individual; update the individuals in the population according to the fitness ratio to obtain a new population.

[0019] According to another aspect of the embodiments of this application, an apparatus for determining offshore drilling paths is also provided, comprising: a creation module for creating a marine environment model, wherein the marine environment model is used to simulate the marine conditions for offshore drilling operations by an offshore drilling vessel, the marine conditions including at least the coordinate positions of multiple wellheads to be drilled, the position coordinates of marine obstacles, and marine environmental parameters, the marine environmental parameters including at least wind direction information and ocean current information; under the marine environment model, a determination module is used to determine the path information of multiple target drilling paths for the offshore drilling vessel using multiple path planning algorithms with the objective of minimizing the overall cost, wherein the overall cost is determined by multiple sub-costs and a preset weight corresponding to each sub-cost, the multiple sub-costs including energy consumption cost, time cost, and satisfaction cost, the satisfaction cost being determined based on a satisfaction index, the satisfaction index being used at least to quantify the operational safety index and navigation comfort index of the offshore drilling vessel according to the drilling path; and outputting the path information of multiple target drilling paths.

[0020] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, wherein a program is stored in the non-volatile storage medium, wherein the program controls the device where the non-volatile storage medium is located to execute the above-mentioned method for determining the offshore drilling path when it runs.

[0021] According to another aspect of the embodiments of this application, an electronic device is also provided, including: a memory and a processor, the processor being configured to run a program stored in the memory, wherein the program executes the above-described method for determining offshore drilling paths when it runs.

[0022] According to another aspect of the embodiments of this application, a computer program product is also provided, including computer instructions, which, when executed by a processor, implement the above-described method for determining offshore drilling paths.

[0023] In this embodiment, a marine environment model is created to simulate the marine conditions under which an offshore drilling vessel performs offshore drilling operations. These marine conditions include at least the coordinates of multiple wellheads to be drilled, the coordinates of marine obstacles, and marine environmental parameters, including at least wind direction and ocean current information. Under this marine environment model, with the objective of minimizing overall cost, multiple path planning algorithms are used to determine the path information for multiple target drilling paths of the offshore drilling vessel. The overall cost is determined through multiple sub-costs and preset weights for each sub-cost. These sub-costs include energy cost, time cost, and satisfaction cost. The satisfaction cost is determined based on a satisfaction index, which is used to quantify the offshore drilling vessel's operation according to the drilling paths. Safety and navigation comfort indicators; outputting path information for multiple target drilling paths; creating a marine environment model simulating a complex marine environment; and then, under the marine environment model, using multiple path planning algorithms to determine the path information for multiple target drilling paths of the offshore drilling vessel with the goal of minimizing the overall cost. The overall cost includes multiple indicators, such as energy cost, time cost, and satisfaction cost. This method achieves the goal of determining drilling paths by considering multiple indicators under complex marine environmental conditions, and at least solves the technical problem that focusing on only a single indicator when determining drilling paths makes it difficult to simulate the complex changes in the ocean for planning drilling paths for ships. Attached Figure Description

[0024] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0025] Figure 1 This is a hardware structure block diagram of a computer terminal for implementing a method for determining offshore drilling paths, according to an embodiment of this application.

[0026] Figure 2 This is a flowchart of a method for determining an offshore drilling path according to an embodiment of this application;

[0027] Figure 3 This is a flowchart illustrating the execution of an ant colony optimization algorithm according to an embodiment of this application;

[0028] Figure 4 This is a flowchart of an execution of a genetic algorithm according to an embodiment of this application;

[0029] Figure 5 This is an execution flowchart of a minimum spanning tree algorithm provided according to an embodiment of this application;

[0030] Figure 6 This is an execution flowchart of a hybrid algorithm provided according to an embodiment of this application;

[0031] Figure 7 This is a flowchart illustrating another method for determining an offshore drilling path according to an embodiment of this application;

[0032] Figure 8 This is a visual flowchart provided according to an embodiment of this application;

[0033] Figure 9 This is a flowchart derived from a result provided in an embodiment of this application;

[0034] Figure 10 This is a parameter configuration flowchart provided according to an embodiment of this application;

[0035] Figure 11 This is a schematic diagram of an operating environment provided according to an embodiment of this application;

[0036] Figure 12 This is a schematic diagram comparing the running results according to an embodiment of this application;

[0037] Figure 13 This is a schematic diagram illustrating the optimization progress of the first algorithm according to an embodiment of this application;

[0038] Figure 14 This is a schematic diagram illustrating the optimization progress of the second algorithm according to an embodiment of this application;

[0039] Figure 15 This is a schematic diagram illustrating the optimization progress of the third algorithm according to an embodiment of this application;

[0040] Figure 16 This is a schematic diagram of a device for determining an offshore drilling path according to an embodiment of this application. Detailed Implementation

[0041] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0042] The information collected in this application embodiment is information and data authorized by the user or fully authorized by all parties. The collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data all comply with the relevant laws, regulations and standards of the relevant regions, and necessary confidentiality measures have been taken. It does not violate public order and good morals, and provides corresponding operation entry points for users to choose to authorize or reject the automated decision results. If the user chooses to reject, the process will proceed to the expert decision-making process.

[0043] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0044] In related technologies, traditional path planning methods often treat a ship as a point moving at a constant speed in an ideal, windless, and current-free ocean environment, ignoring the dynamics and complexity of the real ocean environment, such as the influence of wind speed, wind direction, and the intensity and direction of ocean currents. Furthermore, traditional path planning methods often rely on preset environmental parameters and fixed operational logic, focusing only on a single metric, such as shortest distance or shortest time, while neglecting the necessity of multi-objective optimization. Therefore, there is a technical problem that focusing on only a single metric when determining the drilling path makes it difficult to simulate the complex changes in the ocean for ship drilling path planning. To solve this problem, this application provides relevant solutions, which are described in detail below.

[0045] According to an embodiment of this application, an embodiment of a method for determining an offshore drilling path is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0046] The methods and embodiments provided in this application can be executed on a computer terminal or similar computing device. Figure 1 A hardware block diagram of a computer terminal for implementing a method for determining offshore drilling paths is shown. Figure 1As shown, the computer terminal 10 may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0047] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10. As involved in the embodiments of this application, the data processing circuits serve as processor control (e.g., selection of a variable resistor termination path connected to an interface).

[0048] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the offshore drilling path determination method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned offshore drilling path determination method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0049] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0050] The display can be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10.

[0051] In the above operating environment, this application provides an embodiment of a method for determining an offshore drilling path. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0052] like Figure 2 The diagram shown is a flowchart of a method for determining an offshore drilling path according to an embodiment of this application, including:

[0053] Step S202: Create a marine environment model.

[0054] In the technical solution provided in step S202, the marine environment model is used to simulate the marine conditions for offshore drilling operations by an offshore drilling vessel. The marine conditions include at least the coordinates of multiple wellheads to be drilled, the coordinates of marine obstacles, and marine environmental parameters, which include at least wind direction information and ocean current information.

[0055] In the technical solution provided in step S202, the marine obstacles include at least the drilled well area or obstacle area. The multiple constraints of the marine environment model in different dimensions include at least the speed constraint of the marine drilling vessel, the turning constraint of the marine drilling vessel during navigation, and the energy consumption constraint of the marine drilling vessel during navigation. The speed constraint is used to constrain the actual speed of the marine drilling vessel during navigation. The actual speed is determined based on the preset reference speed, wind direction influence factor, and current direction influence factor. Different wind direction angles correspond to different wind direction influence factors. The wind direction angle is the angle between the wind direction and the heading of the marine drilling vessel. The current direction influence factor is determined at least based on the ocean current angle. The ocean current angle is the angle between the heading of the marine drilling vessel and the direction of the ocean current. The energy consumption constraint is used to constrain the actual energy consumption of the marine drilling vessel during navigation. The actual energy consumption is determined based on the reference energy consumption, the energy consumption coefficient of the first type of navigation segment, and the energy consumption coefficient of the second type of navigation segment.

[0056] Offshore drilling platform path planning systems are core decision support tools in the field of marine engineering; however, there is still a lack of independently developed systems with multi-objective dynamic optimization capabilities. Software in related technologies typically only provides basic algorithm modules and standardized interfaces, requiring application teams to perform extensive secondary development. Because vendors usually only encapsulate the underlying optimization library and general data interfaces, it is difficult for operators to directly perform effective configuration and personalized applications, significantly limiting the promotion of such systems in complex operational scenarios. Furthermore, significant differences in operating logic and software environments exist between different systems, leading to difficulties for users when switching platforms, including repeated installations, high learning costs, and inconsistent operating procedures.

[0057] To address the aforementioned issues, some embodiments of this application provide an integrated intelligent path planning system for executing the offshore drilling path determination method described in these embodiments. The integrated intelligent path planning system offers a user-friendly graphical interface, allowing users to flexibly select optimization objectives and constraints, and is compatible with the import and processing of multi-source marine environmental data. The system acquires raw marine data through a low-level algorithm interface to construct a marine environmental model, which, after storage and real-time computation, is transformed into a visualized route plan and multi-dimensional performance indicators. The built-in multiple path planning algorithms support multi-objective trade-offs optimization, including distance, energy consumption, time, and satisfaction. Through intuitive interactive controls, users can easily adjust environmental parameters, algorithm settings, output options, and constraints. Furthermore, the system comprehensively records operation logs and operational history, providing a basis for troubleshooting and scheme backtracking, and outputs specific path planning information and standards. It also provides parameter template saving and optimization result export functions, significantly improving the reliability and reusability of offshore operation planning. This integrated intelligent path planning system is used to execute the offshore drilling path determination method. The system is developed using Python as its core language. Project dependencies are managed uniformly through a dependency requirements file (requirements.txt, which lists all third-party libraries and their versions required for the project to run). It supports cross-platform virtual environment configuration and multiple mainstream operating systems.

[0058] The integrated intelligent path planning system comprises the following functional modules: marine environment modeling and parameter configuration, multi-objective optimization algorithm implementation, path planning result visualization, optimization process monitoring and analysis, and result export and report generation. After starting the integrated intelligent path planning system, the user first enters the main interface for offshore drilling platform path planning and performs marine environment modeling and parameter configuration (i.e., step S202 above), which is explained in detail below. To ensure the complex needs of offshore drilling operations are met, the marine environment model comprehensively considers the complex environment, including wellhead location, distribution of marine obstacles (including areas cleared by drilled wells or obstacle areas), and multiple marine environmental parameters such as wind force and ocean currents. This provides accurate decision support for subsequent path planning algorithms. When creating the marine environment model, the system first automatically detects and loads the default marine environment data source, and reads the coordinates of multiple wellheads to be drilled from a pre-set file storing the coordinates of these wellheads. The stored coordinates include the X-coordinate (horizontal coordinate) and Y-coordinate (vertical coordinate), as well as the wellhead name. The location coordinates of obstacles at sea are obtained either by random generation or by importing from a pre-defined specific file.

[0059] The marine environment model is used to simulate the marine conditions faced by offshore drilling vessels during drilling operations. To accurately reflect the actual operating environment faced by offshore drilling vessels, initializing the marine environment model requires configuring at least the following parameters: wind direction information (e.g., wind speed and direction) and ocean current information (e.g., current intensity and direction), as well as navigation-related parameters for the drilling platform (e.g., the offshore drilling vessel). These parameters include: safe distance between the collected drilling data and the navigation path; energy consumption coefficients for Category I / II segments; various penalty starting angles and increments; minimum / maximum speed factors for the offshore drilling vessel; wind speed influence coefficient on speed; daily operating costs; fuel unit costs; and the number of collected drilling data. These parameters directly simulate the complexity of the real marine environment and the physical characteristics and operational limitations of the offshore drilling vessel navigating within it. Fine-tuning these parameters allows the simulation to closely approximate the actual operating scenario and enables the algorithm to achieve optimal performance with limited resources. If a missing or abnormal data source is detected during the above process, the integrated intelligent path planning system will display an error message to guide the user in configuring the data or environment.

[0060] The marine environment model configured with ocean parameters must satisfy constraints across multiple dimensions, strictly adhering to the actual operational limitations of the drilling platform. These constraints must include at least the speed constraints of the offshore drilling vessel, the turning constraints during navigation, and, to account for the energy consumption of the vessel during actual navigation, energy consumption constraints. Additionally, constraints may include obstacle constraints for overcoming marine obstacles, meteorological and hydrological constraints for constraining the configured marine environmental parameters, and avoidance requirements for the acquired drilling platform data. Specifically:

[0061] The speed constraints for offshore drilling vessels are performance constraints. Specifically, these constraints include: a preset baseline speed (also known as the base speed factor, representing the baseline speed under calm conditions with no wind or current), set to 1.0; wind speed influence range (the range of the influence coefficient of wind speed on the actual speed of the offshore drilling vessel): 0.5-1.5; current speed influence range (the range of the influence coefficient of ocean current on the actual speed of the offshore drilling vessel): 0.5-2.0; minimum speed limit (the minimum speed factor (to prevent negative speed)): 0.5; maximum speed limit (the highest speed factor): 2, where the unit of speed is m / s. Obstacle constraints specifically include a safe distance (the minimum safe distance between the offshore drilling vessel and an obstacle): 50.0 meters; number of obstacles (the number of obstacles, configurable by the user in the corresponding interface, allowing input of the number and coordinates of obstacles): default 10; and meteorological and hydrological constraints specifically include wind speed (the energy consumption affecting the speed of the offshore drilling vessel): customizable (default 5 m / s). Wind direction (0-360 degrees, East is 0 degrees): Customizable (default 120°). Ocean current intensity (affects the energy consumption of the offshore drilling vessel's speed): Customizable (default 1.2). Ocean current direction (0-360 degrees, East is 0 degrees): Customizable (default 80°). Turning constraints include navigation direction constraints and turning performance constraints. Navigation direction constraints specifically include: Maximum turning angle limit (maximum allowable turning angle between adjacent segments): 90°. Unfavorable heading threshold (angle with wind / current exceeding this value is considered an unfavorable heading): 90°. Turning performance constraints specifically include: Sharp turn threshold (angle exceeding this value is considered a sharp turn): 90°. Turning energy consumption penalty (additional energy consumption penalty for sharp turns (greater than 120°)): 1.5-3.0. Turning energy consumption bonus (energy consumption bonus for not turning (less than 30°)): 0.8-1.0. Energy consumption constraints include: Base energy consumption factor (baseline energy consumption for standard segments): 1.0. Unfavorable segment penalty (for unfavorable segments such as headwind / countercurrent / sharp turn segments): The penalty for unfavorable segments (i.e., Category II segments) is the energy consumption penalty coefficient for headwind / countercurrent / sharp turn segments (i.e., the energy consumption coefficient for Category II segments mentioned above): 1.5-3.0. Favorable segment bonus (for favorable segments such as tailwind / tailcurrent segments): The bonus for favorable segments (i.e., Category I segments) is the energy consumption bonus coefficient for tailwind / tailcurrent segments (i.e., the energy consumption coefficient for Category I segments mentioned above). The above parameters are automatically set to default values, and users can customize and modify them within the allowed range according to their actual needs.

[0062] The marine environment model abandons the common simplistic model that treats offshore drilling vessels as uniformly moving points. Instead, it constructs a dynamic vessel performance constraint model, which is a component of vessel performance constraints, based on satisfying multiple constraints across different dimensions. This model can simulate the actual navigation performance of offshore drilling vessels under the combined effects of wind and current in real time. The dynamic vessel performance constraint model in the marine environment model includes a dynamic speed model and a dynamic energy consumption model. The dynamic speed model defines the actual speed of the offshore drilling vessel during navigation. In the marine environment model, the actual speed is the actual speed between two points (i.e., between any two different wellheads). (Unit: m / s) is no longer a constant, but a function of wind direction and flow direction (i.e., the actual speed mentioned above is determined based on the preset reference speed, wind direction influence factor, and flow direction influence factor): ,in, This represents the preset baseline speed in the speed constraint conditions. It should be noted that the actual speed here refers to the speed of the offshore drilling vessel in calm water and windless conditions. Indicates the wind direction influencing factor. This indicates the wind direction influence factor. The calculation of the wind direction influence factor takes into account the wind direction angle (the angle between the wind direction and the heading of the offshore drilling vessel). Different wind angles correspond to different wind direction influence factors:

[0063] ,

[0064] in, It is wind speed (m / s), which accurately reflects the effect of wind on the ship's speed, whether it helps or hinders it.

[0065] The current direction influence factor is determined at least based on the angle of the ocean current. Specifically: ocean current influence factor (i.e., current direction influence factor). The angle between the ship's heading and the direction of the ocean current (ocean current angle). :

[0066] ,in, It refers to the intensity of the ocean current, when the course of travel is the same as the direction of the current ( )hour, The actual speed of offshore drilling ships increases during navigation; when sailing against the current ( )hour, The actual speed of offshore drilling ships during navigation is reduced.

[0067] The dynamic energy consumption model is used to calculate the energy consumption of offshore drilling vessels during navigation. The energy consumption calculation is directly linked to the segment classification, and the base energy consumption (i.e., the preset base energy consumption value) is (segment distance) (i.e., actual energy consumption level), but penalties or reward coefficients (i.e., environmental penalty coefficients) will be applied depending on the flight segment type. The energy consumption for each flight segment is based at least on a preset baseline energy consumption value (i.e., the aforementioned benchmark energy consumption) and an environmental penalty coefficient (the environmental penalty coefficient includes the energy consumption coefficient for Category I flight segments and the energy consumption coefficient for Category II flight segments). Specifically:

[0068] Flight segment energy consumption = For the first type of flight segment, =0.3 (at this point, the environmental penalty coefficient is the energy consumption coefficient for the first type of flight segment), indicating a significant reduction in energy consumption. For the second type of flight segment, It is the maximum value among headwind penalty, countercurrent penalty, and sharp turn penalty, and the environmental penalty coefficient (at this time, the environmental penalty coefficient is the energy consumption coefficient of the second type of flight segment, with a value of 1.5-3.0) increases linearly with the severity of the angle.

[0069] For example, headwind penalty (when Furthermore, actual energy consumption can be adjusted further based on ocean current conditions.

[0070] To quantify navigation quality—that is, the operational safety and navigation comfort of offshore drilling vessels following the drilling path—the marine environment model also needs to include navigation quality constraints. Innovatively, a satisfaction model is introduced to these constraints. This model deeply integrates traditional constraints (e.g., time) with navigation satisfaction indices. The core of this model lies in decomposing the navigation path into continuous segments and classifying the navigation conditions of each segment to determine the satisfaction index. The evaluation of the satisfaction index is a multi-factor comprehensive indicator, encompassing multiple dimensions such as segment comfort, environmental adaptability, and operational safety. Details are as follows:

[0071] Based on satisfying the above-mentioned constraints across multiple dimensions, the classification criteria for flight segments include three key environmental factors: wind direction angle ( ), ocean current angle ( ) and steering angle ( Specifically, its classification rules are as follows:

[0072] Category 1 flight segment: When both conditions are met , and At that time, this section of the voyage was designated as "Category I". Category I voyages, also known as preferred voyages, indicate that the offshore drilling vessel's comfort and operational safety indices are both above the corresponding thresholds when navigating in that voyage. In this situation, crew comfort is high and vessel maneuverability is smooth.

[0073] Category 2 flight segment: If any of the above three angles exceeds... Then the flight segment is marked as "Category II". For example, Represents sailing against the wind. Represents sailing against the current. This represents sharp turns, which significantly increase navigation difficulty and risk. The second category of navigation segments, also known as non-optimal segments, indicates that the offshore drilling vessel's navigation comfort and operational safety indices are below the corresponding thresholds. In these segments, crew comfort is low, and vessel maneuverability is difficult. Based on this classification, the overall satisfaction S (in %) for the entire drilling path is calculated using the percentage of second-category segments: ,in, It refers to the number of Category II flight segments. This represents the total number of segments along the drilling route. This formula intuitively reflects the overall "smoothness" of the route; the higher the overall satisfaction, the more the route aligns with the ship's actual navigation preferences, resulting in better safety, comfort, and economy.

[0074] By evaluating key parameters such as headwind and tailwind conditions, ocean current direction matching, and turning smoothness for each segment, the type of segment is determined. Then, quantitative analysis is performed to generate overall satisfaction, enabling the offshore drilling platform path planning system to optimize navigation quality while ensuring engineering feasibility and economy.

[0075] To address the trade-offs in multi-objective optimization and plan an optimal route for drilling platforms that balances distance, energy consumption, time, cost, and navigation quality, the offshore drilling platform path planning system has designed an innovative integrated cost function. This function unifies and quantifies traditional economic indicators (energy consumption, time) with a proposed satisfaction indicator. This function overcomes the limitations of traditional single-objective optimization, achieving synergistic optimization of economic efficiency and navigation quality. (Dimensionless) consists of the weighted sum of three standardized sub-costs:

[0076] = ,

[0077] in, Indicates energy consumption cost, Indicates time cost, Indicates the cost of satisfaction. , , These represent the preset weights corresponding to energy cost, time cost, and satisfaction cost, respectively.

[0078] Energy costs are calculated using the following formula: = ,in, It is the total energy consumption of the drilling path (unit: standardized energy consumption unit), calculated by applying an environmental penalty coefficient to the preset base energy consumption value of each segment in the drilling path. =100,000 is a preset maximum energy consumption baseline value used for normalization. The energy consumption calculation itself has been deeply integrated with complex ship performance constraints.

[0079] Time cost is calculated using the following formula: It is the total travel time (in seconds) of the drilling path, and its calculation fully considers the dynamic effects of wind and current on ship speed. =86,400 seconds (24 hours) is the preset normalized time base value used for time normalization.

[0080] The cost of satisfaction is calculated using the following formula: This design transforms overall satisfaction S into satisfaction cost. The higher the satisfaction level (the larger the S value), the higher the corresponding satisfaction cost. The smaller the value, the more it reflects the preference for the high-satisfaction path in the total cost.

[0081] When faced with complex sea conditions, the system intelligently weighs the relationship between direct costs (time, energy consumption) and navigation satisfaction (satisfaction cost), dynamically adjusting optimization weights to find the optimal balance among the three. This comprehensive optimization mechanism ensures that the generated path satisfies both hard constraints and economic efficiency and navigation comfort, achieving true multi-objective collaborative optimization. For example, the preset weights for energy cost, time cost, and satisfaction cost are used... =0.3, =0.5, A weight allocation of 0.2 emphasizes the dominant economic factors of energy consumption and time, while assigning a 20% decision weight to satisfaction to ensure that the optimization results do not sacrifice navigation quality for the sake of economic efficiency. The following constraints apply to time and energy costs: Time cost constraint: Daily operating cost (daily operating expenses of offshore drilling vessels): US$272,000 per day. These parameters are automatically set to default values, allowing users to customize them within the allowable range based on actual needs. Energy cost constraint: Energy cost coefficient (cost per unit of energy consumption): US$1 per day. The offshore drilling platform path planning system organically unifies engineering feasibility, economy, and navigation quality. At the physical constraint level, the system strictly adheres to the actual operational limitations of the drilling platform, including maximum turning angle constraints, collected drilling platform avoidance constraints, and dynamic responses to environmental factors (ocean currents, wind speed, etc.). These fundamental constraints ensure the engineering feasibility of the generated path. In terms of economic assessment, a two-tiered cost analysis system is established: direct costs focus on quantifiable fuel consumption (energy cost) and time costs, while comprehensive costs (…)… This expands the evaluation dimensions by taking into account implicit factors such as flight quality (reflected through satisfaction costs).

[0082] Step S204: Under the marine environment model, with the goal of minimizing the overall cost, various path planning algorithms are used to determine the path information of multiple target drilling paths for the offshore drilling vessel.

[0083] In the technical solution provided in step S204, the comprehensive cost is determined by multiple sub-costs and the preset weights corresponding to each sub-cost. The multiple sub-costs include energy consumption cost, time cost, and satisfaction cost. The satisfaction cost is determined based on the satisfaction index. The satisfaction index is used to quantify the operational safety index and navigation comfort index of the offshore drilling vessel according to the drilling path. Under the marine environment model, there are multiple ways to determine the path information of multiple target drilling paths for an offshore drilling vessel by using various path planning algorithms with the goal of minimizing the overall cost. For example, with the goal of minimizing the overall cost, various path planning algorithms are used under the constraints of multiple dimensions of the marine environment model to traverse the position coordinates of multiple wellheads from the starting wellhead to the ending wellhead to determine the path information of multiple target drilling paths for an offshore drilling vessel. Among them, the various path planning algorithms include ant colony optimization algorithm, genetic algorithm, Prim algorithm, Kruskal algorithm, genetic Prim algorithm and genetic Kruskal algorithm. The genetic Prim algorithm is a hybrid algorithm that combines genetic algorithm and Prim algorithm, and the genetic Kruskal algorithm is a hybrid algorithm that combines genetic algorithm and Kruskal algorithm.

[0084] The path information of the target drilling path for the offshore drilling vessel is determined in the following way: With the path planning algorithm being the Genetic Prim algorithm, aiming to minimize the overall cost, the Prim algorithm traverses the location coordinates of multiple wellheads from the starting wellhead to the ending wellhead under constraints in multiple dimensions of the marine environment model, generating a first initial population. Then, using the first initial population as input, the genetic algorithm iterates through multiple rounds under constraints in multiple dimensions of the marine environment model to determine the path information of the target drilling path corresponding to the Genetic Prim algorithm.

[0085] When the path planning algorithm is the genetic Kruskal algorithm, the genetic Kruskal algorithm determines the path information of the target drilling path of the offshore drilling vessel in the following way: with the goal of minimizing the overall cost, the Kruskal algorithm traverses the position coordinates of multiple wellheads from the starting wellhead to the ending wellhead under the constraints of multiple dimensions of the marine environment model to generate a second initial population; the genetic algorithm uses the second initial population as input and performs multiple rounds of iteration on the second initial population under the constraints of multiple dimensions of the marine environment model to determine the path information of the target drilling path corresponding to the Kruskal algorithm.

[0086] When the path planning algorithm is ant colony optimization (ACO), ACO determines the path information of the target drilling path for the offshore drilling vessel in the following way: A pheromone matrix and a heuristic matrix are created and iteration parameters are configured. The pheromone matrix is ​​an n×n matrix, where n represents the total number of wellheads. In ACO, the pheromone matrix guides the ants in path selection. Each element in the heuristic matrix represents the reciprocal of the relative distance between any two wellhead coordinates. The iteration parameters include at least the number of ants, the number of iterations, the pheromone factor, and the heuristic factor. The following steps are repeated until the number of iterations is reached, then iteration is stopped. The ant path with the minimum overall cost after stopping iteration is determined as the path information of the target drilling path corresponding to ACO: Each ant constructs an ant path based on the pheromone matrix, pheromone factor, and heuristic factor, where one ant path corresponds to one drilling path; the overall cost corresponding to the constructed ant path is calculated, and the pheromone matrix is ​​updated based on the time cost in the corresponding overall cost. The updated pheromone matrix is ​​then determined as the new pheromone matrix.

[0087] When the path planning algorithm is a genetic algorithm, the genetic algorithm determines the path information of the target drilling path of the offshore drilling vessel in the following way: Initialize the population, where each individual in the population corresponds to a drilling path; repeat the following process until the maximum number of iterations is reached, stop the iteration, and determine the individual with the minimum comprehensive cost in the population after stopping the iteration as the path information of the target drilling path of the offshore drilling vessel corresponding to the genetic algorithm: calculate the individual fitness for each individual in the population, where the individual fitness is the reciprocal of the comprehensive cost corresponding to each individual; calculate the sum of the fitness of all individuals in the population, divide the individual fitness of each individual by the sum of fitness to obtain the fitness ratio of each individual; update the individuals in the population according to the fitness ratio to obtain a new population.

[0088] When the path planning algorithm is Prim's algorithm, Prim's algorithm determines the path information of the target drilling path of the offshore drilling vessel in the following way: each wellhead is defined as a node, the edge between any two nodes is defined as a segment, and the segment cost of each segment is defined as the edge weight between the two nodes, where the segment cost is the sum of the segment's time cost, energy cost, and satisfaction cost; Prim's algorithm is used to traverse all wellheads based on the edge weights, starting from the starting wellhead and ending at the ending wellhead, to obtain the Prim's algorithm spanning tree; depth-first traversal is used to traverse the Prim's algorithm spanning tree to obtain the path information of the target drilling path of the offshore drilling vessel corresponding to Prim's algorithm.

[0089] When the path planning algorithm is Kruskal's algorithm, the Kruskal algorithm determines the path information of the target drilling path for the offshore drilling vessel in the following way: each wellhead is defined as a node, the edge between any two nodes is defined as a segment, and the segment cost of each segment is defined as the edge weight between the two nodes, where the segment cost is the sum of the segment's time cost, energy cost, and satisfaction cost; the Kruskal algorithm traverses all wellheads based on the edge weights, starting from the starting wellhead and ending at the ending wellhead, to obtain the Kruskal algorithm spanning tree; the Kruskal algorithm spanning tree is traversed using depth-first traversal to obtain the path information of the target drilling path for the offshore drilling vessel corresponding to the Kruskal algorithm.

[0090] The implementation process of each path planning algorithm is explained in detail below.

[0091] The ant colony optimization algorithm, aiming to minimize overall cost, is used to determine the path information of the target drilling vessel's path by traversing the location coordinates of multiple wellheads from the starting wellhead to the ending wellhead under various constraints of the marine environment model. The process is as follows: The ant colony optimization algorithm is imported into the marine environment model (including various types of constraints, the location coordinates of multiple wellheads, and the distribution of marine obstacles). Ant colony optimization is initiated. First, the pheromone matrix is ​​initialized (an n×n pheromone matrix is ​​created, where n is the total number of wellheads (specifically, the total number of wellheads to be drilled), and all initial pheromone concentrations are set to a constant 1, indicating that all paths are considered equally important in the initial search phase). The heuristic matrix is ​​also initialized (each element represents a heuristic, indicating the reciprocal of the relative distance between two wellheads). Algorithm parameters are set, such as the number of ants, the number of iterations, the pheromone factor, and the heuristic factors (alpha and beta). Then, the following iterative optimization process is performed until the termination condition is met: constructing ant paths, calculating path fitness, and updating the pheromone matrix.

[0092] The specific implementation process of constructing ant paths, calculating path fitness, and updating the pheromone matrix in each iteration is as follows: Constructing ant paths: Each ant maintains a list containing the indices of all unvisited wells during the ant path construction process. When deciding which well to visit next, the ant needs to consider its current well and the previous well to assess the change in turning angle. If the ant has just started path construction (only visited the starting well) or the path length is less than two units (meaning there is only one starting well and the current well), then there is no previous well as a reference. In this case, the ant will randomly select an unvisited well to continue its path construction. For each unvisited well j in the list, the algorithm calculates the angle change from the last visited well (if it exists) to the current well i and then to the unvisited well j. The turning angle is determined using the coordinate information of the three wells. The angle fitness calculation, which evaluates the magnitude of the turning angle, is determined based on the magnitude of the angle change, and then it is determined whether the route from the current well i to the unvisited well j constitutes an unfavorable segment (an unfavorable segment is the second type of segment mentioned above). For each unvisited wellhead j, calculate its fitness to be selected as the next visit point. Fitness reflects the attractiveness of the wellhead relative to the current path.

[0093] The formula for calculating path fitness is as follows:

[0094] .

[0095] Here, pheromone(i,j) is the pheromone concentration in the pheromone matrix for the path from wellhead i to wellhead j. heuristic(i,j) is the heuristic information of the corresponding heuristic matrix. angle_fitness(j) is the angle fitness, evaluating the magnitude of the turning angle. penalty_factor(j) is the penalty factor for unfavorable segments; if a segment is unfavorable, the penalty factor will be greater than 1, reducing the fitness of the corresponding wellhead. alpha and beta are the weighting factors for pheromone and heuristic information, and angle_priority is the weighting factor for angle fitness. After calculating the fitness of all unvisited wellheads j, the ant will decide the next wellhead to visit based on these fitness values. If the sum of the fitness values ​​of all unvisited wellheads is 0 (i.e., all segments are unfavorable), the ant will randomly select a wellhead from the list. Otherwise, the ant will use a roulette wheel selection method to determine the next wellhead. Roulette wheel selection is a probabilistic selection based on the proportion of fitness values; wellheads with higher fitness values ​​have a higher probability of being selected. Through this probabilistic selection mechanism, ants are more likely to choose wells with high pheromone concentration, short distances, small turning angles, and are unaffected by unfavorable flight segments, thus constructing a path with lower overall cost. After visiting all wells in the list, an ant path is generated, consisting of a fixed sequence, covering the coordinates of the starting well among multiple wells as the starting point and the coordinates of the ending well among multiple wells as the ending point, and traversing all third wells in multiple wells without repetition. Then, the pheromone matrix is ​​updated: the comprehensive cost of each ant path is calculated, determined as follows: a weighted sum is performed based on the energy cost, time cost, satisfaction cost, and preset weights corresponding to the energy cost, target time cost, and target satisfaction cost. The target energy cost is determined based on a preset maximum energy consumption benchmark and the total energy consumption required for the offshore drilling vessel to navigate the ant path. The total energy consumption is the sum of the energy consumption corresponding to all segments in the ant path. The energy consumption corresponding to each segment is determined at least based on a preset base energy consumption value and an environmental penalty coefficient. The time cost is determined based on the total travel time corresponding to the ant path and a preset normalized time benchmark. The preset normalized time benchmark is used to normalize the total travel time. The travel distance between two wellheads in the ant path constitutes one segment. The specific implementation involves calling the aforementioned comprehensive cost function to calculate the comprehensive cost of each ant path, which will not be elaborated further here. After obtaining the comprehensive cost of each ant path, the pheromone matrix is ​​updated based on the time cost within the comprehensive cost. Each ant path enhances the pheromone value (also known as pheromone concentration) of the edges it traverses (each edge corresponds to a flight segment). A matrix of all zeros is created to temporarily store the updated pheromone values. For each ant path, the pheromone value between each pair of wellheads on the ant path is enhanced according to its corresponding time cost, with the enhancement degree inversely proportional to the time cost.After accumulating the pheromone update values ​​for all ant paths, a preset pheromone evaporation rate is applied to add the pheromone update values ​​to the pheromone matrix, thus completing the pheromone update.

[0096] Finally, the ant path with the lowest overall cost after stopping iteration is determined as the optimal path. The path information of the optimal path is the target drilling path in the path information of the target drilling path corresponding to the ant colony optimization algorithm. Then, the target drilling path recorded after the algorithm is executed, along with the overall cost, time cost, energy cost, satisfaction cost, total travel distance, and total travel time of the target drilling path, are determined as the path information of the target drilling path.

[0097] like Figure 3 The diagram shown is a flowchart of an ant colony optimization algorithm according to an embodiment of this application. Figure 3 As shown, first, ant colony optimization is enabled, the pheromone matrix and heuristic matrix are initialized, and the algorithm iteration parameters are set: number of ants, number of iterations, etc. , This is an abbreviation for the pheromone factor and heuristic factors alpha and beta mentioned above. Then the algorithm iterative optimization process begins: constructing ant paths, calculating path fitness, updating the pheromone matrix, determining if the termination condition is met, stopping the iteration if the termination condition is met, outputting the optimal path, and ending the algorithm.

[0098] The process of using a genetic algorithm to minimize overall cost, under constraints across multiple dimensions of the marine environment model, to determine the path information of the target drilling route for the offshore drilling vessel by traversing the location coordinates of multiple wellheads from the starting wellhead to the ending wellhead, is as follows: First, the genetic algorithm is imported into the marine environment model (including various types of constraints, the location coordinates of multiple wellheads, and the distribution of marine obstacles), such as... Figure 4The diagram shows a flowchart of a genetic algorithm execution according to an embodiment of this application. When starting the genetic algorithm, the population is initialized, with each individual in the population representing a list of wellhead visit orders, ensuring that each wellhead is visited only once. In the offshore drilling path planning problem, this means creating a series of traversal lists containing all wellhead visit orders, but with different orders for each traversal list. During initialization, the starting wellhead is used as the beginning of the traversal list, and the ending wellhead is used as the end of the traversal list. The visit order of the remaining wellheads is then randomly arranged (each wellhead is visited only once) to ensure population diversity. Then, the algorithm parameters are set, such as population size, number of generations, crossover rate, and mutation rate. The appropriate setting of these parameters is crucial to algorithm performance; for example, the crossover rate and mutation rate should be high enough to promote the generation of new individuals and avoid premature convergence, but not too high to avoid compromising high-quality path features. The algorithm then begins its iterative process, which is the evolutionary process of the population. This process includes calculating individual fitness, selection, crossover, mutation, and determining whether the termination condition is met. If the condition is met, the optimal individual (i.e., the path information of the target drilling path determined by the genetic algorithm) is output. The specific iterative process is explained in detail below:

[0099] The core of a genetic algorithm lies in the iterative process (evolutionary process), which continues until a termination condition is met (e.g., reaching the maximum number of iterations). Each iteration process is as follows:

[0100] Calculate individual fitness: For each individual in the population (i.e., the list of multiple well-gate access orders), calculate the individual fitness. The individual fitness of each individual is the reciprocal of the comprehensive cost value corresponding to each individual. The calculation function of the comprehensive cost has been mentioned above and will not be repeated here. Calculate the sum of the fitness of all individuals in the population. Then perform selection and crossover operations. The purpose of these two operations is to select individuals with better performance as "parents" based on the current fitness distribution of the population, and to create new individuals by combining the "genetic" information of the parents through the concept of crossover in genetics. This gradually optimizes individual performance while maintaining population diversity. The process is as follows: Perform the selection operation based on the fitness value of each individual, and calculate the probability of each individual being selected as a parent based on its fitness value. Divide the fitness value of each individual by the total fitness value to obtain the fitness ratio, ensuring that individuals with higher fitness values ​​have a higher chance of being selected. The selection operation employs a roulette wheel selection mechanism, where individuals with higher fitness ratios have a greater probability of being selected, thus facilitating the transmission of superior traits to offspring. Specifically, in the parent selection phase, a random number *r* is generated, and parents are selected based on cumulative probability. The algorithm accumulates probability values ​​until the value of the random number *r* is less than or equal to the cumulative probability. This is equivalent to mapping the fitness ratio of each individual in the population to a roulette wheel allocated different segments, then spinning the wheel to select the individual that lands on the segment as a parent. The crossover operation in the genetic algorithm involves selecting two parent individuals and exchanging some of their genetic information at a certain crossover point (the crossover point is determined randomly to ensure population diversity) to generate the next generation of individuals. In the path planning problem, the crossover operation must ensure that the generated offspring paths remain valid, i.e., the same wellhead is not visited multiple times.

[0101] Repeat the above iterative process until the termination condition is met (e.g., reaching the maximum number of iterations). After the iteration ends, the individual with the lowest overall cost is determined as the optimal individual, which is the target drilling path in the path information of the target drilling path corresponding to the genetic algorithm. Then, the target drilling path recorded after the algorithm is executed, along with the overall cost, time cost, energy cost, satisfaction cost, total travel distance, and total travel time of the target drilling path, are determined as the path information of the target drilling path.

[0102] In the marine environment model, the Prim algorithm and Kruskal algorithm are imported into the marine environment model (including various types of constraints in the marine environment model, the location coordinates of multiple wellheads, and the distribution of marine obstacles), such as... Figure 5The diagram illustrates the execution flowchart of the minimum spanning tree algorithm, which includes Prim's algorithm and Kruskal's algorithm. Using Prim's algorithm to minimize overall cost, under constraints across multiple dimensions of the marine environment model, the process of determining the target drilling path for the offshore drilling vessel involves traversing the coordinates of multiple wellheads from the starting wellhead to the ending wellhead. The steps are as follows: Obtain all wellhead coordinate nodes (i.e., the coordinates of the aforementioned wellheads). Initialize a priority queue to store edge weights. Select the starting node (i.e., the aforementioned starting wellhead, for example, named X2) and add it to the access set. Traverse all adjacent edges of the current node, adding edges to the priority queue according to their weights. Extract the edge with the smallest weight from the queue and determine if the node connected to that edge has not been visited. If so, add the edge to the minimum spanning tree and mark the new node as visited; otherwise, discard the edge. After all nodes have been visited, output the Prim spanning tree. The next step is to construct a path based on the minimum spanning tree (corresponding to the output spanning tree), and use depth-first traversal (DFS) to traverse the spanning tree, outputting the optimized path sequence as the path information of the corresponding target drilling path.

[0103] The Kruskal algorithm, aiming to minimize overall cost, is employed under constraints across multiple dimensions of the marine environment model. The process involves traversing the coordinates of multiple wellheads from the starting wellhead to the ending wellhead to determine the target drilling path for the offshore drilling vessel. The steps are as follows: Obtain all wellhead coordinate nodes (i.e., the coordinates of the aforementioned multiple wellheads). Calculate the distances between all nodes, generate an edge set, sort the edges in ascending order by distance weight, initialize a union-difference data structure, and for the sorted edges, determine if the two nodes connected by the current edge belong to the same set. If not, add the edge to the minimum spanning tree and merge the sets containing the two nodes. If they belong to the same set, skip the edge to avoid loops. Then, check if all edges or the spanning tree have been traversed, and if the number of edges has reached n-1 (n being the total number of nodes). If so, output the Kruskal spanning tree. The next step is to construct a path based on the minimum spanning tree (corresponding to the output spanning tree), and then use depth-first search (DFS) to traverse the spanning tree. The optimized path sequence is output as the target drilling path in the path information of the target drilling path. Then, the comprehensive cost, time cost, energy cost, satisfaction cost, total travel distance, and total travel time of the target drilling path are determined as the path information of the target drilling path. It is important to note that in both algorithms, each wellhead is defined as a node. The edge between any two nodes is the travel segment between the two wellheads, and the edge weight is the segment cost, which is the sum of the time cost, energy cost, and satisfaction cost of that segment.

[0104] like Figure 6The diagram shown is an execution flowchart of a hybrid algorithm provided according to an embodiment of this application. The hybrid algorithm includes the genetic Prim algorithm and the genetic Kruskal algorithm.

[0105] The Genetic Prim algorithm determines the path information of the target drilling path for an offshore drilling vessel in the following way: With the objective of minimizing overall cost, the Prim algorithm, under constraints in multiple dimensions of the marine environment model, traverses the position coordinates of multiple wellheads from the starting wellhead to the ending wellhead to generate a first initial population; then, using the first initial population as input and under constraints in multiple dimensions of the marine environment model, the genetic algorithm iterates through the first initial population in multiple rounds to determine the path information of the target drilling path corresponding to the Genetic Prim algorithm. This is explained in detail below.

[0106] First, the Prim spanning tree obtained after executing the Prim algorithm is used. The Prim spanning tree is traversed to construct multiple individuals in the first initial population. Each individual is a path traversed from the Prim spanning tree, starting from the starting wellhead and ending at the ending wellhead, without repeating any wellheads. All individuals are combined into the first population. Then, a genetic algorithm is used with this first initial population as the input initial population. Under the constraints of multiple dimensions of the marine environment model, the first initial population is iterated in multiple rounds to determine the path information of the target drilling path corresponding to the genetic Prim algorithm. The specific implementation of the genetic algorithm has been explained above and will not be repeated here.

[0107] The genetic Kruskal algorithm, under constraints in multiple dimensions of the marine environment model, traverses the location coordinates of multiple wellheads from the starting wellhead to the ending wellhead to generate a second initial population. Using this second initial population as input, the genetic algorithm iterates through multiple rounds of the initial population under constraints in multiple dimensions of the marine environment model to determine the path information of the target drilling path corresponding to the genetic Kruskal algorithm. This is explained in detail below.

[0108] First, the Kruskal algorithm spanning tree obtained after executing the above-mentioned Kruskal algorithm is used to traverse the Kruskal algorithm spanning tree and construct multiple individuals in the second initial population. Each individual is a path traversed from the Kruskal algorithm spanning tree that starts at the starting wellhead and ends at the ending wellhead, without repeating any wellheads. All individuals are combined into the second population. Then, a genetic algorithm is used with this second initial population as input. Under the constraints of multiple dimensions of the marine environment model, the second initial population is iterated in multiple rounds to determine the path information of the target drilling path corresponding to the genetic Kruskal algorithm. The specific implementation of the genetic algorithm has been explained above and will not be repeated here.

[0109] It is important to note that the genetic Prim algorithm and the genetic Kruskal algorithm incorporate a stagnation mechanism. If the fitness of the solution falls below a threshold in a set number of iterations (10 rounds), the parameters are adaptively adjusted before the algorithm continues to run.

[0110] In the above path optimization algorithms, the method for determining whether a segment is in the second category is as follows: The segment type is determined based on wind direction, ocean current, and turning angle. Based on the conditions of wind direction angle, ocean current angle, and turning angle, the segment is classified into "Category 1" or "Category 2." Category 1 is also called the preferred segment, and Category 2 is also called the non-preferred segment. Specifically, based on satisfying the above constraints of multiple dimensions, the segment (i.e., the segment) classification criteria include three key environmental factors: wind direction angle (… ), ocean current angle ( ) and steering angle ( Specifically, its classification rules are as follows:

[0111] Category 1 flight segment: When both conditions are met , and At that time, this segment was marked as "Category 1".

[0112] Category 2 flight segment: If any of the above three angles exceeds... Then the flight segment is marked as "Category II". For example, Represents sailing against the wind. Represents sailing against the current. This represents a sharp turn. For each flight segment, the wind direction angle ( ), ocean current angle ( ) and steering angle ( Based on multiple constraints of the marine environment model, the following methods are used to determine the course of the offshore drilling vessel: Under the condition of satisfying the turning constraints, the course is determined by calculating the straight-line direction between the two wellheads corresponding to the navigation segment. Then, the wind direction is determined from the marine environment model based on meteorological and hydrological constraints. The angle between the offshore drilling vessel's course and the wind direction is then determined as the wind direction angle for that navigation segment. The ocean current angle is the angle between the offshore drilling vessel's course and the ocean current direction. The ocean current direction, determined from the marine environment model based on meteorological and hydrological constraints, is then read, and the angle between the offshore drilling vessel's course and the ocean current direction is determined as the wind direction angle for that navigation segment. The path information for any of the aforementioned target drilling paths includes at least the target drilling path, the segment type of each target segment, and multiple indicator values ​​corresponding to the target drilling path. These multiple indicator values ​​include at least the comprehensive cost, time cost, energy cost, satisfaction cost, total travel distance, and total travel time corresponding to the target drilling path. The target drilling path is determined after the corresponding path planning algorithm is executed; it consists of multiple target segments arranged in a fixed order, covering the coordinates of the starting wellhead among multiple wellheads as the starting point and the coordinates of the ending wellhead among multiple wellheads as the ending point, and traversing all third wellheads among the multiple wellheads without repetition. Each target segment is the travel distance between two different wellheads in the target drilling path, and the third wellhead is any wellhead other than the starting and ending wellheads among the multiple wellheads. The total travel time is the time required for the offshore drilling vessel to complete one full voyage from the starting wellhead to the ending wellhead according to the target drilling path.

[0113] Each target segment is categorized into either Category I or Category II. Category I segments indicate that the offshore drilling vessel's navigation comfort and operational safety indices are above the corresponding thresholds when navigating the target segment. Category II segments indicate that the offshore drilling vessel's navigation comfort and operational safety indices are below the corresponding thresholds when navigating the target segment. The rules for classifying each target segment into Category I and Category II segments are as follows: Determine the wind direction angle, ocean current angle, and turning angle of the offshore drilling vessel in the first target segment. The first target segment can be any one of multiple target segments. If the wind direction angle, ocean current angle, and turning angle are all less than the preset division angle (e.g., 90 degrees), the first target segment is designated as Category I. If at least one of the wind direction angle, ocean current angle, and turning angle is greater than the preset division angle, the first target segment is designated as Category II.

[0114] In the technical solution provided in step S204, the satisfaction cost corresponding to any target drilling path is determined in the following way: the total number of target segments in the target drilling path, the total number of second-class segments among all target segments, and the total number of first-class segments among all target segments are determined; the satisfaction value corresponding to the satisfaction index is determined based on the total number of target segments, the total number of second-class segments, and the total number of first-class segments; the target satisfaction cost is determined based on the satisfaction value and the preset weight corresponding to the satisfaction cost, wherein the target satisfaction cost is the satisfaction cost corresponding to the target drilling path.

[0115] The comprehensive cost corresponding to any target drilling path is determined as follows: The target comprehensive cost is obtained by weighted summation based on the target energy cost, target time cost, target satisfaction cost, and their corresponding preset weights. Here, the target energy cost, target time cost, and target satisfaction cost are the energy cost, time cost, and satisfaction cost corresponding to the target drilling path, respectively. The target comprehensive cost is the comprehensive cost corresponding to the target drilling path. The target energy cost is determined based on a preset maximum energy consumption benchmark value and the total energy consumption required for the offshore drilling vessel to navigate the target drilling path. The total energy consumption is the sum of the energy consumption corresponding to all target segments within the target drilling path. The energy consumption corresponding to each target segment is determined at least based on a preset base energy consumption value and an environmental penalty coefficient. The target time cost is determined based on the total navigation time corresponding to the target drilling path and a preset normalized time benchmark value. The preset normalized time benchmark value is used to normalize the total navigation time. The formula for calculating the comprehensive cost (comprehensive cost function) has been explained above and will not be repeated here.

[0116] Step S206: Output the path information for multiple target drilling paths.

[0117] In the technical solution provided in step S206, outputting multiple target drilling paths can be achieved in several ways: A path comparison table is constructed based on the multiple target drilling paths. This table includes the algorithm name for each path planning algorithm, the target drilling path information corresponding to each algorithm, and the execution time required for each algorithm to determine the target drilling path. The path comparison table is then pushed to the target object. The target object can be a client using the system or a client account, etc.

[0118] Figure 7This is a flowchart illustrating another method for determining offshore drilling paths according to an embodiment of this application. First, marine environmental parameters are initialized, wellhead coordinate data (i.e., wellhead location coordinates) are loaded, an optimization algorithm (i.e., path planning algorithm, including ant colony optimization algorithm, genetic algorithm, Prim algorithm, Kruskal algorithm, and two hybrid algorithms combined with genetic algorithm) are selected, then path optimization is performed, path indicators including distance, energy consumption, time, and satisfaction are calculated, then the results are visualized, and finally the optimal result is exported.

[0119] Figure 8 This is a visualization flowchart provided according to an embodiment of this application. Upon receiving a visualization request, the data visualization program begins execution. First, it determines whether the current optimization calculation is complete. After the calculation is complete, it loads the optimization result data, creates a canvas and subplots, selects the visualization type (path planning diagram (drawing wellhead location, drawing the optimal path, marking preferred / non-preferred segments (i.e., first / second type segments)), optimization progress curve (drawing distance convergence curve, drawing energy consumption change curve, drawing time optimization curve), environmental parameter display (drawing wind field vector, drawing flow field distribution)), adds legends and annotations, and then saves the image file. During the operation of the integrated intelligent path planning system in this embodiment, a data recording function is enabled. When an optimization completion event is triggered, the program responds, records and saves the current optimization result information, and displays a preview on the export interface.

[0120] like Figure 9 The diagram shown is a flowchart of a result export process according to an embodiment of this application. The process includes starting the result export, organizing and optimizing the result data, generating a statistical indicator table, formatting the output content, and selecting the export format (CSV file, JSON file, Excel file, or PDF report). For Excel export, the process involves creating a workbook, writing path data, writing performance indicators, and saving the file. For PDF report generation, the process involves creating a report template, inserting charts and tables, adding analysis conclusions, and exporting the PDF.

[0121] Because the execution process of the integrated intelligent path planning system involves the configuration of various parameters, once you enter the parameter configuration module, you can select by category (environmental parameters, algorithm parameters, cost parameters, etc.) due to the large number of parameter categories. After selecting the category, you can enter the corresponding parameter setting interface to make detailed parameter adjustments. Figure 10This is a parameter configuration flowchart provided according to an embodiment of this application. First, the parameter category is selected. When the category is environmental parameter, environmental parameter configuration is performed. Examples include wind speed (default 5 m / s), wind direction (default 120°), ocean current intensity (default 1.2), ocean current direction (default 80°), number of obstacles (default 10), and safety distance (default 50 units). When the category is algorithm parameter, algorithm parameter configuration is performed. This includes parameter configuration for each path planning algorithm, such as population size (default 30-50) and pheromone factor. The default value is 1.0, and the heuristic factor is... The default values ​​are 5.0, crossover rate (default 0.7-0.8), mutation rate (default 0.1-0.3), stagnation limit (default 10 generations), etc. When the category is cost parameters, configure the cost parameters. This includes energy consumption weight (default 0.3), time weight (default 0.3), damping weight (default 0.2), satisfaction weight (default 0.1), and configuration of daily operating costs and unit fuel costs for offshore drilling vessels, etc. After configuration, apply the parameter configuration and verify its validity. If the parameters are valid, save the parameter configuration, generate a configuration file, and end the parameter configuration. If the parameters are invalid, display an error message, modify the parameter configuration, and rerun the configuration.

[0122] The integrated intelligent path planning system in this application integrates six core optimization algorithms, including ant colony optimization, genetic algorithm, Prim algorithm, Kruskal algorithm, and two hybrid algorithms combined with genetic algorithm. The ant colony optimization algorithm simulates the intelligent behavior of ants communicating through pheromones to find the shortest path during foraging, gradually converging to a high-quality solution using a positive feedback mechanism, making it particularly suitable for solving distributed path optimization problems. The genetic algorithm draws on the natural selection and genetic mechanisms in biological evolution, iteratively evolving the population through selection, crossover, and mutation operations, possessing strong global search capabilities and good robustness, suitable for complex multi-objective optimization scenarios. A comparison of these two algorithms reveals the differences in the adaptability of different intelligent optimization strategies in ocean path planning problems. Prim algorithm, as a classic representative of minimum spanning tree algorithms, uses a greedy strategy to gradually expand the spanning tree from a single vertex, ensuring that each step selects the edge with the smallest weight, ultimately obtaining a minimum-cost tree structure connecting all nodes. Kruskal's algorithm is also used to construct minimum spanning trees, but it employs a global greedy strategy of sorting edges by weight. It efficiently identifies and avoids loops using a disjoint-set data structure, making it suitable for optimization problems in sparse graphs. The Genetic Prim algorithm combines the global search capability of genetic algorithms with the efficient local construction of Prim's algorithm, significantly improving the quality and convergence speed of the solution. The Genetic Kruskal algorithm integrates the evolutionary mechanism of genetic algorithms with the global greedy characteristics of Kruskal's algorithm. While maintaining population diversity, it uses the Kruskal method to quickly evaluate and optimize substructure, effectively balancing the contradiction between exploration and exploitation, and providing a more comprehensive and efficient solution for multi-constraint path planning in complex marine environments.

[0123] Two hybrid algorithms combined with genetic algorithms (hereinafter referred to as GA-MST): the Genetic Kruskal algorithm and the Genetic Prim algorithm, respectively, differ from traditional genetic algorithms (GA) primarily in that they introduce a minimum spanning tree (MST) as the initial solution generation mechanism, thereby improving the overall quality of the population and the search efficiency of the algorithm. GA-MST embeds the geometric characteristics of the problem and local optima into the initial population through heuristic paths constructed by the Kruskal or Prim algorithms. This design not only reduces the search space but also effectively reduces ineffective exploration in the early evolutionary stages. Genetic algorithms essentially rely on population diversity and fitness-driven optimization processes, but completely random initialization may lead to low initial population quality, requiring more generations to converge. GA-MST, however, utilizes the spanning tree of the Kruskal or Prim algorithms as a high-quality initial solution (i.e., the first or second initial solution mentioned above), ensuring that some individuals in the population have high fitness from the beginning, providing better gene fragments for crossover and mutation operations, thus accelerating the convergence speed. Furthermore, the introduction of MST does not weaken the global search capability of genetic algorithms, because genetic operators (such as crossover and mutation) still explore new solution spaces during evolution and avoid getting trapped in local optima through elite preservation. Therefore, GA-MST not only inherits the global optimization capability of genetic algorithms, but also improves optimization efficiency and solution quality through the heuristic properties of MST. This combination has significant advantages in complex optimization problems such as path planning. The initial design of GA-MST was to overcome the inefficiency problem that may be caused by random initialization of the population in traditional genetic algorithms, while combining the structural advantages of minimum spanning trees to improve the optimization performance and convergence speed of the algorithm. At the same time, the introduction of constraints will affect the combination effect of GA-MST, and further highlight its advantages in some cases. The heuristic solution provided by MST has low initial cost while satisfying basic geometric properties, and can provide a high-quality starting point close to feasible solution under complex constraints. This high-quality initial solution can reduce the unnecessary search caused by random initialization in the early stage of genetic algorithms, thereby finding solutions that satisfy constraints more quickly. Secondly, when dealing with constrained optimization problems, genetic algorithms, through their global search capabilities of crossover and mutation, can explore more feasible solution spaces based on the initial solution. The results of the Minimum Spanning Tree (MST) algorithm provide a structured reference framework for genetic algorithms (GA), enabling the search to focus more efficiently on potential high-quality solutions and avoid getting trapped in local optima. Therefore, under constraints, the combination of GA and MST not only finds feasible solutions faster but also improves the overall quality of the solutions. The more complex or diverse the constraints, the more effective the complementary relationship between the heuristic advantages of MST and the global search capabilities of GA becomes, making this combination even more efficient.

[0124] Through experimental comparison, the genetic algorithm demonstrates significant advantages over the ant colony algorithm, primarily due to three reasons: First, in terms of constraint handling, the genetic algorithm, through its encoding mechanism and fitness function, can more naturally integrate multiple constraints, while the ant colony algorithm, relying on pheromone update rules, is less adaptable to complex constraints. Second, regarding optimization stability, the genetic algorithm, through the balance of selection, crossover, and mutation operations, can more effectively avoid premature convergence, which is particularly crucial in multi-objective optimization scenarios. Most importantly, when environmental parameters change dynamically, the population diversity mechanism of the genetic algorithm makes it more robust, while the pheromone trajectory of the ant colony algorithm is prone to getting trapped in local optima. These advantages enable the genetic algorithm to achieve better optimization results in key indicators such as travel time, energy consumption control, and satisfaction. Furthermore, the method in this application innovatively combines the genetic algorithm with Kruskal's algorithm and Prim's algorithm respectively, forming two hybrid algorithms. This aims to study the synergistic effect of intelligent algorithms and traditional graph theory methods, exploring whether the advantages of both can be combined to obtain better planning results and overcome the limitations of traditional graph theory algorithms in complex dynamic environments.

[0125] Prim's algorithm provides a globally optimal spatial topology through minimum spanning tree construction, but lacks adaptability to multi-objective optimization and dynamic environmental changes. Genetic algorithms achieve multi-objective search through population evolution, but are prone to getting trapped in local optima. The fusion of these two algorithms creates a collaborative optimization mechanism: the minimum spanning tree path generated by Prim's algorithm serves as a high-quality initial population (i.e., the first initial population mentioned above), significantly improving convergence speed; the crossover and mutation operations of the genetic algorithm (such as sequential crossover and exchange mutation) introduce environmental adaptability, overcoming the static path limitations of Prim's algorithm. This innovative architecture effectively balances global optimality and environmental adaptability, making it particularly suitable for variable marine environments such as ocean currents and wind speeds. Kruskal's algorithm, on the other hand, suffers from the opposite problem. Its edge sorting mechanism disrupts spatial continuity, leading to a high rate of path loops. This further exacerbates the problem of genetic algorithms getting trapped in local optima, causing this innovative algorithm to frequently result in the same outcome as the original algorithm, and sometimes generating fixed topological loops, repeatedly adding invalid paths. In summary, Kruskal's globally greedy strategy conflicts with the local continuity requirement of path planning. Prim's vertex expansion and path generation mechanisms are better suited to navigation continuity constraints, forming a superior topological foundation.

[0126] like Figure 11The diagram shown is a schematic representation of an operating environment according to an embodiment of this application. It illustrates an example of marine environmental parameters for a marine environment model. The blue circles in the diagram represent measurement points, i.e., the coordinates of all wellheads to be drilled (named X1 to X20 in the diagram). The red crosses represent points to be removed from marine obstacles; these are already drilled points. The yellow arrows represent wind direction (e.g., 120°, wind speed 5 m / s), and the blue arrows represent ocean currents (e.g., 80°, intensity 1.2).

[0127] like Figure 12 The diagram shown is a comparison of running results according to an embodiment of this application, illustrating the process of... Figure 11 The results of running various algorithms in the specified environment are compared in the form of comparative graphs. These graphs visually output the optimized paths (i.e., the target drilling paths) of each algorithm (Ant Colony Algorithm (i.e., the Ant Colony Optimization Algorithm mentioned above), Genetic Algorithm, Prim Algorithm, Kruskal Algorithm, Innovative Genetic-Kruskal Algorithm (i.e., the Genetic Kruskal Algorithm mentioned above), and Innovative Genetic-Prim Algorithm (i.e., the Genetic Prim Algorithm mentioned above)). Red circles represent the endpoint wellhead, green circles represent the starting wellhead (e.g., wellhead X2), and blue circles represent measurement points (i.e., other wellheads). Green line segments represent the first type of segment in the target drilling path, and yellow line segments represent the second type of segment in the target drilling path.

[0128] like Figure 13 The diagram shown is a schematic diagram of the optimization progress of the first algorithm provided according to the embodiments of this application, which shows the optimization progress of the genetic algorithm. The horizontal axis represents the number of iterations / generations, and the vertical axis represents various indicators (energy consumption, time, satisfaction, cost).

[0129] like Figure 14 The diagram shown illustrates the optimization progress of the second algorithm according to an embodiment of this application. It displays the optimization progress of the innovative genetic-Prim algorithm (i.e., the aforementioned genetic-Prim algorithm). The horizontal axis represents the number of iterations / generations, and the vertical axis represents various indicators (energy consumption, time, satisfaction, cost). It can be seen that, compared to... Figure 13 Compared to a simple genetic algorithm, the innovative genetic-Prim algorithm (i.e., the genetic-Prim algorithm mentioned above) performs better.

[0130] like Figure 15 The diagram shown illustrates the optimization progress of the third algorithm provided in this application, according to an embodiment of the present application. It displays the optimization progress of the innovative genetic-Kruskal algorithm (i.e., the aforementioned genetic-Kruskal algorithm). The horizontal axis represents the number of iterations / generations, and the vertical axis represents various indicators (energy consumption, time, satisfaction, cost). It can be seen that, compared to... Figure 13 Compared to a simple genetic algorithm, the innovative genetic-Kruskal algorithm (i.e., the genetic Kruskal algorithm mentioned above) performs better.

[0131] This application also provides a device for determining offshore drilling paths, such as... Figure 16 As shown, it includes:

[0132] Create module 1602 to create a marine environment model. The marine environment model is used to simulate the marine conditions for offshore drilling operations by an offshore drilling vessel. The marine conditions include at least the coordinates of multiple wellheads to be drilled, the coordinates of marine obstacles, and marine environmental parameters, which include at least wind direction information and ocean current information.

[0133] The determination module 1604 is used to determine the path information of multiple target drilling paths for offshore drilling vessels under the marine environment model with the goal of minimizing the overall cost. The overall cost is determined by multiple sub-costs and preset weights for each sub-cost. The multiple sub-costs include energy cost, time cost, and satisfaction cost. The satisfaction cost is determined based on the satisfaction index, which is used to quantify at least the operational safety index and navigation comfort index of the offshore drilling vessel according to the drilling path.

[0134] Output module 1606 is used to output path information for multiple target drilling paths.

[0135] It should be noted that, Figure 16 The device shown for determining the offshore drilling path is used to perform... Figure 2 The method for determining the offshore drilling path shown is therefore Figure 2 The relevant explanations in the method for determining the offshore drilling path also apply to the device for determining the offshore drilling path, and will not be repeated here.

[0136] It should be noted that the modules in the above-mentioned offshore drilling path determination device can be program modules (e.g., a set of program instructions to implement a certain function) or hardware modules. For the latter, they can be in the following forms, but are not limited to these: each of the above modules is in the form of a processor, or the functions of each of the above modules are implemented by a processor.

[0137] This application also provides a non-volatile storage medium, which includes a stored program, wherein, when the program is running, it controls the device where the non-volatile storage medium is located to execute the offshore drilling path determination method of any of the above embodiments.

[0138] This application also provides an electronic device, which includes a processor for running a program, wherein the method for determining the offshore drilling path of any of the above embodiments is executed when the program is running.

[0139] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the method for determining the offshore drilling path of any of the above embodiments.

[0140] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0141] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0142] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0143] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0144] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to related technologies, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0145] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method of determining an offshore drilling path, characterized by, The method comprises: creating a marine environment model, wherein the marine environment model is used to simulate marine conditions for offshore drilling operations of an offshore drilling vessel, the marine conditions including at least coordinate positions of a plurality of wellheads to be drilled, position coordinates of offshore obstacles, marine environment parameters including at least wind direction information and ocean current information, and navigation parameters of the offshore drilling vessel including at least a safety distance between a drilled well and a navigation path, a first type of navigation section energy consumption coefficient, or a second type of navigation section energy consumption coefficient, wherein the first type of navigation section represents that the offshore drilling vessel has a navigation comfort index and an operation safety index higher than corresponding thresholds when navigating in a target navigation section, and the second type of navigation section represents that the offshore drilling vessel has the navigation comfort index and the operation safety lower than corresponding thresholds when navigating in a target navigation section; under the marine environment model, path information of a plurality of target drilling paths of the offshore drilling vessel is determined by using a plurality of path planning algorithms respectively, with the objective of minimizing a comprehensive cost, wherein the comprehensive cost is determined by a plurality of sub-costs and preset weights corresponding to each sub-cost, the plurality of sub-costs including energy consumption cost, time cost, and satisfaction cost, the satisfaction cost being determined according to a satisfaction index, and the satisfaction index being used to quantify at least the operation safety and the navigation comfort of the offshore drilling vessel when drilling offshore according to a drilling path; outputting the path information of the plurality of target drilling paths; the comprehensive cost corresponding to any target drilling path is determined by weighted summation of a target energy consumption cost, a target time cost, a target satisfaction cost, and preset weights corresponding to the target energy consumption cost, the target time cost, and the target satisfaction cost, to obtain a target comprehensive cost, wherein the target energy consumption cost, the target time cost, and the target satisfaction cost are the energy consumption cost, the time cost, and the satisfaction cost corresponding to the target drilling path, the target comprehensive cost is the comprehensive cost corresponding to the target drilling path, the target energy consumption cost is determined according to a preset maximum energy consumption reference value and a total energy consumption required for the offshore drilling vessel to navigate the target drilling path, the total energy consumption is the sum of energy consumptions corresponding to all target navigation sections in the target drilling path, and the energy consumption corresponding to each target navigation section is determined at least according to a preset basic energy consumption value and an environmental penalty coefficient, and the target time cost is determined according to a total navigation time corresponding to the target drilling path and a preset normalized time reference value, wherein the preset normalized time reference value is used to perform time normalization on the total navigation time, and the environmental penalty coefficient includes the first type of navigation section energy consumption coefficient and the second type of navigation section energy consumption coefficient; under the marine environment model, path information of a plurality of target drilling paths of the offshore drilling vessel is determined by using a plurality of path planning algorithms respectively, with the objective of minimizing a comprehensive cost, comprising: The path information of the plurality of target drilling paths of the offshore drilling ship is determined by traversing the position coordinates of the plurality of wellheads from a starting wellhead to an ending wellhead under the constraint conditions of a plurality of different dimensions of the marine environment model by using a plurality of path planning algorithms respectively, wherein the plurality of path planning algorithms include an ant colony optimization algorithm, a genetic algorithm, a Prim algorithm, a Kruskal algorithm, a genetic Prim algorithm and a genetic Kruskal algorithm, the genetic Prim algorithm is a hybrid algorithm combining the genetic algorithm and the Prim algorithm, and the genetic Kruskal algorithm is a hybrid algorithm combining the genetic algorithm and the Kruskal algorithm.

2. The method of claim 1, wherein, The path information of any target drilling path at least includes a target drilling path, a segment type of each target segment, and a plurality of index values corresponding to the target drilling path, the plurality of index values at least including a comprehensive cost, a time cost, an energy consumption cost, a satisfaction cost corresponding to the target drilling path, and a total navigation distance and a total navigation time of the target drilling path, wherein the target drilling path is a path determined after the execution of the corresponding path planning algorithm, which is composed of a plurality of target segments in a fixed order, covers the coordinate position of the starting wellhead in the plurality of wellheads as the starting point, the coordinate position of the ending wellhead in the plurality of wellheads as the ending point, and does not repeat the traversal of all other wellheads in the plurality of wellheads, wherein each target segment is a navigation route between two different wellheads in the target drilling path, and the other wellheads are wellheads in the plurality of wellheads except the starting wellhead and the ending wellhead; the total navigation time is the time required for the offshore drilling ship to complete navigation from the starting wellhead to the ending wellhead once according to the target drilling path.

3. The method of claim 1, wherein, Outputting the plurality of target drilling paths includes: constructing a path comparison table and a path comparison diagram according to the plurality of target drilling paths, wherein the path comparison table at least includes the algorithm name of each path planning algorithm, the target drilling path information corresponding to each path planning algorithm, and the execution time required for each algorithm to determine the target drilling path, the path comparison diagram is used for visualizing the plurality of target drilling paths; pushing the path comparison table and the path comparison diagram to a target object.

4. The method of claim 2, wherein, The multiple different dimensional constraint conditions at least include a speed constraint condition of the offshore drilling vessel, a turning constraint condition of the offshore drilling vessel in a voyage process, and an energy consumption constraint condition of the offshore drilling vessel in the voyage process, wherein the speed constraint condition is used to constrain an actual speed of the offshore drilling vessel in the voyage, and the actual speed is determined according to a preset reference speed, a wind direction influence factor, and a flow direction influence factor, different wind direction angles correspond to different wind direction influence factors, the wind direction angle is an angle between a wind direction and a heading direction of the offshore drilling vessel, and the flow direction influence factor is determined at least according to a sea current angle, the sea current angle is an angle between the heading direction of the offshore drilling vessel and a sea current direction, and the energy consumption constraint condition is used to constrain an actual energy consumption of the offshore drilling vessel in the voyage, and the actual energy consumption is determined according to a reference energy consumption, a first type of voyage section energy consumption coefficient, and a second type of voyage section energy consumption coefficient.

5. The method of claim 4, wherein, The voyage section type of each target voyage section is divided into the first type of voyage section or the second type of voyage section, and a rule for dividing each target voyage section into the first type of voyage section and the second type of voyage section is as follows: The wind direction angle, the sea current angle, and a turning angle of the offshore drilling vessel in the first target voyage section are determined, wherein the first target voyage section is any one of the multiple target voyage sections. In a case where the wind direction angle, the sea current angle, and the turning angle are all less than a preset division angle, the first target voyage section is determined as the first type of voyage section. In a case where at least one of the wind direction angle, the sea current angle, and the turning angle is greater than the preset division angle, the first target voyage section is determined as the second type of voyage section.

6. The method of claim 5, wherein, The satisfaction cost corresponding to any target drilling path is determined in the following manner: The total number of target voyage sections in the target drilling path, the total number of the second type of voyage sections in all target voyage sections, and the total number of the first type of voyage sections in all target voyage sections are determined. A satisfaction value corresponding to a satisfaction index is determined according to the total number of target voyage sections, the total number of the second type of voyage sections, and the total number of the first type of voyage sections. A target satisfaction cost is determined according to the satisfaction value and a preset weight corresponding to a satisfaction cost, wherein the target satisfaction cost is the satisfaction cost corresponding to the target drilling path.

7. The method of claim 1, wherein, The path information of the target drilling path of the offshore drilling vessel is determined in the following manner: In a case where the path planning algorithm is the genetic Prim algorithm, a first initial population is generated by traversing position coordinates of the multiple wellheads from a starting wellhead to an ending wellhead by using the Prim algorithm under the multiple different dimensional constraint conditions of the marine environment model, so as to minimize the comprehensive cost. The path information of the target drilling path corresponding to the genetic Prim algorithm is determined by using a genetic algorithm to perform multiple rounds of iteration on the first initial population as input and under the multiple different dimensional constraint conditions of the marine environment model.

8. The method of claim 1, wherein, The path information of the target drilling path of the offshore drilling vessel is determined in the following manner: In the case that the path planning algorithm is the genetic Kruskal algorithm, a second initial population is generated by traversing the position coordinates of the wellheads from a starting wellhead to an ending wellhead under the constraint conditions of different dimensions of the marine environment model by the Kruskal algorithm aiming at minimizing the comprehensive cost; The path information of the target drilling path corresponding to the genetic Kruskal algorithm is determined by performing multiple rounds of iterations on the second initial population under the constraint conditions of different dimensions of the marine environment model by the genetic algorithm taking the second initial population as input.

9. The method of claim 1, wherein, The path information of the target drilling path of the offshore drilling ship is determined in the following manner: In the case that the path planning algorithm is the ant colony optimization algorithm, an information matrix and a heuristic matrix are created and iteration parameters are configured, wherein the information matrix is an n×n matrix, n represents the total number of wellheads, the information matrix is used to guide the path selection of ants in the ant colony optimization algorithm, each element in the heuristic matrix represents the reciprocal of the relative distance between any two wellhead position coordinates, and the iteration parameters at least include the number of ants, the number of iterations, the pheromone factor and the heuristic factor of the ant colony optimization algorithm; The following steps are repeatedly performed until the number of iterations is reached, the iteration is stopped, and the ant path with the minimum comprehensive cost after the iteration is stopped is determined as the path information of the target drilling path corresponding to the ant colony optimization algorithm: Each ant constructs an ant path according to the information matrix, the pheromone factor and the heuristic factor, wherein one ant path corresponds to one drilling path; The comprehensive cost corresponding to the constructed ant path is calculated, the information matrix is updated based on the time cost in the corresponding comprehensive cost, and the updated information matrix is determined as a new information matrix.

10. The method of claim 1, wherein, In the case that the path planning algorithm is the genetic algorithm, the path information of the target drilling path of the offshore drilling ship is determined in the following manner: In the case that the path planning algorithm is the genetic algorithm, an initial population is initialized, wherein each individual in the population corresponds to one drilling path; The following process is repeatedly performed until the maximum number of iterations is reached, the iteration is stopped, and the individual with the minimum comprehensive cost in the population after the iteration is stopped is determined as the path information of the target drilling path of the offshore drilling ship corresponding to the genetic algorithm: The individual fitness of each individual in the population is calculated, wherein the individual fitness is the reciprocal of the comprehensive cost corresponding to each individual; The sum of the fitness of all individuals in the population is calculated, and the individual fitness of each individual is divided by the sum of the fitness to obtain the fitness proportion of each individual; The individuals in the population are updated according to the fitness proportion of the individual to obtain a new population.

11. The method of claim 1, wherein, The path information of the target drilling path of the offshore drilling ship is determined in the following manner: In the case that the path planning algorithm is the Prim algorithm, each wellhead is determined as a node, an edge between any two nodes is determined as a voyage segment, and a voyage segment cost of each voyage segment is determined as an edge weight of the edge between the two nodes, wherein the voyage segment cost is a sum of a time cost, an energy consumption cost and a satisfaction cost of the voyage segment; The Prim algorithm is adopted to traverse all wellheads according to the edge weight, with the starting wellhead as the starting point and the ending wellhead as the ending point, to obtain a Prim algorithm spanning tree; The Prim algorithm spanning tree is traversed by using a depth-first traversal, to obtain path information of the target drilling path of the offshore drilling ship corresponding to the Prim algorithm.

12. The method of claim 1, wherein, The path information of the target drilling path of the offshore drilling ship is determined in the following manner: In the case that the path planning algorithm is the Kruskal algorithm, each wellhead is determined as a node, an edge between any two nodes is determined as a voyage segment, and a voyage segment cost of each voyage segment is determined as an edge weight of the edge between the two nodes, wherein the voyage segment cost is a sum of a time cost, an energy consumption cost and a satisfaction cost of the voyage segment; The Kruskal algorithm is adopted to traverse all wellheads according to the edge weight, with the starting wellhead as the starting point and the ending wellhead as the ending point, to obtain a Kruskal algorithm spanning tree; The Kruskal algorithm spanning tree is traversed by using a depth-first traversal, to obtain path information of the target drilling path of the offshore drilling ship corresponding to the Kruskal algorithm.

13. An apparatus for determining a marine drilling path, characterized by It comprises: a creating module configured to create a marine environment model, wherein the marine environment model is used to simulate marine conditions of offshore drilling operations of an offshore drilling ship, the marine conditions at least including coordinate positions of a plurality of wellheads to be drilled, position coordinates of offshore obstacles, marine environment parameters, the marine environment parameters at least including wind direction information and ocean current information, and navigation parameters of the offshore drilling ship, the navigation parameters at least including a safety distance between a collected drilling and navigation path, a first type of voyage segment energy consumption coefficient or a second type of voyage segment energy consumption coefficient; The determining module is configured to determine path information of a plurality of target drilling paths of the offshore drilling ship under the marine environment model and with the minimum comprehensive cost as the target: the path information of the plurality of target drilling paths of the offshore drilling ship is determined by traversing the position coordinates of the plurality of wellheads from a starting wellhead to an ending wellhead under a plurality of different dimensional constraint conditions of the marine environment model by using a plurality of path planning algorithms with the minimum comprehensive cost as the target, wherein the plurality of path planning algorithms include an ant colony optimization algorithm, a genetic algorithm, a Prim algorithm, a Kruskal algorithm, a genetic Prim algorithm, and a genetic Kruskal algorithm, the genetic Prim algorithm is a hybrid algorithm combining the genetic algorithm and the Prim algorithm, the genetic Kruskal algorithm is a hybrid algorithm combining the genetic algorithm and the Kruskal algorithm, the comprehensive cost is determined by a plurality of sub-costs and preset weights corresponding to each sub-cost, the plurality of sub-costs include an energy consumption cost, a time cost, and a satisfaction cost, the satisfaction cost is determined according to a satisfaction index, and the satisfaction index is used to quantify at least an operation safety index and a navigation comfort index of the offshore drilling ship for offshore drilling according to a drilling path; the comprehensive cost corresponding to any target drilling path is determined by: performing weighted summation on a target energy consumption cost, a target time cost, a target satisfaction cost, and preset weights corresponding to the target energy consumption cost, the target time cost, and the target satisfaction cost to obtain a target comprehensive cost, wherein the target energy consumption cost, the target time cost, and the target satisfaction cost are the energy consumption cost, the time cost, and the satisfaction cost corresponding to the target drilling path, the target comprehensive cost is the comprehensive cost corresponding to the target drilling path, the target energy consumption cost is determined according to a preset maximum energy consumption reference value and a total energy consumption required for the offshore drilling ship to navigate on the target drilling path, the total energy consumption is a sum of energy consumptions corresponding to all target navigation segments in the target drilling path, and the energy consumption corresponding to each target navigation segment is determined at least according to a preset basic energy consumption value and an environmental penalty coefficient, and the target time cost is determined according to a total navigation time corresponding to the target drilling path and a preset normalized time reference value, wherein the preset normalized time reference value is used to perform time normalization on the total navigation time, and the environmental penalty coefficient includes the first-type navigation segment energy consumption coefficient and the second-type navigation segment energy consumption coefficient. The output module is configured to output the path information of the plurality of target drilling paths.

14. A non-volatile storage medium, comprising: The nonvolatile storage medium stores a program, and when the program is executed, the device in which the nonvolatile storage medium is located performs the offshore drilling path determination method in any one of claims 1 to 12.

15. An electronic device, comprising: The memory and the processor are configured to execute the offshore drilling path determination method in any one of claims 1 to 12 when the program stored in the memory is executed. ​ 16. A computer program product comprising computer instructions, characterized in that, The computer instructions, when executed by a processor, implement the method for determining a marine drilling path according to any one of claims 1 to 12.

Images