Control method and device for river and sea towing formation of large floating production platform

Abstract

The invention relates to a control method and device for a river-sea towing formation of a large-scale floating production platform, and belongs to the technical field of ocean engineering towing, and the control method for the river-sea towing formation of the large-scale floating production platform comprises the steps: collecting the multi-source monitoring data of the towing formation in real time; performing coupling feature extraction and feature fusion on the multi-source monitoring data of the towing formation at the current moment to obtain target data; taking the target data as the input of a trajectory prediction model, and determining the output of the trajectory prediction model as the trajectory of the towing formation at the next moment; and risk prediction is carried out based on the trajectory of the towing formation at the next moment, and whether the pose of the towing formation is controlled and adjusted is determined based on a risk prediction result. According to the method, formation trajectory prediction and risk prediction are carried out by fusing a deep learning method and a distributed cooperative control theory, and safe implementation of a towing task of a large floating production platform from a river to a coastal water area is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of marine engineering towing, and in particular to a control method and device for a river-sea towing formation of a large floating production platform. Background Art

[0002] With the continuous advancement of offshore oil and gas resource development, large floating production platforms are increasingly used in the offshore oil and gas industry. These platforms are usually built along rivers and coastal ports, but because they have no power, they need to be towed and transported by tugboats.

[0003] The large ship flow and complex navigation environment in the narrow waterways of rivers and the large tidal range and dense fishing boats in coastal ports make the river-sea linkage towing technology difficult, with high risk factors and many influencing factors. The existing floating production platform towing solutions are difficult to meet the safety requirements of towing large floating production platforms from rivers to coastal waters. Summary of the invention

[0004] In view of this, it is necessary to provide a control method and device for a large floating production platform river-sea towing towing formation to solve the problem that the existing floating production platform towing scheme is difficult to meet the safety requirements of the towing mission of large floating production platforms from rivers to coastal waters.

[0005] In order to solve the above problems, in a first aspect, the present invention provides a control method for a river-sea towing formation of a large floating production platform, comprising: Real-time collection of multi-source monitoring data of the towing formation, wherein the multi-source monitoring data includes motion state parameters and navigation environment parameters of the main tugboat and the large floating production platform; The target data is obtained by performing coupled feature extraction and feature fusion on the multi-source monitoring data of the towing formation at the current moment; The target data is used as the input of the trajectory prediction model, and the output of the trajectory prediction model is determined as the trajectory of the towing formation at the next moment. The trajectory prediction model predicts the trajectory of a single ship based on the GRU-ADMM network, and predicts the trajectory of the towing formation through a distributed collaborative optimization algorithm. The trajectory prediction of a single ship includes the trajectory prediction of the main tugboat and the large floating production platform. A risk prediction is performed based on the trajectory of the towing formation at the next moment, and a determination is made based on the risk prediction result whether to control and adjust the position and posture of the towing formation.

[0006] In a possible implementation, the risk prediction based on the trajectory of the towing formation at the next moment includes: The coupled feature extraction is performed on the multi-source monitoring data of the towing formation at the next moment, and the towing behavior characteristics, environmental impact characteristics, ship motion state characteristics and traffic flow impact characteristics corresponding to the towing formation at the next moment are obtained; Preprocess the towing behavior characteristics, environmental impact characteristics, ship motion state characteristics and traffic flow impact characteristics corresponding to the towing formation at the next moment to obtain the risk feature matrix corresponding to the towing formation at the next moment; The risk feature matrix corresponding to the towing formation at the next moment is used as the input of the risk prediction model, and risk prediction is performed based on the risk value output by the risk prediction model. The risk prediction model is trained based on the historical risk feature matrix and historical risk value.

[0007] In one possible implementation, the risk value is calculated based on the following formula:

[0008] in, represents the risk value, , , , is the weight factor, represents the minimum distance risk index, represents the shortest collision time risk index, Indicates the sailing angle of the towing formation relative to other ships. Indicates the towline tension.

[0009] In a possible implementation, determining whether to control and adjust the position and posture of the towing formation based on the risk prediction result includes: When the risk value output by the risk prediction model is greater than the risk threshold, it is determined to control and adjust the position and posture of the towing formation; When the risk value output by the risk prediction model is less than or equal to the risk threshold, it is determined that no control adjustment is performed on the posture of the towing formation; The controlling and adjusting the posture of the towing formation includes: adjusting the tugboat configuration, track and formation posture of the towing formation.

[0010] In a possible implementation, the adjusting of the tugboat configuration of the towing formation includes: Taking the towing mission cost as the objective function and the thrust balance, torque balance and equipment capacity limitation as the constraint functions, the number of tugboats, tugboat power and thrust direction of the towing formation are adjusted.

[0011] In a possible implementation, the adjusting of the number of tugboats, the power of tugboats and the thrust direction of tugboats in the towing formation includes: Taking the number of tugboats, tugboat power and tugboat thrust direction in the towing formation as variables, the global optimal combination is generated based on genetic algorithm. The global optimal combination is locally optimized based on a deep reinforcement learning network, and the locally optimized global optimal combination is optimized based on a genetic algorithm until a variable combination with a minimum objective function value is determined, and the tugboat configuration of the towing formation is adjusted based on the corresponding variable combination with the minimum objective function value.

[0012] In a possible implementation, the track of the towing formation is adjusted, including: Taking the total path cost as the objective function and the channel width, speed, maneuverability, channel depth and ship encounter distance as the constraint functions, the track of the towing formation is adjusted based on the A* algorithm.

[0013] In a possible implementation, the adjusting the formation posture of the towing formation includes: The formation shape model corresponding to the towing formation is constructed based on the chain leader-follower model; Based on the DDPG algorithm and the formation shape model corresponding to the towing formation, the propulsion force and steering torque of each ship in the towing formation are adjusted.

[0014] In a possible implementation, the controlling and adjusting the posture of the towing formation further includes: Adjust the speed of each ship based on the towing formation's real-time updated formation action space; The towline tension and towing force are calculated based on the thrust and steering torque of each ship in the state space updated in real time by the towing formation, and the towline length of each ship is adjusted.

[0015] On the other hand, the present invention also provides a control device for a river-sea towing formation of a large floating production platform, comprising: A collection module, used to collect multi-source monitoring data of the towing formation in real time, wherein the multi-source monitoring data includes motion state parameters and navigation environment parameters of the main tugboat and the large floating production platform; A processing module is used to extract and fuse coupled features of the multi-source monitoring data of the towing formation at the current moment to obtain target data; The prediction module is used to use the target data as the input of the trajectory prediction model and determine the output of the trajectory prediction model as the trajectory of the towing formation at the next moment. The trajectory prediction model predicts the trajectory of a single ship based on the GRU-ADMM network and predicts the trajectory of the towing formation through a distributed collaborative optimization algorithm. The trajectory prediction of a single ship includes the trajectory prediction of the main tugboat and the large floating production platform. The control module is used to make risk prediction based on the trajectory of the towing formation at the next moment, and determine whether to make control adjustments to the position and posture of the towing formation based on the risk prediction result.

[0016] In a second aspect, the present invention further provides a control terminal, including a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the method for controlling the river-sea towing formation of a large floating production platform described in any of the above implementations.

[0017] In a third aspect, the present invention further provides a computer-readable storage medium for storing computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the method for controlling a river-sea towing formation of a large floating production platform as described in any of the above-mentioned implementations.

[0018] The beneficial effects of the present invention are as follows: the control method and device for the river-sea towing formation of a large floating production platform provided by the present invention collects multi-source monitoring data of the towing formation at the current moment to perform coupled feature extraction and feature fusion to obtain target data for trajectory prediction at the next moment, and improves data accuracy to ensure the reliability of trajectory prediction, and then predicts the trajectory of the towing formation through a distributed collaborative optimization algorithm based on a trajectory prediction model based on a GRU-ADMM network, providing accurate trajectory guidance for formation control and task execution, and finally predicts risks through multi-source data corresponding to the predicted trajectory, and determines whether to control and adjust the towing formation according to the risk prediction result, so as to ensure the safety of the towing formation during the towing operation. The present invention performs trajectory prediction and risk prediction by integrating deep learning methods and distributed collaborative control theory, thereby ensuring the safe implementation of the towing mission of the large floating production platform from rivers to coastal waters. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic flow chart of an embodiment of a control method for a river-sea towing formation of a large floating production platform provided by the present invention; Figure 2 A schematic diagram of an embodiment of the risk prediction and control process provided by the present invention; Figure 3 A schematic flow chart of an embodiment of a tugboat configuration optimization process provided by the present invention; Figure 4 A schematic flow chart of an embodiment of a towing formation and operation process provided by the present invention; Figure 5A schematic structural diagram of an embodiment of a control device for a river-sea towing formation of a large floating production platform provided by the present invention; Figure 6 A schematic structural diagram of an embodiment of a control terminal provided by the present invention. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0021] In the description of the embodiments of the present invention, unless otherwise specified, "multiple" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone.

[0022] The descriptions of "first", "second", etc. involved in the embodiments of the present invention are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" or "second" may explicitly or implicitly include at least one of the features.

[0023] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0024] Before presenting the embodiments, the following terms are explained.

[0025] Floating production platform: A floating production platform is a facility used for offshore oil and gas field development. It is capable of producing, processing and storing oil and gas at sea, and is usually used in deep sea or offshore areas.

[0026] Floating production platform towing: Floating production platform towing refers to the process of towing a floating production platform from one location to another, a process that usually involves complex operations and coordination to ensure the safety and stability of the platform.

[0027] The present invention provides a control method and device for a river-sea towing formation of a large floating production platform, which are respectively described below.

[0028] Figure 1 A flow chart of an embodiment of a control method for a large floating production platform river-sea towing formation provided by the present invention is as follows: Figure 1 As shown, the control method of the river-sea towing formation of a large floating production platform includes: S101. Collect multi-source monitoring data of the towing formation in real time, wherein the multi-source monitoring data includes motion state parameters and navigation environment parameters of the main tugboat and the large floating production platform.

[0029] It should be noted that the multi-source monitoring data of the towing formation may include the motion state parameters and navigation environment parameters of the main tugboat and the large floating production platform. The motion state parameters may include data collected from the Global Positioning System (GPS) sensors, Automatic Identification System (AIS), and Inertial Measurement Unit (IMU) on the ship, while the navigation environment parameters may be data obtained from radars, weather stations, video monitoring stations, etc.

[0030] S102, performing coupled feature extraction and feature fusion on the multi-source monitoring data of the towing formation at the current moment to obtain target data.

[0031] It should be noted that the preprocessing of the multi-source monitoring data of the towing formation at the current moment can include operations such as outlier removal, timestamp unification, and coordinate system alignment to ensure the quality and consistency of the data. Feature extraction of the preprocessed multi-source monitoring data can be to extract key features related to ship motion from the multi-source monitoring data, mainly including: ship state features such as position, speed, heading angle, rudder angle, etc.; formation coordination features such as tow cable tension, relative distance and angle between ships, etc.; environmental features such as wind speed, flow rate, wave height, wave direction, etc. When performing feature fusion, the attention mechanism can be used to weight the data from different sensors to dynamically allocate the importance of different data sources, and the Kalman filtering method can be used to fuse the time series data with the spatial topological relationship. Kalman filtering can effectively reduce noise, improve the accuracy of data, and enable data from different sensors to work together.

[0032] S103. Use the target data as the input of the trajectory prediction model, and determine the output of the trajectory prediction model as the trajectory of the towing formation at the next moment. The trajectory prediction model predicts the trajectory of a single ship based on the GRU-ADMM network, and predicts the trajectory of the towing formation through a distributed collaborative optimization algorithm. The trajectory prediction of a single ship includes the trajectory prediction of the main tugboat and the large floating production platform.

[0033] It should be noted that: after obtaining the target data, the target data can be used as the input of the trajectory prediction model, and the trajectory of the towing formation at the next moment is determined by the output of the trajectory prediction model. The trajectory prediction model is based on the gated recurrent unit (GRU) network and performs trajectory prediction through a distributed collaborative optimization algorithm. The present invention embeds physical factors such as interactions between ships and environmental impacts into the training process of the GRU network by introducing physical constraints based on the dynamic model. This method can effectively improve the model's predictive ability for complex dynamic systems and reduce the impact of data missing or noise on the results. The loss function of the trajectory prediction model can be expressed as: ,in , is the weight factor, represents the state prediction error based on the dynamic equation, Represents the mean square error between the model output and the actual trajectory. In the motion prediction of formation ships, the present invention further adopts a distributed collaborative optimization algorithm to optimize the motion state of the entire formation. Each ship performs local motion state prediction through an edge computing node, and synchronously updates the global motion state through a distributed optimization algorithm (such as the distributed alternating direction method of multipliers (ADMM)) based on the prediction results. This algorithm can ensure the coordination of the motion trajectories between ships, thereby improving the overall motion accuracy and consistency of the formation. Local prediction: Each ship generates a short-term (such as 30 seconds) motion trajectory based on its own and formation status. Global optimization: Coordinate the prediction results within the formation through a distributed algorithm to ensure the overall path consistency. Final motion trajectory output: According to the results of global optimization, the final motion trajectory of the towing formation is output to provide accurate trajectory guidance for formation control and task execution.

[0034] S104: Perform risk prediction based on the trajectory of the towing formation at the next moment, and determine whether to control and adjust the position and posture of the towing formation based on the risk prediction result.

[0035] It should be noted that after determining the trajectory of the towing formation at the next moment, the multi-source monitoring data of the towing formation at the next moment can be obtained for risk prediction, and then the risk prediction results are used to determine whether to adjust the trajectory of the towing formation, so as to ensure the safety of the towing formation during the towing operation.

[0036] In summary, the control method of the river-sea towing formation of a large floating production platform provided in an embodiment of the present invention collects multi-source monitoring data of the towing formation at the current moment to perform coupled feature extraction and feature fusion to obtain target data for trajectory prediction at the next moment, and ensures the reliability of trajectory prediction by improving data accuracy. Then, the trajectory prediction of the towing formation is performed through a distributed collaborative optimization algorithm according to a trajectory prediction model based on a GRU-ADMM network, so as to provide accurate trajectory guidance for formation control and task execution. Finally, risk prediction is performed through multi-source data corresponding to the predicted trajectory, and it is determined whether to control and adjust the towing formation according to the risk prediction result to ensure the safety of the towing formation during the towing operation. The present invention performs trajectory prediction and risk prediction by integrating deep learning methods and distributed collaborative control theory, thereby ensuring the safe implementation of the towing task of the large floating production platform from rivers to coastal waters.

[0037] In some embodiments of the present invention, Figure 2 As shown in the figure, the specific process of risk prediction and control is as follows: 1. Prediction of towing fleet movement based on distributed algorithm The specific prediction scheme has been described above and will not be repeated here.

[0038] 2. Risk prediction is carried out based on the towing fleet risk prediction model based on multi-source data fusion.

[0039] In some embodiments of the present invention, the risk prediction based on the trajectory of the towing formation at the next moment includes: The coupled feature extraction is performed on the multi-source monitoring data of the towing formation at the next moment, and the towing behavior characteristics, environmental impact characteristics, ship motion state characteristics and traffic flow impact characteristics corresponding to the towing formation at the next moment are obtained; Preprocess the towing behavior characteristics, environmental impact characteristics, ship motion state characteristics and traffic flow impact characteristics corresponding to the towing formation at the next moment to obtain the risk feature matrix corresponding to the towing formation at the next moment; The risk feature matrix corresponding to the towing formation at the next moment is used as the input of the risk prediction model, and risk prediction is performed based on the risk value output by the risk prediction model. The risk prediction model is trained based on the historical risk feature matrix and historical risk value.

[0040] Specifically, the towing fleet risk prediction model based on multi-source data fusion mainly predicts the risks of grounding, collision and cable breakage of the towing fleet by integrating AIS data, meteorological and hydrological data and ship status data. The specific steps of the prediction include: (1) Data collection and preprocessing.

[0041] Data collection: Collect multi-source data to be tested, including AIS data (speed, heading, position, etc.), meteorological and hydrological data (wind speed, current speed, tide, etc.), and ship status data (draft, tow cable tension, roll / pitch, etc.).

[0042] Data preprocessing: Preprocess the multi-source data, including data denoising: Use filtering algorithms (such as mean filtering, median filtering, wavelet denoising) or statistical methods to remove random noise in the data and improve data quality. Outlier detection: Use the interquartile range method and Z-score (standard deviation method) to ensure the reliability of the data. Standardization: Normalize data of different dimensions (maximum and minimum normalization or Z-score normalization) to ensure the scale consistency between features and improve the stability of the model. Interpolation and completion: For missing data, use linear interpolation, spline interpolation or long short-term memory network (Long Short-Term Memory, LSTM) prediction based on time series features to complete missing values ​​to ensure the continuity and integrity of the data. Fusion: Time align and feature match data from different sources (such as AIS data, meteorological data, tidal data, traffic flow data, etc.), and fuse them into a unified data format for subsequent analysis and model training.

[0043] (2) Calculate the risk value based on the obtained data set.

[0044] In some embodiments of the present invention, the risk value is calculated based on the following formula:

[0045] in, represents the risk value, , , , is the weight factor, represents the minimum distance risk index, represents the shortest collision time risk index, Indicates the sailing angle of the towing formation relative to other ships. Indicates the towline tension.

[0046] (3) Obtain input features and label values.

[0047] Based on the obtained risk value, the risk of the towing fleet is predicted through the LSTM network to obtain input features and label values. The method of obtaining input features includes feature extraction, normalization processing and data enhancement to ensure the stability and effectiveness of the input data.

[0048] Input features can be divided into the following categories: Towing behavior characteristics: Speed ​​(V): The sailing speed of the towing fleet, which affects the overall maneuverability and safety.

[0049] Towline tension (T): The fluctuation of towline tension reflects the stability of the towing process and is crucial to the coordinated movement of ships and safety risks.

[0050] Environmental impact characteristics: Flow velocity (C): Changes in flow velocity affect the stress and maneuverability of the towing fleet.

[0051] Tidal height (H): Tidal height determines the navigable water depth and affects the navigation risk of towing fleets, especially in shallow waters or narrow channels.

[0052] Ship motion characteristics: Relative speed ( ): The relative speed difference between the ships in the towing fleet determines the coordination and collision risk between the ships.

[0053] Relative position ( ): The azimuth of the towing vessel relative to the towed vessel or other ships, which affects the ship's collision avoidance strategy and risk level.

[0054] Traffic flow impact characteristics: Ship density ( ): The number of ships per unit area or unit length of the waterway, reflecting the impact of traffic flow on the towing fleet.

[0055] Crossing navigation angle ( ): The angle between the towing fleet and the navigation track of other ships, usually used to assess the risk of collision. The smaller the angle, the higher the risk of collision.

[0056] Finally, the input features can be expressed as the risk feature matrix .

[0057] (4) Construct a fleet risk prediction model based on XGBoost, use sliding window technology to continuously update training samples in time series data, and dynamically capture the evolution trend of towing fleet risk. Based on the trained XGBoost model, input the real-time towing fleet multimodal information, and calculate the potential risk of the towing fleet in the future time period in real time.

[0058] 3. Establish a risk prediction and risk management system for towing fleets.

[0059] The system consists of a login module, a data receiving module, an electronic chart module, a ship real-time data module, a risk detection module, an early warning and emergency module, a traffic control module, and a ship dispatch management module. Through the collaborative work of multiple modules, it monitors the navigation status in real time, predicts potential risks, and provides visual decision-making assistance.

[0060] In some embodiments of the present invention, determining whether to control and adjust the posture of the towing formation based on the risk prediction result includes: When the risk value output by the risk prediction model is greater than the risk threshold, it is determined to control and adjust the position and posture of the towing formation; When the risk value output by the risk prediction model is less than or equal to the risk threshold, it is determined that no control adjustment is performed on the posture of the towing formation; The controlling and adjusting the posture of the towing formation includes: adjusting the tugboat configuration, track and formation posture of the towing formation.

[0061] Specifically, when the risk value output by the risk prediction model is greater than the risk threshold, it indicates that there is a safety risk for the towing formation to follow the current trajectory, so it is necessary to control and adjust the posture of the towing formation. When the risk value output by the risk prediction model is less than or equal to the risk threshold, it indicates that the towing formation can travel safely according to the current trajectory and no control adjustment is required.

[0062] In some embodiments of the present invention, the adjusting of the tugboat configuration of the towing formation includes: Taking the towing mission cost as the objective function and the thrust balance, torque balance and equipment capacity limitation as the constraint functions, the number of tugboats, tugboat power and thrust direction of the towing formation are adjusted.

[0063] In some embodiments of the present invention, Figure 3 As shown in the figure, the tugboat configuration adjustment process of the towing formation is as follows: 1. Construction of real-time drag force calculation model.

[0064] The model involves the following key steps: Dynamic model of platform and tugboat: Based on the size, weight, draft of the platform and the power, traction and other parameters of the tugboat, a model of the interaction relationship between the platform and the tugboat is established.

[0065] Influence of environmental factors: By acquiring environmental data in real time, such as wind speed, wind direction, tidal velocity, etc., the model will dynamically adjust the drag calculation results to ensure that it can cope with changes in the natural environment.

[0066] Channel and voyage factors: The width, depth, curvature of the channel, etc. will affect the towing requirements. Especially in narrow waterways or bends, the calculation model will dynamically adjust the towing size according to the channel characteristics to avoid lateral deviation or grounding of the platform.

[0067] 1. Calculation of the whole process towing force and single ship power.

[0068] Total towing resistance The empirical calculation formula is:

[0069] In the formula is the friction resistance of the towed vessel, represents the residual resistance of the towed vessel, Indicates the air resistance of the towed vessel.

[0070] Approximate formula for calculating the resistance of the towed ship:

[0071]

[0072]

[0073] In the formula represents the underwater wetted area of ​​the towed vessel, It represents the median cross-sectional area of ​​the flooded part of the towed vessel. represents the towing speed (the resultant speed of the ship relative to the water), Indicates wind speed, represents the square coefficient, is the air density, 1.22 calculate, The shape factor that represents the windward area.

[0074] 2. Dynamic real-time adjustment and optimization.

[0075] The model dynamically calculates the towing demand through real-time wind and towing speed data feedback, and automatically adjusts the tugboat power, traction distribution and towline tension to ensure the stability and safety of towing operations.

[0076] In the towing mission of river-sea linkage, when the wind speed increases, the real-time calculation model can quickly evaluate the impact of wind force on the platform's resistance and increase the tugboat's power output accordingly. On the other hand, if the tidal flow speed increases, the model will adjust the tugboat configuration according to the direction of the water flow to ensure the stability of the platform's navigation direction.

[0077] 2. Towing mission cost calculation model based on multi-factor optimization.

[0078] Model influencing factors: In towing operations, there are many economic and technical factors involved, which directly affect the overall cost, efficiency and safety. The following are the main influencing factors and their analysis: Number of tugboats: The number of tugboats has a dual effect on towing costs: on the one hand, increasing the number of tugboats will directly increase rental costs; on the other hand, a reasonable increase in the number of tugboats can reduce the load of a single ship, thereby reducing fuel consumption and equipment wear and tear, and achieving long-term cost savings.

[0079] Single vessel power: Single vessel power also has positive and negative effects. High-powered tugboats are usually more expensive to rent, but they may save total costs by reducing the total number of tugboats required; however, high-powered equipment often comes with higher fuel consumption, so a balance needs to be found between performance and economy.

[0080] Operation time: The impact of operation time on cost is mainly reflected in two aspects: first, the rental cost is linearly positively correlated with time, and second, fuel consumption will increase with the accumulation of operation time. Therefore, reasonable planning of the operation cycle is the key to reducing total cost.

[0081] Economic factors: From the perspective of economic factors, the impact of fuel price fluctuations and equipment efficiency on towing costs cannot be ignored. Rising fuel prices will significantly increase operating costs, while equipment efficiency (such as tugboat energy efficiency ratio) directly affects energy consumption and cost control.

[0082] Technical constraints: From an economic perspective, the impact of fuel price fluctuations and equipment efficiency on towing costs cannot be ignored. Rising fuel prices will significantly increase operating costs, while equipment efficiency (such as tugboat energy efficiency ratio) directly affects energy consumption and cost control.

[0083] In tugboat configuration optimization, the total cost is usually composed of multiple parts, including tugboat rental fees, fuel consumption costs, operating time-related costs, etc. Therefore, it is necessary to obtain tugboat information such as tugboat type, number of tugboats to be selected, power, fuel consumption, and rental.

[0084] (1) Tugboat rental costs.

[0085] The cost of leasing a tugboat is directly related to the number of tugboats and the duration of the operation. The formula is as follows:

[0086] In the formula, represents the daily rental of the i-th type tugboat, Indicates the duration of the job (days), Indicates the number of tugboats.

[0087] (2) Fuel consumption cost.

[0088] The fuel consumption cost is related to the tugboat power, operation time and tugboat efficiency. The formula is as follows:

[0089] In the formula, Indicates the fuel consumption coefficient per kilowatt of power, represents the power of the i-th category tugboat, represents the fuel price, Indicates the duration of the job.

[0090] (3)Additional expenses.

[0091] The additional cost takes into account the impact of factors such as sea condition changes, increased resistance, and thrust redundancy on the total cost. Assuming that the resistance increases by 10%, the fuel cost will increase by 8-12%. In complex sea conditions, the thrust redundancy will increase by 15-20%. The additional cost calculation formula is as follows:

[0092] In the formula, Indicates the resistance increase ratio, Indicates the increase in the redundant thrust demand due to complex sea conditions.

[0093] (4) Operation time cost.

[0094] The operation time will directly affect the rental cost and fuel consumption. The formula is as follows:

[0095] In the formula, Indicates fuel consumption rate.

[0096] Combining the above parts, we get the total cost calculation formula:

[0097] The initial total cost is calculated according to the above method. The subsequent tugboat configuration optimization model will select the best tugboat combination and adjust it according to the real-time situation. The total cost will also be updated according to the real-time towing force, power and fuel consumption.

[0098] 3. Tugboat configuration optimization model considering towing formation track control constraints.

[0099] The core constraints of the model are divided into three parts: thrust balance equation, torque balance equation and equipment capacity limitation, which aim to ensure the stability and safety of the towing formation.

[0100] (1) Thrust balance equation.

[0101] The thrust balance equation is one of the key constraints. Its function is to ensure that the total thrust provided by the tugboat can overcome the sailing resistance of the fleet and maintain a certain safety redundant thrust to cope with complex environments (such as wind, current, etc.), so as to ensure that the fleet moves forward smoothly at the target speed. The conditions that the thrust balance equation needs to meet are:

[0102]

[0103] In the formula, Indicates the sailing resistance, represents the safety redundant thrust, represents the thrust direction angle of the tugboat, Indicates the current ship thrust.

[0104] (2) Torque balance equation.

[0105] The moment balance equation ensures balanced thrust distribution of the tugboat by controlling the layout coordinates and thrust direction angle of the tugboat, so that the towed platform maintains a stable heading and attitude. The conditions that the moment balance equation needs to satisfy are:

[0106] In the formula, , Indicates the tugboat layout coordinates.

[0107] (3) Equipment capability limitations Equipment capacity limitation is a constraint on the power of the tugboat to prevent one or more tugboats from overloading, ensure equipment safety and avoid operational risks caused by overloading. The conditions that must be met for equipment capacity limitation are:

[0108] In the formula, Indicates the current maximum thrust of the ship.

[0109] In some embodiments of the present invention, the adjusting of the number of tugboats, the power of tugboats and the thrust direction of tugboats in the towing formation includes: Taking the number of tugboats, tugboat power and tugboat thrust direction in the towing formation as variables, the global optimal combination is generated based on genetic algorithm. The global optimal combination is locally optimized based on a deep reinforcement learning network, and the locally optimized global optimal combination is optimized based on a genetic algorithm until a variable combination with a minimum objective function value is determined, and the tugboat configuration of the towing formation is adjusted based on the corresponding variable combination with the minimum objective function value.

[0110] Specifically, the specific steps for adjusting the number of tugboats, tugboat power and tugboat thrust direction of the towing formation include: 1. First, obtain the relevant parameters of the towing task, including the following parts: Track control constraints: current position, target heading angle, maximum allowable yaw angle, maximum allowable track offset, channel curve radius, and current tugboat thrust direction.

[0111] Genetic Algorithm (GA) parameters: mutation rate, population size.

[0112] Deep Reinforcement Learning (DRL) parameters: learning rate, discount factor.

[0113] 2. Population initialization: The number, power and thrust direction angle of each type of tugboat are used as variables to generate the initial population:

[0114] In the formula, represents the number of tugboats of the i-th category, represents the power of the i-th category tugboat, It represents the thrust direction angle of the i-th type tugboat.

[0115] 3. Fitness function calculation: Evaluate the total cost, thrust error and track stability of each candidate solution, taking into account both economy and safety. The calculation formula is as follows:

[0116] In the formula, represents the total cost, Indicates the thrust error (the difference between the actual thrust and the required thrust), Represents track stability (torque balance error).

[0117] 4. Selection and optimization: Screen out the appropriate combination of tugboat quantity, power and thrust direction through selection, crossover and mutation.

[0118] 5. Configure the reinforcement learning (DRL) environment: In DRL training, the agent needs to interact in the environment and learn the optimal strategy. Therefore, the reinforcement learning environment needs to be defined first. The reinforcement learning environment is configured according to the optimal combination selected by the genetic algorithm, which mainly includes: (1) State space: The state of the environment observed by the agent at each time t, including the current position, target heading angle, yaw angle, wind speed, water flow speed, and tugboat thrust direction.

[0119] (2) Action space: The agent adjusts the thrust direction and power of the tugboat.

[0120] (3) Reward function: DRL guides the agent to learn the optimal tugboat configuration strategy through the reward function. The formula is as follows:

[0121] In the formula, represents fuel cost incentive, represents the track stability reward, Indicates thrust balance reward.

[0122] 6. Model training: Model training uses a deep reinforcement learning network to learn the relationship between the state and the optimal action.

[0123] 7. Gradient descent optimization: Through the gradient descent optimization process, a near-optimal tugboat configuration solution can be quickly found.

[0124] 8. Feedback mechanism optimization: After the DRL optimization is completed, the optimization results are fed back to the GA, the fitness function is updated, and the above steps are repeated.

[0125] 9. Execution optimization strategy: After sufficient training, the intelligent agent learns an optimal strategy and can select the optimal tugboat thrust distribution plan according to different environmental conditions. In the actual towing mission, it can adjust the tugboat thrust direction at any time and optimize the towing power distribution to adapt to changes in environmental factors such as wind speed and ocean currents.

[0126] In some embodiments of the present invention, Figure 4 As shown, the towing formation and operation process specifically include the adjustment of route, formation and attitude.

[0127] In some embodiments of the present invention, adjusting the track of the towing formation includes: Taking the total path cost as the objective function and the channel width, speed, maneuverability, channel depth and ship encounter distance as the constraint functions, the track of the towing formation is adjusted based on the A* algorithm.

[0128] Specifically, the adjustment of the towing formation's track includes: 1. According to the inland navigation rules, seaport navigation rules and navigation environment data, the inland waterway network and the seaport route network are constructed respectively, the maritime navigation environment is modeled, and the A* algorithm is used to generate the maritime route network in combination with the wind, wave and current information.

[0129] 2. Based on complex network theory, the inland waterway network, seaport route network and maritime route network are integrated to construct a full-segment river-sea towing route network.

[0130] 3. Use the improved A* algorithm to plan the global optimal navigation path in the river-sea towing route network. The improved A* algorithm includes the objective function and constraint condition settings, and the specific steps are as follows: Objective function settings:

[0131] In the formula is the total path cost; is the length of the i-th channel; is the actual speed of the ith section of the channel; is the waiting time for the i-th channel; is the penalty term for the high-risk area (e.g., rapids) in the jth segment; is the risk weight factor.

[0132] Constraint settings: Channel width constraints:

[0133] The available width of the channel must be greater than the total width of the formation (including the safety margin Δ on both sides). The navigation area can be adjusted according to special rules. For example, large ships with low speeds in the navigation lane should sail along the right edge of the navigation lane as much as possible. Under the condition of ensuring safety, they can enter the recommended route for navigation.

[0134] Speed ​​constraints (the Jiangsu section of the Yangtze River is taken as an example here, and different sections may have different constraints): Maximum speed limit within traffic lanes:

[0135] Minimum speed limit within traffic lanes:

[0136] This restriction does not apply when sailing in other waters.

[0137] Manipulative constraints:

[0138] Turning Radius 3 times the total length of the formation (to ensure that the towline is not subject to excessive lateral tension).

[0139] Channel depth constraints:

[0140] The dynamic water depth must satisfy the draft + safety margin (δ=0.5m).

[0141] Rule compliance constraints:

[0142] Taking inland river navigation as an example, the minimum encounter distance of all encountering ships meets the standard =0.3 nautical miles. During coastal navigation, the minimum encounter distance can be adjusted appropriately according to actual conditions.

[0143] In some embodiments of the present invention, the adjusting the formation posture of the towing formation includes: The formation shape model corresponding to the towing formation is constructed based on the chain leader-follower model; Based on the DDPG algorithm and the formation shape model corresponding to the towing formation, the propulsion force and steering torque of each ship in the towing formation are adjusted.

[0144] Specifically, the formation posture adjustment process is as follows: 1. Construct a tugboat dynamics model and a towing formation shape model, and initialize the formation shape matrix based on the chain leader-follower model , where the formation shape model initialization process is as follows;

[0145] in,( , ) is the location, For speed, is the heading angle, is the angular velocity, and is the propulsion force and steering torque, For quality, is the moment of inertia, and is the damping coefficient.

[0146] Adopting a chain leader-follower structure, defining a formation matrix :

[0147] in, , is the scaling factor, , is the expected relative distance between the follower and the direct leader, For Node direct leader.

[0148] 2. Based on the planned navigation path and ship maneuvering rules, the state space and action space of the towing fleet are dynamically updated, and a formation maintenance reward mechanism is set up. The DDPG-LF method is used to realize the intelligent formation of the river-sea towing fleet. The specific steps of the river-sea towing collaborative formation method based on DDPG-LF are as follows: At each time step t, each tugboat has a Select Action , and receive rewards ; Store experience data in the classification replay pool, and update network parameters according to priority sampling; If obstacles or turbulence are detected, trigger local path replanning and adjust reward weights.

[0149] Define the towing formation state space:

[0150] Define the towing formation action space:

[0151] That is, the propulsion force change and the steering torque change must satisfy the physical constraints: .

[0152] Implementation of dynamic formation algorithm for towing formation based on DDPG:

[0153] Formation Keeping Rewards: , is the current relative distance, is the expected value; energy consumption optimization: ; Path tracking reward: , is the maximum allowable track deviation.

[0154] In some embodiments of the present invention, the controlling and adjusting the posture of the towing formation further includes: Adjust the speed of each ship based on the towing formation's real-time updated formation action space; The towline tension and towing force are calculated based on the thrust and steering torque of each ship in the state space updated in real time by the towing formation, and the towline length of each ship is adjusted.

[0155] Specifically, a multi-agent system is used to design the tugboat formation. Each tugboat acts as an independent agent and communicates with adjacent tugboats to maintain the target formation. The relative positions of the tugboats are adjusted by a consensus-based control law, as follows:

[0156]

[0157] In the formula, , is the control gain, , and , are the positions of tugboats i and j, , and , are the speeds of tugboats i and j.

[0158] Tension control is used to adjust the cable length. The optimal cable length is determined based on the tugboat performance and environmental conditions: if the tension exceeds the limit, the cable length is shortened, and if the tension is insufficient, the cable length is extended. The tension formula is:

[0159] In the formula, is the pulling force exerted by tugboat i, It is the length of the cable between the tugboat and the floating platform.

[0160] In order to better implement the control method of the river-sea towing formation of a large floating production platform in the embodiment of the present invention, based on the control method of the river-sea towing formation of a large floating production platform, correspondingly, Figure 5 As shown, the embodiment of the present invention further provides a control device for a large-scale floating production platform river-sea towing formation, and the control device 500 for a large-scale floating production platform river-sea towing formation includes: The acquisition module 501 is used to collect multi-source monitoring data of the towing formation in real time, wherein the multi-source monitoring data includes motion state parameters and navigation environment parameters of the main tugboat and the large floating production platform; Processing module 502, for performing coupled feature extraction and feature fusion on the multi-source monitoring data of the towing formation at the current moment to obtain target data; Prediction module 503, used to use target data as input of trajectory prediction model, and determine the output of trajectory prediction model as the trajectory of towing formation at the next moment. Trajectory prediction model predicts the trajectory of single ship based on GRU-ADMM network, and predicts the trajectory of towing formation through distributed collaborative optimization algorithm. The trajectory prediction of single ship includes trajectory prediction of main tugboat and large floating production platform. The control module 504 is used to perform risk prediction based on the trajectory of the towing formation at the next moment, and determine whether to control and adjust the position and posture of the towing formation based on the risk prediction result.

[0161] The control device 500 for the river-sea towing fleet of a large floating production platform provided in the above embodiment can implement the technical solution described in the control method embodiment of the river-sea towing fleet of a large floating production platform. The specific implementation principles of the above modules or units can refer to the corresponding contents in the control method embodiment of the river-sea towing fleet of a large floating production platform, which will not be repeated here.

[0162] like Figure 6 As shown, the present invention also provides a control terminal 600. The control terminal 600 includes a processor 601, a memory 602 and a display 603. Figure 6 Only some components of the control terminal 600 are shown, but it should be understood that it is not required to implement all of the shown components, and more or fewer components may be implemented instead.

[0163] In some embodiments, the processor 601 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 602, such as the magnetic resonance image optimization method of the present invention.

[0164] In some embodiments, the processor 601 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 601 may be local or remote. In some embodiments, the processor 601 may be implemented in a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

[0165] In some embodiments, the memory 602 may be an internal storage unit of the control terminal 600, such as a hard disk or memory of the control terminal 600. In other embodiments, the memory 602 may also be an external storage device of the control terminal 600, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the control terminal 600.

[0166] Furthermore, the memory 602 may include both an internal storage unit of the control terminal 600 and an external storage device. The memory 602 is used to store application software installed in the control terminal 600 and various data.

[0167] In some embodiments, the display 603 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an organic light-emitting diode (OLED) touch device, etc. The display 603 is used to display information on the control terminal 600 and to display a visual user interface. The components 601-603 of the control terminal 600 communicate with each other via a system bus.

[0168] In one embodiment, when the processor 601 executes the control program of the large floating production platform river-sea towing formation in the memory 602, the following steps may be implemented: Real-time collection of multi-source monitoring data of the towing formation, wherein the multi-source monitoring data includes motion state parameters and navigation environment parameters of the main tugboat and the large floating production platform; The target data is obtained by performing coupled feature extraction and feature fusion on the multi-source monitoring data of the towing formation at the current moment; The target data is used as the input of the trajectory prediction model, and the output of the trajectory prediction model is determined as the trajectory of the towing formation at the next moment. The trajectory prediction model predicts the trajectory of a single ship based on the GRU-ADMM network, and predicts the trajectory of the towing formation through a distributed collaborative optimization algorithm. The trajectory prediction of a single ship includes the trajectory prediction of the main tugboat and the large floating production platform. A risk prediction is performed based on the trajectory of the towing formation at the next moment, and a determination is made based on the risk prediction result whether to control and adjust the position and posture of the towing formation.

[0169] It should be understood that: when the processor 601 executes the control program of the large floating production platform river-sea towing formation in the memory 602, in addition to the above functions, other functions can also be realized. For details, please refer to the description of the corresponding method embodiment above.

[0170] Furthermore, the embodiment of the present invention does not specifically limit the type of the control terminal 600 mentioned. The control terminal 600 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the control terminal 600 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0171] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, the steps or functions in the control method of the river-sea towing formation of a large floating production platform provided in the above-mentioned method embodiments can be implemented.

[0172] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0173] The control method and device for the river-sea towing formation of a large floating production platform provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A control method for a large floating production platform river-sea towing fleet, characterized in that: include: Real-time collection of multi-source monitoring data of the towing formation, wherein the multi-source monitoring data includes motion state parameters and navigation environment parameters of the main tugboat and the large floating production platform; The target data is obtained by performing coupled feature extraction and feature fusion on the multi-source monitoring data of the towing formation at the current moment; The target data is used as the input of the trajectory prediction model, and the output of the trajectory prediction model is determined as the trajectory of the towing formation at the next moment. The trajectory prediction model predicts the trajectory of a single ship based on the GRU-ADMM network, and predicts the trajectory of the towing formation through a distributed collaborative optimization algorithm. The trajectory prediction of a single ship includes the trajectory prediction of the main tugboat and the large floating production platform. A risk prediction is performed based on the trajectory of the towing formation at the next moment, and a determination is made based on the risk prediction result whether to control and adjust the position and posture of the towing formation.

2. The control method of the river-sea towing formation of a large floating production platform according to claim 1 is characterized in that: The risk prediction based on the trajectory of the towing formation at the next moment includes: The coupled feature extraction is performed on the multi-source monitoring data of the towing formation at the next moment, and the towing behavior characteristics, environmental impact characteristics, ship motion state characteristics and traffic flow impact characteristics corresponding to the towing formation at the next moment are obtained; Preprocess the towing behavior characteristics, environmental impact characteristics, ship motion state characteristics and traffic flow impact characteristics corresponding to the towing formation at the next moment to obtain the risk feature matrix corresponding to the towing formation at the next moment; The risk feature matrix corresponding to the towing formation at the next moment is used as the input of the risk prediction model, and risk prediction is performed based on the risk value output by the risk prediction model. The risk prediction model is trained based on the historical risk feature matrix and historical risk value.

3. The control method of the river-sea towing formation of a large floating production platform according to claim 2 is characterized in that: The risk value is calculated based on the following formula: in, represents the risk value, , , , is the weight factor, represents the minimum distance risk index, represents the shortest collision time risk index, Indicates the sailing angle of the towing formation relative to other ships. Indicates the towline tension.

4. The control method of the river-sea towing formation of a large floating production platform according to claim 2 is characterized in that: The determining whether to control and adjust the position and posture of the towing formation based on the risk prediction result includes: When the risk value output by the risk prediction model is greater than the risk threshold, it is determined to control and adjust the position and posture of the towing formation; When the risk value output by the risk prediction model is less than or equal to the risk threshold, it is determined that no control adjustment is performed on the posture of the towing formation; The controlling and adjusting the posture of the towing formation includes: adjusting the tugboat configuration, track and formation posture of the towing formation.

5. The control method of the river-sea towing formation of a large floating production platform according to claim 4 is characterized in that: The adjustment of the tugboat configuration of the towing formation includes: Taking the towing mission cost as the objective function and the thrust balance, torque balance and equipment capacity limitation as the constraint functions, the number of tugboats, tugboat power and thrust direction of the towing formation are adjusted.

6. The control method of the river-sea towing formation of a large floating production platform according to claim 5 is characterized in that: The adjustment of the number of tugboats, tugboat power and tugboat thrust direction of the towing formation includes: Taking the number of tugboats, tugboat power and tugboat thrust direction in the towing formation as variables, the global optimal combination is generated based on genetic algorithm. The global optimal combination is locally optimized based on a deep reinforcement learning network, and the locally optimized global optimal combination is optimized based on a genetic algorithm until a variable combination with a minimum objective function value is determined, and the tugboat configuration of the towing formation is adjusted based on the corresponding variable combination with the minimum objective function value.

7. The control method of the river-sea towing formation of a large floating production platform according to claim 4 is characterized in that: Adjust the towing formation's track, including: Taking the total path cost as the objective function and the channel width, speed, maneuverability, channel depth and ship encounter distance as the constraint functions, the track of the towing formation is adjusted based on the A* algorithm.

8. The control method of the river-sea towing formation of a large floating production platform according to claim 4 is characterized in that: The adjusting of the formation posture of the towing formation includes: The formation shape model corresponding to the towing formation is constructed based on the chain leader-follower model; Based on the DDPG algorithm and the formation shape model corresponding to the towing formation, the propulsion force and steering torque of each ship in the towing formation are adjusted.

9. The control method of the river-sea towing formation of a large floating production platform according to claim 4, characterized in that: The controlling and adjusting the posture of the towing formation also includes: Adjust the speed of each ship based on the towing formation's real-time updated formation action space; The towline tension and towing force are calculated based on the thrust and steering torque of each ship in the state space updated in real time by the towing formation, and the towline length of each ship is adjusted.

10. A control device for a large floating production platform river-sea towing fleet, characterized in that: include: A collection module, used to collect multi-source monitoring data of the towing formation in real time, wherein the multi-source monitoring data includes motion state parameters and navigation environment parameters of the main tugboat and the large floating production platform; A processing module is used to extract and fuse coupled features of the multi-source monitoring data of the towing formation at the current moment to obtain target data; The prediction module is used to use the target data as the input of the trajectory prediction model and determine the output of the trajectory prediction model as the trajectory of the towing formation at the next moment. The trajectory prediction model predicts the trajectory of a single ship based on the GRU-ADMM network and predicts the trajectory of the towing formation through a distributed collaborative optimization algorithm. The trajectory prediction of a single ship includes the trajectory prediction of the main tugboat and the large floating production platform. The control module is used to make risk prediction based on the trajectory of the towing formation at the next moment, and determine whether to make control adjustments to the position and posture of the towing formation based on the risk prediction result.

Images