Balance adjustment method for LNG (Liquefied Natural Gas) ship formation integrating virtual connection and distribution prediction

Abstract

The invention belongs to the field of shipping, and particularly relates to an LNG ship formation balance adjustment method fusing virtual connection and distribution prediction. The method comprises the following steps: firstly, representing a multi-body system of the LNG ship formation; the multi-body system sets a virtual connection relationship representing mutual influence between ships. Collecting ship navigation states, utilizing a multi-body system to generate corresponding risk state vectors, and combining with the virtual connection relation to generate risk prediction vectors; inputting the risk prediction vector of each ship into a pre-trained risk prediction model based on time series data, predicting local risks of the ships, and fusing the local risks into global risks of the formation; querying a preset regulation and control strategy experience set according to the global state and the risk level, and obtaining an optimal regulation and control strategy; and when the yaw angle or the pitch angle of any ship exceeds a safety threshold value, a balance regulation and control instruction is given to the ship. The problem that in the prior art, a ship formation level balance regulation and control strategy is lacked is solved, and the navigation stability of the LNG ship formation is guaranteed.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of shipping, and particularly relates to a balance adjustment method for LNG ship formation by fusing virtual connection and distributed prediction, and a corresponding computer program product and ship formation balance control device. BACKGROUND

[0002] In the field of ship engineering technology, the stability and safety of ship navigation have always been the focus of research. With the development of trade demand, LNG ship formation navigation is increasing, and ensuring the stability and safety of LNG ship formation navigation can optimize shipping resource allocation, reduce transportation risk and improve shipping efficiency.

[0003] In traditional ship balance control research, most control methods mainly focus on the balance adjustment of a single ship itself, focusing on the structural design of the ship itself and the limited balance device regulation and control, but ignoring the importance of ship formation collaborative operation. When focusing on LNG ship formation, the limitations of the above traditional balance control methods are more prominent. During the navigation of LNG ships, the liquid in the tank has a large and random sloshing amplitude, which has a non-negligible impact on the balance state of the ship. However, the existing methods almost do not comprehensively and systematically integrate multi-ship collaborative control into the balance control system. At the same time, in LNG ship formation navigation, the active balance weight system as a key auxiliary facility, its optimization degree is directly related to the ability of the ship to cope with liquid sloshing.

[0004] However, current research on LNG ship active balance weight system pays little attention to the collaborative optimization of energy consumption and balance effect, including the comprehensive consideration of weight block movement strategy, overall balance state of the ship and energy consumption, and the comprehensive influence of these factors on dynamic balance control of the ship. This leads to the difficulty of efficiently coping with the unbalanced force caused by LNG liquid sloshing during ship navigation, greatly increasing the risk of navigation; the ship design and manufacturing department lacks scientific and effective balance control scheme support when designing LNG ships, making it difficult to reasonably allocate balance devices; and the shipping company also lacks precise balance control method when operating LNG ships, which cannot guarantee the safety and stability of navigation. SUMMARY

[0005] In order to solve the problem that the prior art lacks a balance regulation scheme for ship formation level, the present application provides a balance regulation method for LNG ship formation by fusing virtual connection and distributed prediction, and a corresponding computer program product and ship formation balance control device.

[0006] The present application adopts the following technical solutions: A balance regulation method for LNG ship formation by fusing virtual connection and distributed prediction, comprising: A multibody system characterizing an LNG ship convoy is constructed based on rigid body dynamics theory. The multibody system determines whether there is a virtual connection relationship between any two ships by combining the distance between them, and generates the corresponding interaction forces and moments.

[0007] The system acquires the real-time navigation status of each vessel and uses a multibody system to generate a corresponding risk state vector based on the navigation status.

[0008] Collect data from each ship i angular velocity of sway Liquid level height h i and acceleration along the plane ( a xi , a yi ), and compare it with its own risk state vector X risk,i And other ships with virtual connections. j Risk state vector X risk,j Together as a risk prediction vector for current ships D i .in, i =1… n , n This indicates the number of ships in the formation.

[0009] The risk prediction vector for each vessel is input into a trained time-series-based risk prediction model, WXS, to generate the corresponding risk prediction result for each vessel. And utilize the fusion weights determined based on the entropy weight method. w i according to Generate global risk for the entire ship formation .

[0010] when If the preset safety threshold is exceeded, a risk is identified; at this point, the overall formation status is determined. s and risk level R c Query a preset set of experience for control strategies to obtain an optimal control strategy. B* , B* ={ b i}, i =1… n ; and when the yaw and / or pitch angle of any vessel exceeds the safety threshold, according to B* Issue balance control instructions to each vessel; Among them, the global state of the formation sThe virtual connection between the ships in the fleet is established by high-precision communication and positioning technology. x , y The virtual connection between the ships in the fleet is established by high-precision communication and positioning technology. v and a risk prediction vector of each ship D i The risk level R c The global risk predicted according to the WXS model The evaluation is generated. b i The control action of the i-th ship is represented as i ; Δ v i and respectively represent the velocity and displacement vectors of the counterweight in the ship.

[0011] The present application includes a computer program product comprising a computer program. When the computer program is executed by a processor, the balancing adjustment method of the LNG ship fleet integrating virtual connection and distributed prediction is realized as described above; and the imbalance risk of the fleet as a whole is predicted according to the real-time state of each ship in the fleet, and adaptive control actions are generated to maintain the balance of the ships.

[0012] The present application includes a ship fleet balancing control device comprising a memory, a processor, and a computer program stored on the memory and running on the processor. When the processor executes the computer program, the balancing adjustment method of the LNG ship fleet integrating virtual connection and distributed prediction is realized as described above; and the imbalance risk of the fleet as a whole is predicted according to the real-time state of each ship in the fleet, and adaptive control actions are generated to maintain the balance of the ships.

[0013] The technical solution provided by the present application has the following beneficial effects: The present application addresses the balance and control problems of each ship in the LNG ship fleet caused by liquid sloshing in the storage tank and the influence of adjacent ships during navigation. By establishing virtual connection between ships through high-precision communication and positioning technology, the fleet is analyzed as a whole, and multi-ship cooperative control is realized. In the imbalance prediction, the present application deploys a distributed balance prediction algorithm, uses sensor data of each ship and shared information of the fleet to establish a local prediction model, and fuses to generate a global prediction to predict the imbalance risk in advance. In generating the control strategy, the present application innovatively uses the DQN reinforcement learning algorithm to optimize the active balance counterweight system of the ship, takes the balance degree and energy consumption as the objective function to obtain the optimal counterweight movement strategy, and combines the pre-trained control strategy experience set to realize fast response. Through the cooperation of the above three, the present application can automatically coordinate the actions of the propulsion system, balancing device and counterweight when the ship is out of balance, efficiently restore the balance of the fleet, significantly improve the navigation safety and stability of the LNG ship fleet, and provide an innovative solution for dynamic balance control.​ Attached Figure Description

[0014] Figure 1 This is a flowchart of the steps in the LNG ship formation balance adjustment method that integrates virtual connectivity and distribution prediction provided in Embodiment 1 of the present invention.

[0015] Figure 2 This is a flowchart illustrating the prediction of ship formation imbalance risk using the WXS model in Embodiment 1 of the present invention.

[0016] Figure 3 This is a flowchart of the imbalance control strategy for generating different states using a reinforcement learning algorithm in Embodiment 1 of the present invention.

[0017] Figure 4 To test the time-series curves of the additional force of LNG liquid sloshing in the X direction under wind and wave loads for different schemes in the experiment.

[0018] Figure 5 To test the time-series curves of the additional force of LNG liquid sloshing in the Y direction under wind and wave loads for different schemes in the experiment.

[0019] Figure 6 To test the time-series curves of the additional torque of LNG liquid sloshing in the X direction under wind and wave loads for different schemes in the experiment.

[0020] Figure 7 To test the time-series curves of the additional torque of LNG liquid sloshing in the Y direction under wind and wave loads for different schemes in the experiment.

[0021] Figure 8 To test the time-series variation curves of the additional force and additional torque of liquid sloshing under different schemes in the experiment.

[0022] Figure 9 To test the time-series comparison curves of local and global risks of ship formations under different schemes in the experiment.

[0023] Figure 10 To test the time-series variation curves of the yaw and pitch angles of different ship formations in the experiment.

[0024] Figure 11 Radar chart to test the overall performance of different schemes in the experiment. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0026] Example 1 The skilled person of the present embodiment scheme finds that the conventional ship balance control technology focuses on single ship independent regulation and control, lacks consideration of overall coordination of LNG ship formation, and is difficult to cope with the chain reaction caused by the imbalance of a ship in the formation. In view of this problem, the scheme provided by the present embodiment combines the chain reaction between ships during navigation to construct a virtual connection relationship between the ships, and then performs dynamic analysis and coordinated control on all ships in the ship formation having the virtual connection relationship as a whole; this scheme can quickly coordinate the multi-ship propulsion system and the balancing device when the ship is unbalanced, greatly improving the balance recovery efficiency of the formation.

[0027] In terms of imbalance risk prediction, the prior art relies on simple sensor monitoring or experience judgment, lacking systematic and forward-looking prediction mechanism. The technical scheme provided by the present embodiment acquires data collected by sensors deployed in all ships, and fuses local prediction results of each ship to form a global risk through a risk prediction model WXS based on time series data. This strategy not only improves the prediction accuracy and misjudgment rate of the risk, but also predicts the imbalance risk 1-3 minutes in advance, so as to gain sufficient response time for control measures.

[0028] In terms of imbalance risk regulation, the present embodiment adopts an existing ship active balance counterweight system. Unlike the existing real-time optimization regulation strategy; in order to improve the comprehensiveness and real-time performance of the optimization target, the present embodiment adopts a brand-new strategy library matching strategy. In the generation process of each regulation strategy in the strategy library, the present embodiment adopts an optimization target considering balance effect and energy consumption, and uses a reinforcement learning algorithm to optimize the regulation strategy of the counterweight system under different working conditions. The related regulation strategy not only can effectively compensate the imbalance force generated by the LNG liquid sloshing of the ship, but also can reduce the energy consumption of the balance counterweight system by 20%-30%, with obvious economic benefits.

[0029] Specifically, as shown in Figure 1 The balance regulation method of the LNG ship formation provided by the present embodiment combining virtual connection and distributed prediction includes the following processes: I. Constructing a multi-body system of the ship formation In order to accurately analyze the influence of the interaction between each ship in the formation on the imbalance risk of the whole ship formation, the present embodiment first constructs a multi-body system representing the LNG ship formation based on rigid body dynamics theory. In the multi-body system constructed in the present embodiment, whether there is a virtual connection relationship between any two ships is determined in combination with the distance between the two ships, and the corresponding interaction force and interaction torque are generated for any two ships having a virtual connection relationship. i and j The multi-body system constructed in the present embodiment can clearly associate the interaction force between the ships with the motion parameters, providing an accurate dynamic basis for subsequent coordinated control.

[0030] In detail, in this embodiment, each ship is defined. i The generalized coordinate vector is ;in, i =1… n , n This indicates the number of ships in the formation. Among them, ( x i , y i Corresponding ships i Plane coordinates; x i and y i Let the x-coordinate and y-coordinate of ship i in the plane coordinate system be represented respectively. In practical applications, the ship's latitude and longitude can also be used to represent the corresponding plane coordinates. , , Ships i The yaw, pitch, and heading angles are all measured. These data, characterizing the ship's real-time status, can be obtained through real-time monitoring using the ship's navigation and positioning system and various sensors.

[0031] In order to establish a system that includes the mass of each ship m i and moments of inertia in three dimensions I xi , I yi , I zi In this embodiment, considering the additional inertial forces and torques generated by the sloshing of liquid within the storage tanks during the LNG vessel's navigation, innovative additional dynamic parameters are introduced to construct the dynamic model of each vessel in the multibody system corresponding to the ship formation. In this embodiment, to effectively assess the vessel's imbalance risk, the vessel's dynamic model consists of two parts: the ship's translational dynamics equations and rotational dynamics equations.

[0032] Specifically, in a multi-body system, any first... i The translational dynamics equations of a ship can be expressed as follows: ; In the above formula, j Indicates with ships i Other vessels with virtual connection relationships; m i Indicates a ship i quality; F ij For ships j For ships i The interaction force vector; Fli is the additional force vector due to LNG liquid sloshing; F wi is the environmental load force vector including wave drift force; r i is the position vector of the ship, i . .

[0033] In the present embodiment, the environmental load force vector F wi can be calculated by using the following Morison formula: ; In the above formula, denotes the seawater density, C D denotes the drag force coefficient, C M denotes the added mass coefficient, A denotes the ship's wetted surface area, V denotes the ship's displacement volume, v ri denotes the ship's velocity vector relative to the water flow; is the first derivative of v ri , i.e., the ship's acceleration vector relative to the water flow.

[0034] The rotational dynamics equation of any i th ship is: ; wherein, is the interaction torque vector of the ship j on the ship i ; is the additional torque vector due to LNG liquid sloshing; is the environmental load torque vector; I i is the inertia moment matrix of the ship i , I i = diag( I xi , I yi , I zi ); is the angular velocity vector of the ship i , .

[0035] In the rotational dynamics equation of the ship constructed in the present embodiment, the skilled person further adopts an innovative micro-element integration strategy to quantitatively analyze the additional force vector F li and the additional torque vector due to the LNG liquid sloshing carried in the ship, and the corresponding calculation formula is as follows: ; In the above formula, is the LNG liquid density, V l is the LNG liquid volume in the ship tank; v l is the liquid micro-element velocity vector, r cl is the position vector of the liquid micro-element relative to the ship center of mass; represents the derivative with respect to time.

[0036] wherein the liquid micro-element velocity vector v l can be obtained by solving the Navier-Stokes equation considering the free surface sloshing: In the above formula, p l is the liquid pressure; u l is the liquid dynamic viscosity, g is the gravity acceleration vector; represents the gradient calculation symbol.

[0037] In the translation dynamics equation and the rotation dynamics equation of the ship constructed in the embodiment, the interaction force vector F ij and the interaction torque vector between any two ships in the ship formation reflect the virtual connection relationship between any two ships in the ship formation; the virtual connection relationship needs to be determined comprehensively in combination with the relative position and attitude of any two ships in the formation, and in actual application, the interaction force vector F i and the interaction torque vector j between any two ships ij and can be calculated through the following virtual force field model: In the above formula, k ij and c ij are respectively the elastic coefficient and the damping coefficient of the virtual connection; k tij and c tij are respectively the torsional elastic coefficient and the torsional damping coefficient of the virtual connection; r i and r j are respectively the position vectors of the ships i and j ; and are respectively the position vectors of the ships i and​​​j The lateral angle; d ij This represents the actual distance between the two ships. d th This is the preset effective operating distance threshold.

[0038] Analysis of the above process shows that in the multibody system of this embodiment, when the distance between any two ships exceeds a threshold, the influence between them is considered small, and no virtual connection is needed; they belong to two independent single-unit systems. However, when the distance between two ships is lower than a preset distance threshold, their navigation and maneuvers will interact through the water. In this embodiment, a corresponding "virtual connection" is established between them, generating a corresponding interaction force vector F. ij and interaction torque vector This allows for a joint analysis of the states of both entities.

[0039] Furthermore, the dynamic model of the multibody system constructed in this embodiment not only considers traditional rigid body dynamics factors, but also innovatively introduces additional dynamic parameters of LNG liquid sloshing and a ship-to-ship interaction model based on virtual connection, thus enabling a more accurate description of the dynamic characteristics of a formation containing multiple LNG ships under complex operating conditions.

[0040] II. Prediction of Imbalance Risk Based on the constructed multi-body system of ship formations, such as Figure 2 As shown, this embodiment can acquire data for each ship in real time. i The navigation state is determined, and then a corresponding risk state vector is generated based on the navigation state using a multibody system. X risk,i Among them, any number of... i Risk state vector of a ship X risk,i The data format is: ; In practical applications, It can be obtained directly from the ship's translational and rotational dynamics equations; E li The formula for calculating the sway energy of a ship is as follows: Finally, this embodiment can extract the yaw rate from the dynamic model after processing by a fourth-order Butterworth low-pass filter. and pitch acceleration .

[0041] In this embodiment, to achieve more accurate analysis and prediction of ship status and imbalance risk, this embodiment... i State data (i.e.) Xrisk,i ) and the state of the formation, and i The state of all associated ships with virtual connection relationship are collectively taken as input data for evaluating the imbalance risk of the ship.

[0042] Specifically, the embodiment collects the swing angular velocity i , liquid level height of each ship h i and the in-plane acceleration a xi , a yi , and takes it together with the risk state vector X risk,i of the ship itself and the risk state vector X risk,j of other ships with virtual connection relationship as the risk prediction vector D i of the current ship ,

[0043] Next, the embodiment inputs the risk prediction vector of each ship into a trained risk prediction model WXS based on time series data to generate the corresponding risk prediction result of each ship.

[0044] In the scheme of the embodiment, the risk prediction model is the key to realizing the local analysis of the imbalance risk of each ship. The risk prediction model (WXS model) of the embodiment is a network model trained based on machine learning, which can establish the mapping relationship between “dynamic parameters-risk level” through massive historical data of ship operation. In actual application, the embodiment can adopt a cross-entropy comprehensive prediction model based on wavelet analysis, which predicts the current risk prediction result D i of the ship x ( t ) according to the input time series data i .

[0045] In actual application, the risk prediction model first performs wavelet decomposition on the input original collected data, and then performs inference analysis according to the decomposition result to obtain the prediction result. In the embodiment, the wavelet decomposition formula used by the risk prediction model is as follows: ; In the above formula, t denotes time; and are the scale function and the wavelet function, respectively; a ​j,k is the approximation coefficient of the model at the kth time j layer; d j,k is the approximation coefficient of the model at the kth time j layer at the kth time k , the detail coefficient of the model at the kth time, k represents the time axis index of the time series data.

[0046] In the further optimized scheme of the embodiment, the information ship transmission can be realized through the special communication module carried by each ship C i i = 1, 2, …, n) In order to ensure the accuracy of the data, the collected data is first processed by a fourth-order Butterworth low-pass filter, and the transfer function is: In the above formula, s represents the frequency domain characteristics of the data used; s k is the pole of the filter, which removes high-frequency noise interference and ensures the accuracy and stability of the data. Subsequently, a virtual connection relationship between ships is constructed based on the self-organizing network protocol to form a dynamic topology network, and the communication delay between nodes in the network meets the real-time requirement. On this basis, d j,k The following dynamic threshold function is used for processing to enhance the feature signal-to-noise ratio: In the above formula, represents the enhanced detail coefficient; represents the dynamic threshold parameter, is the standard deviation estimate of the detail coefficient, N is the data length of the time series data.

[0047] In the training stage of the risk prediction model constructed in the embodiment, the cross-entropy loss L CE is used as the loss function for model optimization: In the above formula, p c represents the true probability distribution of the ship imbalance risk; is the class probability distribution predicted by the model; C is the total number of risk categories.

[0048] The risk prediction model of the embodiment is composed of multiple base models, and in the training stage, the risk prediction model uses dynamically updated adaptive weights, and the weight update formula is: ​​​​​ ; In the above formula, T Indicates the number of iterations; and They are the first T and T The risk prediction model included in the +1 round of iterations m The weights of each base model. This represents the learning rate. In this embodiment, an adaptive learning rate related to the prediction error volatility is used in practical applications: ; In the above formula, Based on the learning rate, Var ( Error ) represents the variance of the prediction error.

[0049] In practical applications, each vessel can upload its own status data to a central management module on a command ship. The central management module then assesses the imbalance risk of each vessel based on data from different sources. The prediction task can also be performed by embedded modules deployed in each ship, which can then combine their own state data to predict their respective imbalance risks. The prediction results are then uploaded to the central management module, whereby the command ship performs a global analysis of the risk of imbalance in the ship formation.

[0050] Finally, this embodiment utilizes the fusion weights determined based on the entropy weight method. w i according to Generate global risk for the entire ship formation The calculation formula is as follows: ; III. Regulation of Imbalance Risk Imbalance risk of individual ships predicted by the WXS model and the overall risk of formation These respectively reflect the probability distributions of the local and global prediction results for ship imbalance risk. When If the preset safety threshold is exceeded, the ship formation is deemed to have an imbalance risk. Specifically, in practical applications, the safety threshold set in this embodiment is 0.4. A value greater than 0.4 indicates a risk, while when... If the value is ≤0.4, then there is no risk.

[0051] Based on this, and for ease of management and control, this embodiment can further refine the global risk predicted by the WXS model. Discretization is performed to determine the risk level of formation imbalance.R c In the typical solution provided in this embodiment, global risk... Risk level R c The mapping relationship is as follows: When 0.5≥ When >0.4, R c =R1 indicates low risk; When 0.6≥ When >0.5, R c =R2 indicates medium risk; when When >0.6, R c =R3 indicates high risk.

[0052] When the prediction results indicate that there is a risk, this embodiment first considers the global risk. The prediction results are converted into corresponding risk levels. R c Then, based on the global state of the formation s and risk level R c Query a preset set of experience for control strategies to obtain an optimal control strategy. B* , B* ={ b i}, i =1… n ; and when either the yaw angle or the pitch angle of any vessel exceeds the safety threshold, according to B* Balance control commands are issued to each vessel. In this embodiment, the safety thresholds for both the yaw and pitch angles of the vessels are set to 3°. During the control process, each vessel will also provide real-time attitude data to form a closed-loop control, ensuring that the LNG vessel formation is restored to a balanced state within 30 seconds, thus guaranteeing safe and stable navigation in complex sea conditions.

[0053] In the technical solution provided in this embodiment, the control strategy experience set is generated by a reinforcement learning algorithm based on the historical navigation data of the ship formation, representing the global state of any formation. s and risk level R c With regulation strategy B* A dataset containing mapping relationships. This mapping relationship is represented as: s + R c → B* .

[0054] Among them, the global state of the formation sIncluding formation position ( x , y Formation speed v and risk prediction vectors for each vessel D i The formation position can be determined by the position of the command ship within the formation, or by the approximate center of the positions of all ships in the formation. Risk Level R c Global risk predicted by the WXS model Evaluation and generation. Under the optimal control strategy. B* middle, b i Indicates the first i The control actions of individual ships, ;Δ v i and These represent the velocity and displacement vectors of the counterweight in the ship, respectively.

[0055] For ship active balancing counterweight systems, such as Figure 3 As shown, in this embodiment, when using the DQN reinforcement learning algorithm to optimize the ballast strategy and then construct the control strategy, the ship's pitch angle is used as the reference. Heading angle The sum of absolute values and energy consumption of counterweight movement E Minimization is used as the optimization objective function. In the reinforcement learning framework, the state space is defined to include the ship's position, attitude, and risk, and the action space is defined to include the three-dimensional movement parameters of the counterweight. A reward function is designed to balance the control effect and energy consumption. Through experience playback and deep neural network training, the optimal counterweight movement strategy is output to ensure that the heel and roll angles are controlled within ±3° and energy consumption is reduced by 20%-30%.

[0056] State space: In the reinforcement learning framework for constructing a set of experience for control strategies, the state space is the foundation for the DQN algorithm to perceive the environment and must comprehensively reflect the ship's current equilibrium state and risk characteristics. This embodiment includes each global state in a three-dimensional information state space. s The definition of is: ; in, , .

[0057] Motion space and adaptation mechanism: The action space defines the adjustment operations that the counterweight system can perform. In the solution provided in this embodiment, the granularity of the adjustment action will be based on the risk level of the output. R cThe dynamic adjustment is performed to realize the response logic of "the higher the risk, the more decisive the action", which is mathematically defined as , the moving unit of the counterweight is m, and the speed unit is m / s.

[0058] When R c =R1, it belongs to a low-risk scenario. At this time, the ship attitude fluctuates less, and the probability of imbalance in the future is reduced. The action space adopts a fine adjustment mode, and the purpose of this design is to maintain balance while minimizing energy consumption and avoiding unnecessary frequent adjustment. The action space used in this state is: .

[0059] When R c =R2, it belongs to a medium-risk scenario. At this time, the probability of imbalance is high, and a balance needs to be struck between response speed and energy consumption; the adjustment range of the action space is expanded. The action space used in this state is: .

[0060] When R c =R3, it belongs to a high-risk scenario. At this time, the ship has approached the imbalance threshold, and the model predicts that the probability of imbalance in the near future is high. The action space switches to the emergency adjustment mode, prioritizing rapid recovery of balance and appropriately relaxing the energy consumption limit. The action space used in this state is: .

[0061] In the above self-adaptive action space designed in this embodiment, the total dimension of the action space is 3 3 ×3=81 (covering all combinations of 3 risk levels), ensuring that the algorithm has sufficient adjustment freedom in different risk scenarios.

[0062] Reward function: The reward function guides policy optimization by quantifying the pros and cons of actions. The reward function of this design fully integrates parameters to achieve multi-objective collaborative optimization. Specifically, the reward function is: ; In the above formula, R balance and R energy represent the balance reward and energy consumption reward, respectively; α and β represent the weights of the balance reward and energy consumption reward, respectively; and respectively represent the ship's yaw angle and pitch angle after performing the control action; and respectively represent the penalty term determined according to the standard deviation of the yaw angle and the pitch angle; for example, in high sea conditions (large) , even if the inclination is small, the rapid attitude change will be given a negative reward to suppress violent shaking. E is the energy consumption increment generated by the control action, ; wherein, E and are the energy consumptions of the ship's active balance weight system before and after control. represents the risk adaptation coefficient determined according to the risk level. In this embodiment, for the three risk levels, , the values of are 0.8, 1.0 and 1.2 respectively, so as to appropriately relax the energy consumption limit in high-risk state.

[0063] The neural network used in the reinforcement learning framework of this embodiment is composed of an input layer, a risk feature layer, a fusion layer and an output layer. The number of neurons in the input layer corresponds to the dimension of the state vector s , and the original data is standardized and transmitted into the network. The risk feature layer contains 32 neurons, which are specifically used to process R c and extract risk features through a LeakyReLU activation function. The fusion layer contains 128 neurons and is used to fuse the attitude and risk features, and then extract the hidden association between parameters through a ReLU activation function. For example, in the state of "high risk + rapid rolling", a more aggressive weight strategy needs to be matched; the output layer contains 81 neurons, corresponding to the action space, and outputs the action value Q s , b ).

[0064] In addition, the network loss function of the embodiment introduces a weighting factor of the risk level to improve the training weight of high-risk samples: ; wherein, y t is the target Q value, is the risk weight, represents the Q value corresponding to the action in the current state; represents the model parameters of the neural network.

[0065] Experience replay and exploration strategy: Partitioned storage and sampling of experience pool: the experience pool is divided into D 1, D 2, D ​3 three sub-pools, respectively store the interaction data under the corresponding scene s t , b t , r t , s t+1 Instead of random sampling, the probability of risk occurrence in actual navigation is weighted (high-risk sample ratio ≥ 40%) to ensure that the algorithm has enough learning samples for dangerous scenarios and avoids strategy failure in high-risk scenarios due to a high proportion of low-risk samples.

[0066] To balance “using known optimal actions” and “exploring new actions”, The value is dynamically adjusted according to the risk level: under three risk levels, The values are 0.2, 0.4, and 0.6, respectively. When the risk is low, = 0.2 (mainly for utilization), and when the risk is high, = 0.6 (increasing exploration to cope with complex situations). This strategy avoids missing the optimal solution due to excessive reliance on old experience in emergency scenarios.

[0067] In this embodiment, according to the global state of the formation s and the risk level R c The process of querying the preset control strategy experience set to obtain an optimal control strategy is as follows: first, select several control strategy experience sets with the same risk level as the current predicted structure from the control strategy experience set, then match the s value of each control strategy with the s value of the current ship, and finally select the control strategy with the highest matching degree as the current optimal control strategy B* .

[0068] After obtaining the optimal control strategy B* , this embodiment executes the control strategy as follows: When the ship's yaw angle or pitch angle exceeds the limit and triggers an imbalance alarm, first generate a control instruction set B* according to the optimal control strategy ; among them, the propulsion system thrust adjustment instruction u propulsion The propeller speed n and steering angle are determined through fuzzy reasoning rules, and the specific relationship can be expressed as:

[0069] Through the time-sensitive network (TSN) between ships, the control instruction set U is sent to each ship with sub-millisecond delay. The propulsion system receivesu propulsion Afterwards, according to n Adjust the propeller speed according to Change direction; balance fins respond to fin commands. u fit In α fin Changing the angle of attack generates a normalizing torque; the counterweight operates according to the configuration instructions. u weight The planned path, with v * ( t The ship moves rapidly at high speed. During the control process, each vessel uses sensors to provide real-time attitude data to form a closed-loop control; the control error is calculated based on the error function; and the new round of control commands is adjusted based on the PID control algorithm. , and :

[0070] In the above formula, E 1. E 2 and E 3 represents the adjustment errors of the propulsion system, balance fins, and counterweights, respectively; K p1 , K p2 and K p3 These are the proportional coefficients for the propulsion system, the balancing fins, and the counterweights, respectively. K i1 , K i2 and K i3 These are the integral coefficients of the propulsion system, the balancing fins, and the counterweights, respectively. K d1 , K d2 and K d3 These are the differential coefficients of the propulsion system, the balancing fins, and the counterweight; each coefficient can be determined through offline simulation optimization. By continuously adjusting the control commands, the PID controller can ensure that the requirements are met within t≤30s. and This will restore the balance of the LNG vessel fleet and ensure its safe and stable navigation in complex sea conditions.

[0071] Furthermore, after each successful regulation in this embodiment, a new regulation strategy can be generated based on the regulation process and stored in the regulation strategy experience set.

[0072] Example 2 The balance adjustment method of LNG ship formation integrating virtual connection and distribution prediction provided in embodiment 1 is essentially a data processing method. In order to better apply the scheme, the embodiment further provides a computer program product, a storage medium and a ship formation balance control device.

[0073] The computer program product provided in the embodiment includes a computer program which, when executed by a processor, implements the balance adjustment method of LNG ship formation integrating virtual connection and distribution prediction as in embodiment 1; and further predicts the imbalance risk of the whole formation according to the real-time state of each ship in the formation, and generates adaptive control actions to maintain ship balance.

[0074] The storage medium provided in the embodiment stores a computer program. The computer program, when executed by a processor, implements the balance adjustment method of LNG ship formation integrating virtual connection and distribution prediction as in embodiment 1; and further predicts the imbalance risk of the whole formation according to the real-time state of each ship in the formation, and generates adaptive control actions to maintain ship balance.

[0075] The ship formation balance control device provided in the embodiment includes a memory, a processor and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the balance adjustment method of LNG ship formation integrating virtual connection and distribution prediction as in embodiment 1; and further predicts the imbalance risk of the whole formation according to the real-time state of each ship in the formation, and generates adaptive control actions to maintain ship balance.

[0076] The ship formation balance control device provided in the embodiment. Essentially, it is a computer device. In actual application, the computer device can be an embedded device, or an independent computer device such as a notebook computer, a tablet computer, a desktop computer, or a medium or large computer device capable of executing a computer program, such as a rack server, a blade server, a tower server or a cabinet server (including an independent server, or a server cluster composed of multiple servers). Further, the MRI output from the front end is optimized in the back end.

[0077] The computer device of the embodiment at least includes but is not limited to a memory and a processor which can be connected to each other in communication through a system bus. In the embodiment, the memory (i.e. a readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory can be an internal storage unit of the computer device, for example, a hard disk or a memory of the computer device. In other embodiments, the memory can also be an external storage device of the computer device, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device. Of course, the memory can include both the internal storage unit and the external storage device of the computer device. In the embodiment, the memory is usually used to store an operating system and various application software installed on the computer device, etc. In addition, the memory can also be used to temporarily store various data that have been output or will be output.

[0078] The processor in some embodiments can be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. The processor is usually used to control the overall operation of the computer device.

[0079] Performance test To verify the effectiveness of the LNG ship formation balance adjustment method provided by the fusion virtual connection and distribution prediction of the application, the technical personnel simulate the related scheme, design multiple groups of comparative experiments in the experimental process, construct an LNG ship formation model conforming to the actual sailing scene through a simulation platform, and quantitatively verify the risk prediction accuracy, balance regulation effect, and energy consumption optimization capability of the scheme of the application.

[0080] I. Experimental content 1.1, Simulation parameter setting In this experiment, a simulation platform based on MATLAB and Python is used as a joint simulation environment to construct a formation model including three LNG ships (the ship parameters refer to the design of a 170,000 cubic meter LNG transport ship), integrate a rigid body dynamics module, a virtual connection force field module, an LNG liquid sloshing module, and a reinforcement learning regulation module. Some simulation parameters are as follows: (1) Ship basic parameters: single ship mass is 50000 kg, roll inertia moment is 10 8 kgm2 , the roll inertia moment is 2 x 10 8 kgm 2 , the LNG density in the storage tank is 425 kg / m 3 , the storage tank volume is 1000 m 3 .

[0081] (2) Virtual connection parameters: the elastic coefficient is 10 4 N / m, the damping coefficient is 5 x 10 3 Ns / m, the torsional elastic coefficient is 5 x 10 3 Nm / rad, the torsional damping coefficient is 2 x 10 3 Nms / rad, and the effective action distance threshold is 150 m.

[0082] (3) Environmental load parameters: the wind and wave current load is simulated by using the Morison formula, the wind speed is 15 m / s, the effective wave height is 3 m, the wave period is 8 s, and the sea current speed is 2 m / s.

[0083] (4) Risk prediction model parameters: the WXS model uses 3-layer wavelet decomposition, the dynamic threshold parameter is 0.8, the basic learning rate is 0.01, and the cross-entropy loss function category number is 3 (corresponding to three risk levels).

[0084] (5) Reinforcement learning parameters: the DQN algorithm experience pool capacity is 10 5 , the target network update interval is 100 steps, the discount factor is 0.95, and the exploration rate is dynamically adjusted according to the risk level.

[0085] 1.2, Control group setting In this experiment, the scheme of the application is used as the experimental group, and two control groups are set up to verify the advantages of the scheme of the application through comparison experiments. The experimental group and the control group are as follows: ① Experimental group (ship formation 1): using the method of the application (fusion of virtual connection + WXS risk prediction + reinforcement learning regulation) ② Control group (ship formation 2): traditional single ship independent regulation method (without virtual connection, only based on single ship attitude feedback regulation) ③ Control group (ship formation 3): formation regulation method without risk prediction (retaining virtual connection, only passive regulation after the attitude angle exceeds the threshold) Each group of experiments lasts 300 s, the sampling frequency is 10 Hz, and the average value is taken for 5 repeated experiments.

[0086] II. Experimental results and analysis 2.1, Verification of wind and wave coupling effect This experiment first tests the time sequence curve of the LNG liquid sloshing additional force in the X direction of different ships in the formation under the wind and wave load, and the experimental results are shown in Figure 4 .

[0087] According to the data in the figure, the additional force X component of the ships 1, 2 and 3 all shows obvious periodic fluctuation characteristics, and the fluctuation period is basically consistent with the coupling period of sea wave excitation and ship attitude response, reflecting the strong correlation between liquid sloshing and environmental load and ship movement. The amplitude of the additional force X component of the ship 3 is higher than that of the ships 1 and 2 as a whole, and the average amplitude is close to 2000 N, which is due to the fact that the ship 3 is in the rear position in the formation, and the superimposed influence of the flow field disturbance of the front ship and the attitude coupling effect of the ship itself is more significant; while the ship 1 as the lead ship of the formation, is relatively weakly affected by the indirect action of the following ships, and the amplitude of the additional force X component is relatively small, about 1000 N on average.

[0088] Then the time sequence curves of the LNG liquid sloshing additional force in the Y direction of different ships in the formation under the wind and wave load are tested, and the experimental results are shown in Figure 5 .

[0089] According to the data in the figure, the additional force Y component of the three ships has both synchronization and difference in the time dimension, the synchronization reflects the mutual correlation of the ship movement response in the formation, and the difference is due to the different spatial positions, initial attitudes and liquid sloshing phases of the ships in the formation. The distribution characteristics of the liquid sloshing additional force Y component bring challenges to the transverse balance regulation and control of the ship formation, and further verify the necessity of the virtual connection force field and the distributed prediction method proposed in the present application in coordinating the sloshing response of multiple ships in the longitudinal direction.

[0090] Next, the time sequence curves of the LNG liquid sloshing additional moment in the X direction of different ships in the formation under the wind and wave load are tested, and the experimental results are shown in Figure 6 .

[0091] According to the data in the figure, the amplitude of the additional moment X component of the ship 3 is the largest, the positive peak value is nearly 120000 Nm, and the negative peak value is about 100000 Nm; the amplitude of the ship 2 is the second, and the amplitude of the ship 1 is the smallest. The change trend of the additional moment X component of the three ships has synchronization but phase difference, which is due to the difference of the spatial positions, initial attitudes and liquid sloshing phases of the ships.

[0092] The time sequence curves of the LNG liquid sloshing additional moment in the Y direction of different ships in the formation under the wind and wave load are also tested, and the experimental results are shown in Figure 7 .

[0093] According to the data in the figure, it can be seen that the amplitude of the additional moment Y component of ship 2 is relatively larger, and the positive peak value is close to 42000Nm, while the amplitude of ship 1 and ship 3 is relatively smaller. This distribution increases the complexity of the balance regulation of the formation pitch, and further illustrates the importance and effectiveness of the method in coordinating the pitch response of multiple ships.

[0094] Finally, the time sequence variation curves of the liquid sloshing additional force and additional moment are drawn, and the experimental results are shown in Figure 8

[0095] According to the data in the figure, it can be seen that the amplitude of the additional moment Y component of ship 2 is relatively larger, and the positive peak value is close to 42000Nm, while the amplitude of ship 1 and ship 3 is relatively smaller. This distribution increases the complexity of the balance regulation of the formation pitch, and further illustrates the importance and effectiveness of the method in coordinating the pitch response of multiple ships.

[0096] 2.2, risk prediction accuracy The experiment further verifies the time sequence comparison of local risk and global risk of ship formation in different schemes, and the corresponding variation curves are shown in Figure 9 The comparison of risk prediction performance between the present application and the second control group is shown in Table 1: Table 1: Comparison of risk prediction performance indicators

[0097] According to the analysis of the risk prediction index statistics in Table 1: The global risk changes dynamically in the interval [0.2, 0.8], in which R1 accounts for 32%, R2 accounts for 45%, and R3 accounts for 23%, and the coincidence degree with the actual attitude threshold value reaches 92%, proving that the WXS model can accurately map the relationship between ship state and risk level. In addition, the risk prediction accuracy of the experimental group reaches 90.5%, which is 22.3 percentage points higher than that of the control group 2 (without risk prediction) of 68.2%, the false positive rate (no risk misjudgment as risk) is reduced to 5.3%, and the false negative rate (high risk misjudgment as low risk) is reduced to 4.2%. At the same time, the global risk fusion weight based on entropy weight method (ship 1: 0.32, ship 2: 0.35, ship 3: 0.33) matches the stress weight of the ship in the formation, avoiding the deviation of single ship risk dominating the global judgment.

[0098] 2.3, balance regulation effect verification The time sequence variation of the yaw angle and pitch angle of the ship formation in different schemes is further tested, and the variation curves are​Figure 10 The balance control effect in the same state is shown in Table 2.

[0099] Table 2: Comparison of posture balance control effect indicators

[0100] From the analysis of the control effect indicators in Table 2, it can be seen that: The average amplitude of the yaw angle of the experimental group is 2.8°, and the average amplitude of the pitch angle is 2.5°, both of which are controlled within the 3° safety threshold; the average amplitude of the yaw angle of the control group 1 (single ship control) is 4.5°, and the pitch angle is 3.8°, with an out-of-threshold time length ratio of 18.3%; the out-of-threshold time length ratio of the control group 2 (without risk prediction) is 12.7%, proving that the invention can effectively suppress the posture out-of-limit through the "prediction-control" closed loop; at the same time, when a short-time strong load causes the posture to approach the threshold, the experimental group can restore the posture to within 1° within 15-20s, which is about 50% faster than the control group 1 (35-40s) and about 30% faster than the control group 2 (25-30s), reflecting the rapid response advantage of the reinforcement learning control strategy; the posture standard deviation of the experimental group 3 ships (yaw angle: 0.52°, pitch angle: 0.48°) is reduced by 58%-55% compared with the control group 1 (yaw angle: 1.23°, pitch angle: 1.05°), proving that the virtual connection can realize the cooperation of multiple ship postures and avoid the problem of "single ship stabilization and formation shaking".

[0101] 2.4, Energy consumption optimization effect verification The energy consumption results of different schemes are shown in Table 3.

[0102] Table 3: Comparison of energy consumption and comprehensive performance indicators

[0103] From the energy consumption indicators in Table 3, it can be seen that: the total energy consumption of the experimental group balance weight system is 2850kJ, which is reduced by 30.8% compared with the control group 1 (4120kJ) and by 22.5% compared with the control group 2 (3680kJ), because the energy consumption weight in the reinforcement learning reward function is 0.3, which moderately relaxes the energy consumption limit in high-risk situations and prioritizes energy saving in low-risk situations, achieving the coordinated optimization of balance and energy consumption. At the same time, the experimental group is superior to the control groups in four core indicators: risk prediction accuracy (90.5%), balance recovery speed (15-20s), posture control precision (maximum amplitude 2.8°), and energy consumption efficiency (2850kJ), with a radar chart comprehensive score that is 42% higher than the control group 1 and 27% higher than the control group 2, proving the systematic advantage of the invention method.

[0104] 2.5, Comparison of comprehensive performance of different schemes According to the experimental data analysis above, the present application draws a multi-dimensional performance radar comparison chart of the ship formation and the traditional ship formation control scheme, so as to directly compare the performance of the research method and the traditional method in the risk prediction accuracy, the balance recovery speed, the attitude control precision and the energy consumption efficiency. Figure 11

[0105] According to the data in the figure, the performance of the present application scheme (blue area) is better than that of the traditional method (red area) in each index, especially in risk prediction accuracy and balance recovery speed, which fully reflects the comprehensive performance advantage of the present method in the balance adjustment of the ship formation.

[0106] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.​

Claims

1. A method for balanced regulation of LNG ship formation with fusion of virtual connection and distribution prediction, characterized in that, It comprises: A multi-body system representing LNG ship formation is constructed based on rigid body dynamics theory; The multi-body system determines whether there is a virtual connection relationship between any two ships according to the distance between them, and generates the corresponding interaction force and interaction torque; acquiring each ship i a real-time sailing status, generating a corresponding risk status vector according to the sailing status by using the multi-body system X risk ; Collect data from each ship i angular velocity of sway Liquid level height h i and acceleration along the plane ( a xi , a yi ), and compare it with its own risk state vector X risk,i And other ships with virtual connections. j Risk state vector X risk,j Together as a risk prediction vector for current ships D i ; i =1… n , n Indicates the number of ships in the formation; input the risk prediction vector of each ship into a trained risk prediction model WXS based on time series data, to generate the corresponding risk prediction result and the fusion weight determined based on the entropy weight method w i According to generate a global risk ; When the preset safety threshold is exceeded, it is determined that there is a risk; at this time, according to the platoon position (v x , y ), the platoon speed v and the risk prediction vector D of each ship i , the platoon global state s and the risk level R c , a preset control strategy experience set is queried to obtain an optimal control strategy B* , B* { b i}, i =1… n ; and when the yaw angle and / or the pitch angle of any vessel exceeds a safety threshold, according to B* issuing a balancing control instruction to its vessels; wherein, b i denotes the control action of the i th ship, ; Δ v i and denote the velocity and displacement vectors of the ballast in the ship, respectively.

2. The method of claim 1, wherein, Let the generalized coordinate vector of each ship be defined as ; the moments of inertia in three dimensions are respectively: I xi , I yi , I zi ; in,( x i , y i Corresponding ships i Plane coordinates; , , For ships i Yaw angle, pitch angle and heading angle: The translational dynamics equation of any i-th ship in the multi-body system is: i The translational dynamics equation of any i-th ship in the multi-body system is: ； in, j Indicates with ships i Other vessels with virtual connection relationships; m i Indicates a ship i quality; F ij For ships j For ships i The interaction force vector; F li F is the vector of the additional force generated by the sloshing of LNG liquid. wi r is the environmental load force vector that includes wind, waves, and current. i For ships i The position vector, ; Any of the i The rotational dynamics equation for any of the ships is: ； wherein is the vector of the interaction forces and moments acting on the ship j is the vector of the interaction forces and moments acting on the ship i is the vector of the interaction forces and moments acting on the ship is the vector of the additional moments due to the LNG liquid sloshing is the vector of the environmental load moments i is the vector of the environmental load moments i is the vector of the environmental load moments i = diag( I xi , I yi , I zi ); is the vector of the angular velocity of the ship i is the vector of the angular velocity of the ship is the vector of the angular velocity of the ship 3. The method of balanced regulation of LNG fleet formation fusing virtual connection with distributed prediction according to claim 2, characterized in that: Interaction force vector F between any two vessels i and j Interaction force vector F between any two vessels ij and interaction torque vector Based on the virtual connection relationship and relative position, attitude information determination, and through the following virtual force field model calculation: ； ； In the above formulae, k ij and c ij are the virtual connection's elastic and damping coefficients, respectively; k tij and c tij are the virtual connection's torsional elastic and damping coefficients, respectively; r i and r j are the position vectors of the ship i and j , respectively; and are the yaw angles of the ship i and j , respectively; d ij is the actual distance between the two ships; d th is the preset effective action distance threshold.

4. The method of balanced regulation of LNG fleet formation fusing virtual connection with distributed prediction according to claim 3, characterized in that, The risk state vector of any nth ship generated using the multi-body system i X risk,i The data format is:​ ； In the above formula, E li represents the sway energy of the ship, ; u l is the kinematic viscosity of the liquid.

5. The method of balanced regulation of LNG fleet formation fusing virtual connection with distributed prediction according to claim 4, characterized in that, Additional force vector F li And additional moment vector The calculation formula is as follows: ； In the above formula, is the LNG liquid density, V l is the LNG liquid volume in the ship tank; v l is the liquid micro-element velocity vector, r cl is the liquid micro-element position vector relative to the ship center of mass; denotes the material derivative; Liquid cell velocity vector v l By solving the Navier-Stokes equations considering sloshing of the free surface: ； wherein p l is the liquid pressure; u l is the liquid dynamic viscosity, g is the gravitational acceleration vector; denotes a gradient operator.

6. The method of balanced regulation of LNG fleet formation fusing virtual connection with distributed prediction according to claim 5, characterized in that: The risk prediction model adopts a cross-entropy comprehensive prediction model based on wavelet analysis, which predicts the current risk prediction result of the ship according to the input risk prediction vector D i of the time sequence data x t ​​​ The wavelet decomposition formula used by the risk prediction model is as follows: ； In the above formula, t Indicates time; and These are the scaling function and the wavelet function, respectively. a j,k For the model number j The approximation coefficients of the layer at time k; d j,k For the model number j The layer in the first k The detail factor of each moment, k The time axis index represents the time series data; d j,k Processing is performed using a dynamic threshold function as follows to enhance feature signal-to-noise ratio: ； wherein, denotes the enhanced detail coefficient; denotes a dynamic threshold parameter, ; is a standard deviation estimate of the detail coefficients, N is a data length of the time series data; And / or, the risk prediction model employs a cross-entropy loss function in the training phase L CE : ； In the above formula, p c a true probability distribution representing the risk of imbalance of the ship; is a model-predicted class probability distribution; c represents an index of the risk class; C is the total number of classes of risk. And / or, the dynamic weight update formula used by the risk prediction model is: ； wherein, T denotes the number of iterations; and are the weights of the first T and T the first m base models included in the risk prediction model in the m th iteration; denotes the learning rate; and / or, Adopting adaptive learning rate related to the fluctuation rate of prediction error: ； In the above formula, is the base learning rate, Var Error represents the variance of the prediction error.​ 7. The method of balanced regulation of LNG fleet formation fusing virtual connection with distributed prediction according to claim 6, characterized in that: The regulation strategy experience set is a data set representing the global state of any formation generated by a reinforcement learning algorithm according to historical navigation data of the ship formation s and risk levels R c and the mapping relationship between the regulation strategy B* ​ and / or, in the reinforcement learning framework of building the set of regulation policy experiences, the definition of each global state in the state space s is: ； wherein , ; each action in the action space b i for: ； Reward function is: ； In the above formula, R balance and R energy respectively represent the balance reward and the energy consumption reward; α and β respectively represent the weights of the balance reward and the energy consumption reward; and respectively represent the ship yaw angle and the pitch angle after the execution of the control action; represents the global state after the execution of the control action; and respectively represent the penalty term determined according to the standard deviation of the yaw angle and the pitch angle; Δ E is the energy consumption increment generated by the control action; represents the risk adaptation coefficient determined according to the risk level.

8. The method of balanced regulation of LNG fleet formation fusing virtual connection with distributed prediction according to claim 7, characterized in that: Global risk predicted by the WXS model with risk level R c The mapping relationship is: When 0.5 ≥ > 0.4, R c = R1, indicating low risk; When 0.6 ≥ > 0.5, R c = R2, indicates medium risk; When > 0.6, R c = R3, indicates high risk; And / or, each action in the reinforcement learning framework adopts an adaptive action space according to the risk level, including: When R c = R1, ; When R c = R2, ; When R c = R3, .

9. A computer program product comprising a computer program, characterised in that, When the computer program is executed by the processor, the balance adjustment method of the LNG ship formation integrating virtual connection and distribution prediction is realized, and then the imbalance risk of the whole formation is predicted according to the real-time state of each ship in the formation, and adaptive control actions are generated to maintain the balance of the ships.

10. A vessel formation balancing control device comprising a memory, a processor, and a computer program stored on the memory and running on the processor, characterized in that: When the computer program is executed by the processor, the balance adjustment method of the LNG ship formation integrating virtual connection and distribution prediction is realized, and then the imbalance risk of the whole formation is predicted according to the real-time state of each ship in the formation, and adaptive control actions are generated to maintain the balance of the ships.

Images