Ship operation efficiency intelligent control system and method based on large model optimization

Abstract

The invention relates to the field of ship operation efficiency intelligent control, in particular to a ship operation efficiency intelligent control system and method based on large model optimization. Comprising the following steps: collecting real-time data of ship operation and environment, eliminating dimensional difference through normalization processing to obtain normalized data, forming a normalized data vector, and performing feature extraction on the normalized data vector by adopting a multi-dimensional data feature mapping algorithm to obtain a feature vector; calculating through a dynamic adaptive disturbance optimization algorithm to obtain an optimal solution; and generating a dimensionless control vector based on the difference between the optimal solution and the initial solution, and converting the dimensionless control vector into an actual control vector through a reverse normalization operation. The problem that an existing method cannot comprehensively consider mutual influence between ship and environmental factors, especially efficient optimization in a complex dynamic environment is solved; a traditional optimization method is easy to fall into a local optimal solution; the technical problem that a traditional control method lacks real-time and accurate adjustment is solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control of ship operation efficiency, and in particular to a system and method for intelligent control of ship operation efficiency based on large model optimization. Background Art

[0002] In the field of modern shipping, with the advancement of global economic integration and the rapid growth of international trade, the shipping industry is facing more and more challenges. How to improve the operational efficiency of ships, reduce operating costs, optimize energy consumption during navigation, and reduce environmental pollution has become an important issue that the industry needs to solve. Traditional ship operation efficiency optimization methods mostly rely on experience and rules. Although they can improve efficiency to a certain extent, they often show great limitations when facing complex sea conditions, route changes, and diversified ship types.

[0003] In this context, the intelligent control method of ship operation efficiency based on big model optimization came into being. Big model optimization technology uses advanced artificial intelligence, big data analysis, deep learning and other technologies, combined with real-time ship operation data and environmental data, to achieve refined management and real-time dynamic adjustment of the ship's operating efficiency throughout its life cycle, thereby improving shipping efficiency, reducing energy consumption, optimizing navigation routes, and ultimately achieving intelligent control of ship operation efficiency.

[0004] However, the above-mentioned existing ship operation efficiency intelligent control system and method based on large model optimization still have technical problems such as being unable to fully optimize fuel consumption and energy utilization during ship operation, resulting in energy waste, high carbon emissions and high operating costs; and being unable to fully consider the interactive effects of dynamic environmental factors, resulting in the failure to maximize the ship's operating efficiency. Summary of the invention

[0005] The present invention provides a ship operation efficiency intelligent control system and method based on large model optimization to solve the technical problems that the existing methods cannot fully consider the mutual influence between the ship and environmental factors, especially the efficient optimization in a complex dynamic environment; the traditional optimization method is prone to fall into the local optimal solution; and the traditional control method lacks real-time and precise adjustment.

[0006] The present invention provides a ship operation efficiency intelligent control system and method based on large model optimization, which specifically includes the following technical solutions: A ship operation efficiency intelligent control method based on large model optimization includes the following steps: S1. Collect real-time data of ship operation and environment, eliminate dimension differences through normalization processing, obtain normalized data, form a normalized data vector, and use a multi-dimensional data feature mapping algorithm to extract features from the normalized data vector to obtain a feature vector; S2. Perform disturbance search and adaptive adjustment through dynamic adaptive disturbance optimization algorithm to calculate the optimal solution; generate a dimensionless control vector based on the gap between the optimal solution and the initial solution, and convert the dimensionless control vector into an actual control vector through denormalization operation.

[0007] Preferably, the S1 specifically includes: The multi-dimensional data feature mapping algorithm integrates the current normalized data vector and the historical normalized data vector as the basic part of the input enhancement matrix, and introduces the pseudo-periodic disturbance vector and the environmental coupling factor vector to form the input enhancement matrix.

[0008] Preferably, the S1 specifically includes: In the implementation process of the multidimensional data feature mapping algorithm, the input enhancement matrix is ​​converted into an intermediate feature matrix through nonlinear feature mapping. The calculation formula is: , in, Indicates at time The intermediate feature matrix of represents the transpose of the input augmentation matrix; represents transpose; Indicates at time The input augmentation matrix of represents the square of the Frobenius norm as part of the normalization factor; Represents the environmental attenuation matrix, reflecting the time Attenuating effects of environmental factors.

[0009] Preferably, the S1 specifically includes: In the implementation process of the multidimensional data feature mapping algorithm, the intermediate feature matrix is ​​processed by inverse mapping, the intermediate feature matrix is ​​reversely mapped back to the input space to obtain the pseudo-inverse matrix of the intermediate feature matrix, and a dynamic projection matrix is ​​designed to combine the pseudo-inverse matrix of the intermediate feature matrix with the dynamic projection matrix to finally obtain a feature vector including fuel efficiency and energy utilization.

[0010] Preferably, the S2 specifically includes: The dynamic adaptive disturbance optimization algorithm introduces random disturbance and adaptive step size, and uses disturbance feedback and historical experience to dynamically adjust the search direction and step size; in the initialization stage, the optimization objective function is defined and the initial solution is set; the initial solution is composed of the fuel efficiency and energy utilization rate at the current moment.

[0011] Preferably, the S2 specifically includes: In the implementation process of the dynamic adaptive perturbation optimization algorithm, an iterative search is performed. In each round of iteration, a random perturbation vector is generated to perturb the current solution, thereby obtaining a candidate solution; the random perturbation vector is generated through a standard normal distribution and is normalized after each generation to become a unit vector, that is, the random perturbation direction.

[0012] Preferably, the S2 specifically includes: In the implementation process of the dynamic adaptive perturbation optimization algorithm, an adaptive step size mechanism is introduced to dynamically adjust the perturbation step size according to the difference between the current optimization objective function value and the historical maximum optimization objective function value. The calculation formula of the perturbation step size is: , in, Indicates The perturbation step size for each iteration; Indicates The perturbation step size of the iteration; represents the step size attenuation factor; represents the function used to adjust the perturbation step size; Indicates The optimized objective function value of the iteration; Represents the historical maximum optimization target objective function value.

[0013] Preferably, the S2 specifically includes: In the implementation process of the dynamic adaptive disturbance optimization algorithm, candidate solutions are generated by weighted sum based on the disturbance step size; after multiple rounds of iterations, the optimal solution is finally output, that is, the fuel efficiency and energy utilization rate that maximizes the optimization objective function value in the entire optimization process.

[0014] A ship operation efficiency intelligent control system based on large model optimization includes the following parts: Real-time data acquisition and normalization processing module, feature extraction module, adaptive optimization processing module, control generation module, and anti-normalization module; Real-time data acquisition and normalization processing module: collects real-time data of ship operation and environment, eliminates dimension differences through normalization processing, obtains normalized data, constructs normalized data vectors from the normalized data, and outputs the normalized data vectors to the feature extraction module; Feature extraction module: uses a multi-dimensional data feature mapping algorithm to extract features from the normalized data vector from the real-time data acquisition and normalization processing module to obtain a feature vector, which includes fuel efficiency and energy utilization. The fuel efficiency and energy utilization constitute an initial solution, and outputs the feature vector to the adaptive optimization processing module, and outputs the feature vector as an initial solution to the control generation module; Adaptive optimization processing module: Based on the feature vector of the feature extraction module, the dynamic adaptive disturbance optimization algorithm is used to perform disturbance search and adaptive adjustment, calculate the fuel efficiency and energy utilization rate that maximizes the optimization objective function value, obtain the optimal solution, and output the optimal solution to the control generation module; Control generation module: Based on the gap between the optimal solution of the adaptive optimization processing module and the initial solution of the feature extraction module, a dimensionless control vector is generated through a proportional control method, and the dimensionless control vector is output to the anti-normalization module; Denormalization module: The dimensionless control vector from the control generation module is converted into the actual control vector through the denormalization operation.

[0015] The beneficial effects of the technical solution of the present invention are: 1. By collecting real-time data on ship operation and environment and performing normalization processing, dimensional differences are eliminated, ensuring the consistency and comparability of data, so that ship operation data can be accurately analyzed and processed, laying the foundation for subsequent feature extraction and optimization decision-making, and ensuring the quality and reliability of data.

[0016] 2. By extracting key features from ship operation data, including fuel efficiency and energy utilization, the ship's operating status can be accurately described. By introducing pseudo-periodic disturbance vectors and environmental coupling factor vectors, the time dependency and environmental interaction effects can be captured, reflecting the dynamic changes of the ship under different operating conditions. This can provide accurate data support for ship operation efficiency optimization and effectively improve the accuracy of optimization decisions.

[0017] 3. Through nonlinear feature mapping, the complex patterns hidden in the data are further revealed. At the same time, the environmental influence is integrated through the environmental attenuation matrix, and the influence of normalized factors such as waves and wind speed on ship efficiency is considered. The inhibitory effect of environmental factors on ship operation efficiency can be accurately captured, thereby providing a more comprehensive and detailed feature description for ship operation efficiency optimization, making the optimization results more in line with actual operating conditions.

[0018] 4. The introduction of the dynamic projection matrix improves the directionality of the eigenvector, especially by introducing the influence of the normalized heading angle, which further enhances the ability to characterize the ship's operating status, making the final calculation of fuel efficiency and energy utilization more accurate, and providing a reliable basis for ship optimization decisions.

[0019] 5. By introducing random perturbations and adaptive step sizes, the dynamic adaptive perturbation optimization algorithm can efficiently explore nonlinear space, avoid the limitations of traditional methods, and find a balance between the global optimal solution and the local optimal solution. By continuously adjusting the perturbation step size and direction, it can quickly approach the maximum value of the optimization objective function, effectively improving the accuracy and efficiency of ship optimization decisions, and ensuring that ships can achieve optimal fuel efficiency and energy utilization in complex environments.

[0020] 6. By designing the time smoothness penalty term, the optimization objective function can ensure that the ship remains stable during the optimization process without drastic performance fluctuations, thereby improving the stability and reliability of the ship operation efficiency intelligent control system, avoiding the instability caused by excessive adjustment, and enhancing the operability and adaptability of the ship in practical applications.

[0021] 7. Through the inverse normalization operation, the dimensionless control vector is converted into an actual control vector, so that the speed and heading adjustment of the ship can be reasonably executed in actual operation, ensuring that the ship can accurately adjust its operating state according to the optimization results, thereby improving fuel efficiency and energy utilization, reducing operating costs, and improving the ship's operating performance.

[0022] 8. The constraint boundary mechanism is introduced to ensure that the solution obtained in each optimization is physically feasible, ensuring that the ship operates within the actual operational range, improving the safety and practicality of the optimization process, and avoiding the emergence of solutions that do not meet the actual operating conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a structural diagram of a ship operation efficiency intelligent control system based on large model optimization according to the present invention; Figure 2 This is a flow chart of a method for intelligent control of ship operation efficiency based on large model optimization described in the present invention. DETAILED DESCRIPTION

[0024] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0026] The specific scheme of a ship operation efficiency intelligent control system and method based on large model optimization provided by the present invention is described in detail below with reference to the accompanying drawings.

[0027] See attached Figure 1 , which shows a structural diagram of a ship operation efficiency intelligent control system based on large model optimization provided by an embodiment of the present invention, the system includes the following parts: Real-time data acquisition and normalization processing module, feature extraction module, adaptive optimization processing module, control generation module, and anti-normalization module; Real-time data acquisition and normalization processing module: collects real-time data of ship operation and environment, and eliminates dimension differences through normalization processing to obtain normalized data, including: normalized ship speed, engine power, fuel consumption rate, wind speed, wave height and heading angle, and constructs a normalized data vector from the normalized data, and outputs the normalized data vector to the feature extraction module; Feature extraction module: uses a multi-dimensional data feature mapping algorithm to extract features from the normalized data vector from the real-time data acquisition and normalization processing module to obtain a feature vector, which includes fuel efficiency and energy utilization. The fuel efficiency and energy utilization constitute an initial solution, and outputs the feature vector to the adaptive optimization processing module, and outputs the feature vector as an initial solution to the control generation module; Adaptive optimization processing module: Based on the feature vector of the feature extraction module, the dynamic adaptive disturbance optimization algorithm is used to perform disturbance search and adaptive adjustment, calculate the fuel efficiency and energy utilization rate that maximizes the optimization objective function value, obtain the optimal solution, and output the optimal solution to the control generation module; Control generation module: Based on the gap between the optimal solution of the adaptive optimization processing module and the initial solution of the feature extraction module, a dimensionless control vector is generated through a proportional control method, and the dimensionless control vector is output to the anti-normalization module; Denormalization module: The dimensionless control vector from the control generation module is converted into the actual control vector through the denormalization operation.

[0028] See attached Figure 2 , which shows a flow chart of a ship operation efficiency intelligent control method based on large model optimization provided by an embodiment of the present invention, the method comprising the following steps: S1. Collecting real-time data of ship operation and environment, and eliminating dimension differences through normalization processing to obtain normalized data, forming a normalized data vector, and using a multi-dimensional data feature mapping algorithm to extract features from the normalized data vector to obtain a feature vector; Real-time data of ship operation and environment are collected, and dimension differences are eliminated through normalization processing to obtain normalized data, including: normalized ship speed, engine power, fuel consumption rate, wind speed, wave height and heading angle, and the normalized data are formed into a normalized data vector, which is expressed as follows: , in, Indicates at time Normalized data vector; Indicates at time Normalized ship speed; Indicates at time Normalized engine power; Indicates at time Normalized fuel consumption rate; Indicates at time Normalized wind speed; Indicates at time Normalized wave height; Indicates at time Normalized heading angle; represents transpose; In order to extract practical operation characteristics from the real-time data of ship operation and provide data support for ship operation efficiency optimization decision-making, a multi-dimensional data feature mapping algorithm is used to extract features from the normalized data vector to obtain a feature vector, including fuel efficiency and energy utilization; The multidimensional data feature mapping algorithm integrates the current normalized data vector and the historical normalized data vector as the basic part of the input enhancement matrix. In order to capture the time dependency and environmental interaction effects, the multidimensional data feature mapping algorithm introduces two additional disturbance terms: one is a pseudo-periodic disturbance vector, which generates periodic changing features through sine function and cosine function based on the normalized ship speed and the normalized wind speed. Specifically, the sine value is calculated by multiplying the normalized ship speed by the time step, and the cosine value is calculated by multiplying the normalized wind speed by the time step to form a two-dimensional vector that reflects the periodic dynamics of the normalized data; the second is an environmental coupling factor vector, which generates another two-dimensional vector by multiplying the normalized wind speed by the normalized wave height, and the product of the normalized ship speed and the normalized heading angle cosine value to characterize the interaction between environmental factors; The input enhancement matrix is ​​expressed as follows: , in, Indicates at time The input augmentation matrix is ​​used to capture the time dependency of ship operation and the environmental interaction effects; Indicates at time Normalized data vector; Indicates at time Normalized data vector; Represents the pseudo-periodic perturbation vector, reflected in time Based on the pseudo-periodic disturbances of the normalized ship speed and the normalized wind speed, the time dynamic characteristics of the normalized data are enhanced by introducing periodic disturbances. The pseudo-periodic disturbance vector is expressed as: , represents the normalized sine transform of the ship's speed; represents the cosine transform of the normalized wind speed; Indicates the time step, which can be set according to the specific implementation scenario and is not limited here; Represents the environmental coupling factor vector, reflected in time The coupling effect between environmental factors, the environmental coupling factor vector is expressed as: , Indicates at time The product of normalized wind speed and normalized wave height reflects the wind-wave interaction effect. Indicates at time The product of the normalized ship speed and the normalized cosine of the heading angle reflects the influence of the heading on the ship speed; The input enhancement matrix is ​​further transformed into an intermediate feature matrix through nonlinear feature mapping to explore hidden patterns in the normalized data while avoiding the limitations of traditional activation functions. Specifically, the input enhancement matrix is ​​multiplied by its own transpose to obtain a new matrix, which emphasizes the intrinsic correlation between the data. At the same time, in order to avoid calculation instability caused by too large or too small values, normalization processing is performed. The normalization processing method is to calculate the Frobenius norm of the input enhancement matrix, that is, the square root of the sum of squares of all elements, and then the square of the Frobenius norm plus 1 is used as the denominator, and the product of the input enhancement matrix and its own transpose is divided by the denominator to obtain a scaled matrix; In order to further incorporate environmental influences, an environmental attenuation matrix is ​​designed. The first element of the environmental attenuation matrix is ​​the result of calculating the exponential function after taking the negative value of the normalized wave height, and the second element is the result of calculating the exponential function after taking the negative value of the normalized wind speed. The non-diagonal elements are zero, reflecting the inhibitory effect of environmental factors on the characteristics. For example, the higher the waves or the greater the wind speed, the lower the operating efficiency of the ship may be. Add the scaled matrix to the environmental attenuation matrix to get the intermediate feature matrix, which is calculated as: , in, Indicates at time The intermediate feature matrix is ​​used to capture the nonlinear patterns and environmental effects of the input data; represents the transpose of the input augmentation matrix, which is the same as the input augmentation matrix Multiply to generate the matrix self-product result, which is used to extract the intrinsic relationship between data; Represents the square of the Frobenius norm, which is used as part of the normalization factor to prevent the result of the matrix multiplication from being too large and maintain numerical stability; Represents the environmental attenuation matrix, reflecting the time The attenuation effect of environmental factors, the environmental attenuation matrix is ​​expressed as: , in, represents the exponential decay term of the normalized wave height; represents the exponential decay term of the normalized wind speed; The final eigenvector is extracted from the intermediate feature matrix, including fuel efficiency and energy utilization. Specifically, the intermediate feature matrix is ​​processed by inverse mapping. Since the intermediate feature matrix is ​​not necessarily a square matrix or reversible, the intermediate feature matrix is ​​inversely mapped back to the input space to obtain a pseudo-inverse matrix of the intermediate feature matrix to ensure calculation stability. In order to further introduce the influence of the normalized heading angle and improve the directionality of the feature, a dynamic projection matrix is ​​designed. The elements of the dynamic projection matrix are calculated based on the tangent value of the normalized heading angle. The elements on the main diagonal are all 1, the upper right element is the tangent value of the normalized heading angle, and the lower left element is the negative value of the tangent value of the normalized heading angle. The calculation formula of the eigenvector is: , in, Indicates at time The eigenvector of contains fuel efficiency and energy utilization, as the initial solution, which reflects the operation efficiency of the ship. The eigenvector is expressed as: , Indicates at time Fuel efficiency, Indicates at time Energy utilization rate; express The pseudo-inverse matrix of Reverse mapping back to the input space ensures computational stability, especially in It can still be solved when it is non-reversible; Represents the dynamic projection matrix, introduces the influence of the normalized heading angle, adjusts the directionality of the eigenvector, and improves the ability to characterize the ship's operating status. The dynamic projection matrix is ​​expressed as: , in, represents the tangent function, reflecting the influence of the heading angle of the intermediate feature matrix; Represents back projection, used for directional adjustment; By extracting effective features from ship operation data, a more accurate assessment of the ship's fuel efficiency and energy utilization can be made, providing a reliable basis for subsequent optimization decisions; S2. Perform disturbance search and adaptive adjustment through dynamic adaptive disturbance optimization algorithm to calculate the optimal solution; generate a dimensionless control vector based on the gap between the optimal solution and the initial solution, and convert the dimensionless control vector into an actual control vector through an anti-normalization operation; Ship operation needs to find the optimal balance between economy and performance. The dynamic adaptive disturbance optimization algorithm is used to search for disturbances and make adaptive adjustments. It can efficiently explore nonlinear space, avoid the limitations of traditional methods, calculate the fuel efficiency and energy utilization rate that maximizes the optimization objective function value, and provide target values ​​for subsequent control. The dynamic adaptive perturbation optimization algorithm introduces random perturbations and adaptive step sizes to explore the global optimal solution in nonlinear and non-convex optimization problems. It uses perturbation feedback and historical experience to dynamically adjust the search direction and step size, and quickly approaches the maximum value of the optimization objective function in the search space while avoiding falling into the local optimal solution. The specific implementation is as follows: In the initialization stage, the optimization objective function is defined and an initial solution is set; the initial solution is composed of the fuel efficiency and energy utilization rate at the current moment; The optimization objective function aims to balance the fuel efficiency and energy utilization of the ship, while taking into account time smoothness, ensuring that the operation of the ship remains stable and does not cause performance fluctuations due to excessive adjustments. Specifically, by weighting the fuel efficiency and energy utilization, the optimization objective function can comprehensively consider the fuel consumption and energy utilization of the ship, and through the time smoothness penalty term, ensure that the ship does not experience drastic performance fluctuations during the optimization process, thereby improving the stability and reliability of the ship operation efficiency intelligent control system; The optimization objective function is defined as follows: , in, Represents the optimization objective function value, which is used to measure the quality of the current solution and serves as an evaluation criterion for the optimization process to decide whether to update the current solution. The weighting coefficient representing fuel efficiency is used to control the importance of fuel efficiency in the optimization process. It can be set according to the specific implementation scenario and is not limited here. The weighted coefficient representing the energy utilization rate is used to control the importance of the energy utilization rate in the optimization process. It can be set according to the specific implementation scenario and is not limited here. It represents the time smoothness penalty term, which is used to avoid drastic changes in a short period of time and penalize the initial solution with drastic changes, thereby reducing shocks and increasing stability; Represents the smoothing coefficient, which is used to control the intensity of the smoothness penalty to avoid too many rapid changes. It can be set according to the specific implementation scenario and is not limited here; Indicates at time fuel efficiency; Indicates at time Energy utilization rate; In the iterative search process, the dynamic adaptive perturbation optimization algorithm dynamically adjusts the search step size and direction based on the current solution and historical state. By introducing random perturbations, it ensures extensive exploration of potential optimal solutions. In each round of iteration, a random perturbation vector is generated to perturb the current solution to obtain a candidate solution. The random perturbation vector is generated by a standard normal distribution and is normalized after each generation to become a unit vector (length 1) to ensure the consistency of the random perturbation direction, so that the dynamic adaptive perturbation optimization algorithm can conduct a comprehensive exploration in high-dimensional space and effectively avoid falling into a local optimal solution. The formula for the random perturbation direction is: , in, Indicates The random perturbation direction of the iteration is used to generate candidate solutions to ensure the randomness of the search; Represents a random perturbation vector, which obeys a two-dimensional standard normal distribution. generate; Represents the Euclidean norm of the random perturbation vector, reflecting the size of the generated random perturbation vector; In order to ensure the convergence and efficiency of the dynamic adaptive perturbation optimization algorithm, an adaptive step size mechanism is introduced. In each iteration, the perturbation step size is dynamically adjusted according to the difference between the current optimization objective function value and the historical maximum optimization objective function value. If the current optimization objective function value is close to the historical maximum optimization objective function value, the perturbation step size will be reduced to improve the accuracy of the local search. On the contrary, if the current optimization objective function value is far away from the historical maximum optimization objective function value, the perturbation step size will be increased to speed up the global search. The perturbation step size is adjusted by the cosine function, thereby achieving a smooth search process, enabling a more extensive exploration in the early stage, and finely adjusting the solution in the later stage, thereby improving the convergence speed and accuracy of the dynamic adaptive perturbation optimization algorithm. The calculation formula of the perturbation step size is: , in, Indicates The perturbation step size of the iteration determines the size of each search step and is adjusted adaptively to improve the search accuracy. Indicates The perturbation step size of the iteration; Represents the step size attenuation factor, which is used to adjust the change speed of the perturbation step size at each iteration. It can be set according to the specific implementation scenario and is not limited here; It represents the function used to adjust the perturbation step size. The cosine function ensures that when the optimization objective function value is close to the historical maximum optimization objective function value, the perturbation step size will gradually decrease, thereby finely searching the area near the optimal solution. Indicates The optimized objective function value of the iteration; Represents the historical maximum optimization target objective function value; In each round of iteration, the generated perturbation step will affect the update of the current solution. Based on the perturbation step, a new candidate solution will be generated by weighted sum, and the calculation formula is: , in, Indicates Candidate solutions for iterations; Indicates Candidate solutions for iterations; Represents the momentum weight, which is used to control the impact of historical momentum on the current disturbance. It can be set according to the specific implementation scenario and is not limited here; Indicates The momentum vector of the iteration is used to adjust the direction when updating the current solution. In each round of iteration, the momentum vector is obtained by the random perturbation direction and update history of the previous round. The calculation formula is: ; Indicates The momentum vector of the iteration; In order to ensure the physical feasibility of the candidate solution, a constraint boundary mechanism is introduced so that each element of the candidate solution is subject to certain constraints to ensure that the optimal solution is within the valid range. The constraint boundary value is set as: ; If the current optimization objective function value is greater than the optimization objective function value of the previous iteration, it means that the current solution is better and the solution and momentum need to be updated. Otherwise, keep the solution and momentum unchanged. The optimization process is terminated by two termination conditions: the maximum number of iterations and the minimum step size. If the maximum number of iterations is reached or the step size has been reduced to a small enough level, the optimization process is terminated and the final optimal solution is output, ensuring that the final result can be given after fully exploring the solution space, while avoiding meaningless over-iteration. After multiple rounds of iterations, the optimal solution is finally output, that is, the fuel efficiency and energy utilization rate that maximize the optimization objective function value in the entire optimization process. The optimal solution is expressed as: , in, represents the best fuel efficiency; Indicates the optimal energy utilization; Based on the gap between the optimal solution and the initial solution, a dimensionless control vector is generated by a proportional control method. The proportional control method is a technical means well known to those skilled in the art and will not be described in detail here. The formula is as follows: , in, represents a dimensionless control vector, which is used to adjust the speed and heading of the ship and is expressed as: , Indicates at time The amount of control over the ship's speed, Indicates at time The amount of control over the ship's heading angle; Represents the proportional control gain matrix, which is used to convert the difference between the optimal solution and the initial solution into the adjustment of the ship's speed and heading, and determines the adjustment strength of each control variable (speed and heading). It can be set according to the specific implementation scenario and is not limited here. The expression is: , Indicates the speed adjustment gain, Indicates the heading angle adjustment gain; The dimensionless control vector is converted into an actual control vector through the anti-normalization operation to ensure that the ship can perform reasonable speed and heading adjustments. The anti-normalization formula is: , in, It represents the actual control vector. The control vector is denormalized and converted into a physical quantity, which represents the actual speed and heading of the ship that need to be adjusted. Indicates the maximum value of the control amount; Indicates the minimum value of the control amount; and Used in the denormalization process to ensure that the actual control vector obtained is within a reasonable range in practical applications; By adjusting the speed and course of the ship in real time, the fuel efficiency and energy utilization of the ship can be effectively improved, energy waste can be reduced, the ship can adapt to complex environmental changes, operating costs can be reduced, and ultimately the optimization of ship operation can be achieved.

[0029] In summary, a ship operation efficiency intelligent control system and method based on large model optimization has been completed.

[0030] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0031] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0032] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A ship operation efficiency intelligent control method based on large model optimization, characterized in that: The following steps are involved: S1. Collect real-time data of ship operation and environment, eliminate dimension differences through normalization processing, obtain normalized data, form a normalized data vector, and use a multi-dimensional data feature mapping algorithm to extract features from the normalized data vector to obtain a feature vector; S2. Perform disturbance search and adaptive adjustment through dynamic adaptive disturbance optimization algorithm to calculate the optimal solution; generate a dimensionless control vector based on the gap between the optimal solution and the initial solution, and convert the dimensionless control vector into an actual control vector through denormalization operation.

2. According to claim 1, a method for intelligent control of ship operation efficiency based on large model optimization is characterized in that: The S1 specifically includes: The multi-dimensional data feature mapping algorithm integrates the current normalized data vector and the historical normalized data vector as the basic part of the input enhancement matrix, and introduces the pseudo-periodic disturbance vector and the environmental coupling factor vector to form the input enhancement matrix.

3. The method for intelligent control of ship operation efficiency based on large model optimization according to claim 2 is characterized in that: The S1 specifically includes: In the implementation process of the multidimensional data feature mapping algorithm, the input enhancement matrix is ​​converted into an intermediate feature matrix through nonlinear feature mapping. The calculation formula is: ， in, Indicates at time The intermediate feature matrix of represents the transpose of the input augmentation matrix; represents transpose; Indicates at time The input augmentation matrix of represents the square of the Frobenius norm as part of the normalization factor; Represents the environmental attenuation matrix, reflecting the time Attenuating effects of environmental factors.

4. The method for intelligent control of ship operation efficiency based on large model optimization according to claim 3 is characterized in that: The S1 specifically includes: In the implementation process of the multidimensional data feature mapping algorithm, the intermediate feature matrix is ​​processed by inverse mapping, the intermediate feature matrix is ​​reversely mapped back to the input space to obtain the pseudo-inverse matrix of the intermediate feature matrix, and a dynamic projection matrix is ​​designed to combine the pseudo-inverse matrix of the intermediate feature matrix with the dynamic projection matrix to finally obtain a feature vector including fuel efficiency and energy utilization.

5. The method for intelligent control of ship operation efficiency based on large model optimization according to claim 1 is characterized in that: The S2 specifically includes: The dynamic adaptive disturbance optimization algorithm introduces random disturbance and adaptive step size, and uses disturbance feedback and historical experience to dynamically adjust the search direction and step size; in the initialization stage, the optimization objective function is defined and the initial solution is set; the initial solution is composed of the fuel efficiency and energy utilization rate at the current moment.

6. The method for intelligent control of ship operation efficiency based on large model optimization according to claim 5 is characterized in that: The S2 specifically includes: In the implementation process of the dynamic adaptive perturbation optimization algorithm, an iterative search is performed. In each round of iteration, a random perturbation vector is generated to perturb the current solution, thereby obtaining a candidate solution; the random perturbation vector is generated through a standard normal distribution and is normalized after each generation to become a unit vector, that is, the random perturbation direction.

7. The method for intelligently controlling ship operation efficiency based on large model optimization according to claim 6 is characterized in that: The S2 specifically includes: In the implementation process of the dynamic adaptive perturbation optimization algorithm, an adaptive step size mechanism is introduced to dynamically adjust the perturbation step size according to the difference between the current optimization objective function value and the historical maximum optimization objective function value. The calculation formula of the perturbation step size is: ， in, Indicates The perturbation step size for each iteration; Indicates The perturbation step size for each iteration; represents the step size attenuation factor; represents the function used to adjust the perturbation step size; Indicates The optimized objective function value of the iteration; Represents the historical maximum optimization objective function value.

8. The method for intelligent control of ship operation efficiency based on large model optimization according to claim 7 is characterized in that: The S2 specifically includes: In the implementation process of the dynamic adaptive disturbance optimization algorithm, candidate solutions are generated by weighted sum based on the disturbance step size; after multiple rounds of iterations, the optimal solution is finally output, that is, the fuel efficiency and energy utilization rate that maximizes the optimization objective function value in the entire optimization process.

9. A ship operation efficiency intelligent control system based on large model optimization, applied to the ship operation efficiency intelligent control method based on large model optimization according to claim 1, characterized in that: Includes the following parts: Real-time data acquisition and normalization processing module, feature extraction module, adaptive optimization processing module, control generation module, and anti-normalization module; Real-time data acquisition and normalization processing module: collects real-time data of ship operation and environment, eliminates dimension differences through normalization processing, obtains normalized data, constructs normalized data vectors from the normalized data, and outputs the normalized data vectors to the feature extraction module; Feature extraction module: uses a multi-dimensional data feature mapping algorithm to extract features from the normalized data vector from the real-time data acquisition and normalization processing module to obtain a feature vector, which includes fuel efficiency and energy utilization. The fuel efficiency and energy utilization constitute an initial solution, and outputs the feature vector to the adaptive optimization processing module, and outputs the feature vector as an initial solution to the control generation module; Adaptive optimization processing module: Based on the feature vector of the feature extraction module, the dynamic adaptive disturbance optimization algorithm is used to perform disturbance search and adaptive adjustment, calculate the fuel efficiency and energy utilization rate that maximizes the optimization objective function value, obtain the optimal solution, and output the optimal solution to the control generation module; Control generation module: Based on the gap between the optimal solution of the adaptive optimization processing module and the initial solution of the feature extraction module, a dimensionless control vector is generated through a proportional control method, and the dimensionless control vector is output to the anti-normalization module; Denormalization module: The dimensionless control vector from the control generation module is converted into the actual control vector through the denormalization operation.

Images