A Marine Hybrid Power Energy Management Method and System Based on MOEAD Algorithm

Abstract

This invention discloses a marine hybrid power system energy management method and system based on the MOEAD algorithm, comprising: building a marine diesel-electric hybrid power system model; determining the decision variables for hybrid power system optimization; and using the MOEAD algorithm to perform multi-objective optimization of fuel consumption and emissions of the hybrid power system. This invention achieves significant beneficial effects by employing the MOEAD algorithm to optimize the energy management of marine diesel-electric hybrid power systems. It effectively reduces fuel consumption and emissions, positively impacting environmental protection. Compared to traditional logic threshold-based strategies, this method improves the accuracy and efficiency of energy management, reduces reliance on experience, and optimizes energy allocation. It enhances the operational performance and economy of ships, providing a more intelligent and efficient solution for the energy management of marine hybrid power systems.

Description

Technical Field

[0001] This invention relates to the field of marine hybrid power energy management technology, specifically to a marine hybrid power energy management method and system based on the MOEAD algorithm. Background Technology

[0002] In the field of energy management for marine hybrid power systems, traditional methods typically employ logic-based threshold energy management strategies. The core of this strategy is to control the ship's operating modes by setting a series of predefined thresholds, such as when to use the diesel engine, when to switch to the electric motor, and when to use both simultaneously. These thresholds are usually based on specific operating parameters, such as speed, load, or battery status. Because it relies on simple logical judgments, this method has relatively low computational complexity and is suitable for scenarios requiring rapid response. The clear boundaries between different operating modes make the system's behavior under different states easier to predict and control. However, the setting of these logic thresholds largely depends on the designer's experience and understanding of the specific ship's operating environment. This may result in these thresholds becoming inapplicable on different ships or under different operating conditions. Due to a lack of comprehensive systemic considerations, this method is generally less effective than more complex optimization algorithms in terms of global energy consumption optimization and emission reduction.

[0003] To address these limitations of traditional methods, this invention proposes a novel energy management strategy that utilizes a decomposition-based multi-objective optimization algorithm (MOEAD) to optimize energy use in hybrid power systems. Compared to logic threshold-based methods, this invention provides a more refined and comprehensive energy management solution, reducing reliance on experience and demonstrating superior performance in reducing fuel consumption and emissions. The introduction of this method marks a shift towards more intelligent and efficient energy management strategies for marine hybrid power systems. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by this invention is that: energy management strategies based on logic thresholds are widely used in the energy management of hybrid-powered ships, with optimization objectives mostly focusing on fuel consumption and greenhouse gas emissions from the ship's propulsion system. However, the setting of logic thresholds relies excessively on experience, resulting in poor overall optimization performance. This patent combines the traditional logic threshold-based method with the MOEAD algorithm, proposing a marine hybrid power energy management method based on the MOEAD algorithm, which improves the optimization effect for specific optimization objectives.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a marine hybrid power energy management method based on the MOEAD algorithm, comprising: building a marine diesel-electric hybrid power system model;

[0007] Determine the decision variables for optimizing the hybrid power system;

[0008] The MOEAD algorithm is used to perform multi-objective optimization of fuel consumption and emissions of hybrid power systems.

[0009] As a preferred embodiment of the marine hybrid power energy management method based on the MOEAD algorithm described in this invention, the construction of the marine diesel-electric hybrid power system model includes: adopting a steady-state modeling method and modeling according to the operating mechanism of the model object, including a diesel engine model, an electric motor model, a lithium battery model, a parallel gearbox model, a diesel generator model, and a ship model.

[0010] As a preferred embodiment of the marine hybrid power energy management method based on the MOEAD algorithm described in this invention, the decision variables for determining the optimization of the hybrid power system include the design operating power P of the diesel generator 1. gen1opt The diesel generator 2 is designed to have a working power P. gen2opt Battery SOC upper and lower ranges up and SOC down Diesel engine design operating torque T eopt and motor design working torque T m_opt_max .

[0011] As a preferred embodiment of the marine hybrid power energy management method based on the MOEAD algorithm described in this invention, the MOEAD algorithm includes: assigning weight vectors to subproblems, determining the adjacent weight vectors of each weight vector, initializing the population and target vector values, initializing reference points, performing crossover, mutation, selection and boundary absorption processing using an adaptive differential evolution algorithm, updating the reference points and population, and updating the output population.

[0012] As a preferred embodiment of the marine hybrid power energy management method based on the MOEAD algorithm described in this invention, the method of assigning weight vectors to sub-problems includes assigning a population individual to each sub-problem, and each population individual also having a corresponding weight vector. For each weight vector, the elements in the vector need to satisfy that they are greater than or equal to 0 and their sum is 1. For a multi-objective optimization problem with two objectives, the weight vector of the i-th population individual... Represented as:

[0013]

[0014] in, This represents the j-th element of the weight vector for the i-th subproblem, where i = 1, ..., P. size ;P size Indicates population size;

[0015] Determining the neighboring weight vectors of each weight vector includes defining them using the Euclidean distance between them, denoted as:

[0016]

[0017] Represents the weight vector λ i and weight vector λ j Euclidean distance d ij ;

[0018] The initialization of the population and target vector values ​​includes setting the lower bound of the decision variables as follows: Let the upper bound of the decision variable be... The magnitude of the j-th decision variable in the i-th initial population individual is expressed as:

[0019]

[0020] Where rand[0,1] represents a uniformly random number between 0 and 1; k represents the number of decision variables;

[0021] After obtaining the initial population, assuming the number of decision variables is M, the objective function vector is obtained by inputting the decision variable values ​​of each individual into the multi-objective optimization problem, as follows:

[0022] V i =OF(x i )

[0023] Where, x i V represents a real-valued parameter vector of dimension M for the i-th individual in the population; OF represents a multi-objective function; V i This represents the target vector value of the i-th individual in the population.

[0024] As a preferred embodiment of the marine hybrid power energy management method based on the MOEAD algorithm described in this invention, the initialization reference point includes replacing the theoretical reference point vector z with a reference point vector z composed of the minimum values ​​of the objective function of the initialization population. * z can be calculated using the following formula:

[0025]

[0026] z = (z1, ..., z M ) T

[0027] The crossover and mutation process using the adaptive differential evolution algorithm includes, from the neighborhood Nh i ={i1,i2,...,i TIf three individuals with different superscripts are randomly selected and differential evolution is performed, the resulting mutation vector, based on the principle of the differential evolution algorithm, is obtained by the following formula:

[0028]

[0029] Where, η i Gen+1 Represents the offspring vector resulting from the mutation; i a i b i c Indicates from the neighborhood Nh i Three weight vector indices are randomly selected from the given values, where a, b, c and weight vector index i are all different; F represents the mutation operator;

[0030] The size of the specific mutation operator is expressed as follows:

[0031] F' = F0 × 2 λ

[0032]

[0033] Where F0 represents the initial mutation operator; Gen max Indicates the maximum number of iterations; F' is the adaptive mutation operator;

[0034] In addition to mutation, crossover is also necessary to increase population diversity. The specific steps are as follows:

[0035] ζ i Gen+1 =(ζ i 1,Gen+1 ,..,ζ i k,Gen+1 )

[0036]

[0037] Where, ζ i Gen+1 represents the weight vector obtained after crossover; k represents the number of decision variables; CR represents the crossover operator; randb(j) represents the j-th random number generated by a random number generator from 0 to 1; rnbr(j) represents the j-th random number generated by a random integer generator from 0 to M;

[0038] The selection and boundary absorption process includes comparing the weight vector after mutation and crossover with the current population's weight vector, and selecting the weight vector with the smallest objective function value to become the new individual in the population. This process ensures that the weight vector ζ... i The elements are located within the feasible region of the multi-objective problem. All parameter values ​​outside the feasible region are set to the nearest upper or lower boundary values ​​to obtain the corrected ζ. i'.

[0039] As a preferred embodiment of the marine hybrid power energy management method based on the MOEAD algorithm described in this invention, wherein: the updated reference point Z and population include, the corrected ζ i Substituting this into the objective function, if equation (1) holds, then update the reference point z according to equation (2):

[0040]

[0041] z j =f j (ζ i' (2)

[0042] For any i∈Nh i ={i1,i2,...,i T If equation (3) holds, then update the population individuals and the objective function vector according to equations (4) and (5):

[0043] g te (ζ i' |λ i ,z)≤g te (x i |λ i ,z) (3)

[0044] x i =ζ i' (4)

[0045] V i =OF(ζ i' (5)

[0046] Among them, g te This represents Chebyshev's formula;

[0047] The updated output population includes removing OF(ζ) from the optimal solution set. i' If the output solution set does not have a dominant objective function vector, then OF(ζ) is the dominant function vector. i' If the objective function vector is ζ, then OF(ζ) i' The objective function vector of the optimal solution is denoted as . After the termination iteration condition is met, the output result is the Pareto optimal solution.

[0048] A marine hybrid power energy management system based on the MOEAD algorithm is characterized by including a model building module for building a marine diesel-electric hybrid power system model.

[0049] Decision variable determination module: Determines the decision variables for optimizing the hybrid power system;

[0050] MOEAD Algorithm Module: Uses the MOEAD algorithm to perform multi-objective optimization of fuel consumption and emissions in hybrid power systems.

[0051] A computer device includes a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the method described above.

[0052] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0053] The beneficial effects of this invention are as follows: This invention achieves significant benefits by employing a decomposition-based multi-objective optimization algorithm (MOEAD) to optimize the energy management of marine diesel-electric hybrid power systems. It effectively reduces fuel consumption and emissions, positively impacting environmental protection. Compared to traditional logic threshold-based strategies, this method improves the accuracy and efficiency of energy management, reduces reliance on experience, and optimizes energy allocation. It enhances the operational performance and economy of ships, providing a more intelligent and efficient solution for the energy management of marine hybrid power systems. Attached Figure Description

[0054] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0055] Figure 1 The first embodiment of the present invention provides an overall flowchart of a marine hybrid power energy management method based on the MOEAD algorithm;

[0056] Figure 2 The first embodiment of the present invention provides a marine hybrid power system structure and system energy flow diagram under different operating modes for a certain type of ship diesel-electric hybrid power system based on the MOEAD algorithm energy management method;

[0057] Figure 3 A flowchart of the MOEAD algorithm for a marine hybrid power energy management method based on the MOEAD algorithm, provided for the first embodiment of the present invention;

[0058] Figure 4 This is a diagram showing fuel consumption and emissions under the Pareto optimal solution of a marine hybrid power energy management method based on the MOEAD algorithm, provided in the second embodiment of the present invention. Detailed Implementation

[0059] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0060] Example 1

[0061] Reference Figures 1-3 As an embodiment of the present invention, a marine hybrid power energy management method based on the MOEAD algorithm is provided, comprising:

[0062] S1: Build a model of a marine diesel-electric hybrid power system.

[0063] To study marine hybrid power systems, a suitable system model is needed. A steady-state modeling approach is adopted, modeling based on the operating mechanism of the model objects, ignoring transient behavior. This model includes the diesel engine, electric motor, lithium battery, parallel gearbox, diesel generator, and ship. Energy flow between the models can be referenced... Figure 2 .

[0064] S2: Determine the decision variables for optimizing the hybrid power system.

[0065] There are 6 decision variables in this optimization problem of the series-parallel hybrid power system, including the design operating power P of diesel generator 1. gen1opt The diesel generator 2 is designed to have a working power P. gen2opt Battery SOC upper and lower ranges up and SOC down Diesel engine design operating torque T eopt and motor design working torque T m_opt_max .

[0066] S3: Use the MOEAD algorithm to perform multi-objective optimization of fuel consumption and emissions of hybrid power systems.

[0067] (1) Subproblem weight vector assignment: Each subproblem is assigned a population individual, and these individuals also have corresponding weight vectors. For each weight vector, the elements in the vector must satisfy the condition that they are greater than or equal to 0 and their sum is 1. For a multi-objective optimization problem with two objectives, the weight vector of the i-th population individual... It can be represented as:

[0068]

[0069] in, This represents the j-th element of the weight vector for the i-th subproblem, where i = 1, ..., P. size ;P size Indicates the population size.

[0070] (2) Determine the neighboring weight vectors of each weight vector: A characteristic of decomposition-based multi-objective optimization algorithms is the need to find the neighboring weight vectors of each weight vector for differential evolution operations. Neighborhood can be defined by the Euclidean distance between weight vectors, as shown in the following formula for weight vector λ. i and weight vector λ j Euclidean distance d ij The number of adjacent weight vectors is a manually defined parameter in the MOEAD algorithm. For example, if we need to find T adjacent weight vectors... Then the neighborhood of each weight vector is the set of indices of the T nearest weight vectors to that vector, defined as Nh. i ={i1,i2,...,i T};

[0071]

[0072] (3) Initialize the population and target vector values: The simplest way to initialize the population is to randomly select values ​​for the decision variables within the feasible region based on the number of individuals in the population, assuming that all randomly initialized populations conform to a uniform probability distribution. Let the lower bound of the decision variables be... Let the upper bound of the decision variable be... The size of the j-th decision variable in the i-th initial population can be expressed as:

[0073]

[0074] Where rand[0,1] represents a uniform random number between 0 and 1; k represents the number of decision variables.

[0075] After obtaining the initial population, assuming the number of decision variables is M, the objective function vector is obtained by inputting the decision variable values ​​of each individual into the multi-objective optimization problem, as follows:

[0076] V i =OF(x i )

[0077] Where, x i V represents a real-valued parameter vector of dimension M for the i-th individual in the population; OF represents a multi-objective function; V i This represents the target vector value of the i-th individual in the population.

[0078] (4) Initialize reference points: Use aggregation functions to update the reference point information needed by the neighbor solutions. The theoretical reference point vector z *It consists of the minimum values ​​of the objective functions of all solutions in the solution set, which are difficult to obtain in practice. Therefore, a reference point vector z, composed of the minimum values ​​of the objective functions of the initial population, can be used to replace z. * z can be calculated using the following formula:

[0079]

[0080] z = (z1, ..., z M ) T

[0081] (5) Use the adaptive differential evolution algorithm for crossover and mutation: from the neighborhood Nh i ={i1,i2,...,i T Arbitrarily select three individuals from the population with different superscripts and perform differential evolution. Based on the principle of the differential evolution algorithm, the resulting mutation vector can be obtained by the following formula:

[0082]

[0083] Where, η i Gen+1 Represents the offspring vector resulting from the mutation; i a i b i c Indicates from the neighborhood Nh i Three weight vector indices are randomly selected, where a, b, c and weight vector index i are all different; F represents the mutation operator.

[0084] When the mutation operator has a fixed value, if it is too large, the algorithm's search efficiency deteriorates, and the accuracy of the obtained global optimum is low; if it is too small, the population diversity decreases, and the algorithm is prone to getting trapped in local optima. Therefore, the mutation operator needs to change accordingly with the number of algorithm iterations. It should maintain a large value in the early stages to improve population diversity, and gradually decrease in the later stages to improve algorithm efficiency and the accuracy of the global optimum. Specifically, the size of the mutation operator is expressed as follows:

[0085] F' = F0 × 2 λ

[0086]

[0087] Where F0 represents the initial mutation operator; Gen max Indicates the maximum number of iterations; F' is the adaptive mutation operator.

[0088] In addition to mutation, crossover is also necessary to increase population diversity. The specific steps are as follows:

[0089] ζ i Gen+1=(ζ i 1,Gen+1 ,..,ζ i k,Gen+1 )

[0090]

[0091] Where, ζ i Gen+1 represents the weight vector obtained after crossover; k represents the number of decision variables; CR represents the crossover operator; randb(j) represents the j-th random number generated by a random number generator from 0 to 1; rnbr(j) represents the j-th random number generated by a random integer generator from 0 to M.

[0092] It should be noted that, in addition to using a single differential evolution algorithm to generate new individuals, Gaussian mutation can also be combined to improve the algorithm's local search capability.

[0093] (6) Selection and Boundary Absorption Processing: The weight vector after mutation and crossover needs to be compared with the weight vector of the current population. The weight vector with the smallest objective function value becomes the new individual in the population. To ensure the weight vector ζ i The elements are located within the feasible region of the multi-objective problem. All parameter values ​​outside the feasible region are set to the nearest upper or lower boundary values ​​to obtain the corrected ζ. i' .

[0094] (7) Update reference point z and population: update the corrected ζ i' If equation (1) holds true, then the reference point z is updated according to equation (2).

[0095]

[0096] z j =f j (ζ i' (2)

[0097] For any i∈Nh i ={i1,i2,...,i T If equation (3) holds, then update the population individuals and objective function vectors according to equations (4) and (5).

[0098] g te (ζ i' |λ i ,z)≤g te (x i |λ i ,z) (3)

[0099] x i =ζ i' (4)

[0100] V i =OF(ζ i' (5)

[0101] Among them, g te This represents the Chebyshev formula.

[0102] (8) Update the output population: Remove the population affected by OF(ζ) from the optimal solution set. i' If the output solution set does not have a dominant objective function vector, OF(ζ) i' The objective function vector of OF(ζ) i' The objective function vector is the vector representing the optimal solution. After the termination iteration condition is met, the output is the Pareto optimal solution.

[0103] It should be noted that fuel consumption can be obtained by integrating the instantaneous e-liquid consumption rate over time, expressed as:

[0104]

[0105] Among them, g gen_de1_ins This represents the instantaneous fuel consumption rate (g / s) of diesel generator 1; g gen_de2_ins This indicates the instantaneous fuel consumption rate (g / s) of the diesel generator 2; g e_ins G represents the instantaneous fuel consumption rate of the diesel engine (g / s); G represents the total fuel consumption (kg).

[0106] Greenhouse gas emissions can be calculated using the following formula:

[0107] EM = (E gen_de1 +E gen_de2 +E e )EM fuel +E b EM ele

[0108] Where EM represents total greenhouse gas emissions (kg); E gen_de1 E represents the energy consumed by diesel generator 1 (kW·h); gen_de2 This indicates the energy consumed by diesel generator 2 (kW·h); EM fuel E represents the carbon dioxide emissions per kilowatt-hour produced by a diesel engine (kg / (kW·h)); b E represents the energy consumed by the battery (kW·h). e This indicates the energy consumed by the diesel engine (kW·h); EM ele This indicates the amount of carbon dioxide emissions generated per kilowatt-hour of shore power (kg / (kW·h)).

[0109] The above embodiments also include a marine hybrid power energy management system based on the MOEAD algorithm, specifically:

[0110] Model building module: Builds a model of a marine diesel-electric hybrid power system;

[0111] Decision variable determination module: Determines the decision variables for optimizing the hybrid power system;

[0112] MOEAD Algorithm Module: Uses the MOEAD algorithm to perform multi-objective optimization of fuel consumption and emissions in hybrid power systems.

[0113] The computer device can be a server. This computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores data cluster data from the power monitoring system. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network. When the computer program is executed by the processor, it implements a marine hybrid power energy management method based on the MOEAD algorithm.

[0114] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0115] Example 2

[0116] refer to Figure 3 As an embodiment of the present invention, a marine hybrid power energy management method based on the MOEAD algorithm is provided. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation / comparative experiments.

[0117] There are 6 decision variables in this optimization problem of the series-parallel hybrid power system, including the design operating power P of diesel generator 1. gen1opt The diesel generator 2 is designed to have a working power P. gen2opt Battery SOC upper and lower ranges up and SOC down Diesel engine design operating torque T eoptand motor design working torque T m_opt_max Table 1 shows the parameter settings for the MOEAD algorithm, where the number of iterations is 60, the population size is 20, and the number of neighbor weight vectors is 4.

[0118] Table 1. Genetic Algorithm Parameter Settings

[0119] Number of iterations 60 Number of objective functions 2 Population size 20 Decision variables 6 Number of neighbor weight vectors 6

[0120] refer to Figure 3 , is the size of the objective function under the 20 Pareto optimal solutions obtained through calculation.

[0121] Table 2 can also be consulted:

[0122] Table 2. Reference table for the magnitude of decision variables under Pareto optimal solution.

[0123]

[0124] It can be seen that using the MOEAD algorithm can reduce fuel consumption and emissions by 2.23% and 0.92% respectively for a parallel hybrid power system based on a logic threshold energy management strategy compared to an unoptimized system.

[0125] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A marine hybrid power energy management method based on the MOEAD algorithm, characterized in that, include: Build a model of a marine diesel-electric hybrid power system; Determine the decision variables for optimizing the hybrid power system; The MOEAD algorithm is used to perform multi-objective optimization of fuel consumption and emissions of hybrid power systems. The construction of the ship diesel-electric hybrid power system model includes the use of a steady-state modeling method, which models the system based on the operating mechanism of the model objects, including a diesel engine model, an electric motor model, a lithium battery model, a parallel gearbox model, a diesel generator model, and a ship model. The decision variables for determining the optimization of the hybrid power system include the design operating power of diesel generator 1. Diesel generator 2 design operating power upper and lower ranges of battery SOC and Diesel engine design operating torque and motor design operating torque .

2. The marine hybrid power energy management method based on the MOEAD algorithm as described in claim 1, characterized in that: The MOEAD algorithm includes: assigning weight vectors to subproblems, determining adjacent weight vectors for each weight vector, initializing the population and target vector values, initializing reference points, performing crossover, mutation, selection, and boundary absorption using an adaptive differential evolution algorithm, updating the reference points and population, and updating the output population.

3. The marine hybrid power energy management method based on the MOEAD algorithm as described in claim 2, characterized in that: The assignment of weight vectors to subproblems includes assigning a population individual to each subproblem, and each population individual also has a corresponding weight vector. For each weight vector, the elements in the vector must satisfy the condition that they are greater than or equal to 0 and their sum is 1. For a multi-objective optimization problem with two objectives, the th... The weight vector of each individual in the population Represented as: in, Indicates the first The weight vector of the sub-problem One element, =1,…, ; Indicates population size; Determining the neighboring weight vectors of each weight vector includes defining them using the Euclidean distance between them, denoted as: Represents the weight vector and weight vector European distance ; The initialization of the population and target vector values ​​includes setting the lower bound of the decision variables as follows: Let the upper bound of the decision variable be... Then the first The first individual in the initial population The size of each decision variable is represented as follows: in, Represents a uniformly random number between 0 and 1; Indicates the number of decision variables; After obtaining the initial population, assume the number of decision variables is... To input the decision variable values ​​of each individual into the multi-objective optimization problem, we obtain the objective function vector, represented as: in, Indicates the first The individual dimension value of each population is: The real-valued parameter vector; Represents a multi-objective function; Indicates the first The target vector value of each individual in the population.

4. The marine hybrid power energy management method based on the MOEAD algorithm as described in claim 3, characterized in that: The initialization reference points include a reference point vector composed of the minimum values ​​of the objective function of the initialization population. To replace the theoretical reference point vector , It can be calculated using the following formula: The use of adaptive differential evolution algorithm for crossover and mutation includes, from the neighborhood... By arbitrarily selecting three individuals from the population with different superscripts and performing differential evolution, the resulting mutation vector, based on the principles of the differential evolution algorithm, is obtained by the following formula: in, Represents the offspring vector produced by the mutation; , , Indicates from the neighborhood Three weight vector indices are randomly selected from the data, among which... , , and weight vector index They are all different; Represents the mutation operator; The size of the specific mutation operator is expressed as follows: in, Represents the initial mutation operator; Indicates the maximum number of iterations; Adaptive mutation operator; In addition to mutation, crossover is also necessary to increase population diversity. The specific steps are as follows: in, This represents the weight vector obtained after the crossover. Indicates the number of decision variables; Represents the crossover operator; The first number represents the random number generator between 0 and 1. A random number; Represents 0 to The first random integer generator A random number; The selection and boundary absorption process includes comparing the weight vector after mutation and crossover with the weight vector of the current population. The weight vector with the smallest objective function value becomes the new individual in the population. To ensure the weight vector... The elements are located within the feasible region of the multi-objective problem. All parameter values ​​outside the feasible region are set to the nearest upper or lower boundary values ​​to obtain the corrected values. .

5. The marine hybrid power energy management method based on the MOEAD algorithm as described in claim 4, characterized in that: The updated reference point and population include the corrected... If equation (1) holds true when substituted into the objective function, then the reference point is updated according to equation (2). : （1） （2） For any If equation (3) holds, then update the population individuals and the objective function vector according to equations (4) and (5): （3） （4） （5） in, This represents Chebyshev's formula; The updated output population includes removing the best solution set from the optimal solution set. If the target function vector is dominated, and the output solution set does not have a dominant function vector, then... If the objective function vector is , then The objective function vector of the optimal solution, after satisfying the termination iteration condition, outputs the Pareto optimal solution.

6. A marine hybrid power energy management system based on the MOEAD algorithm, employing the method described in any one of claims 1-5, characterized in that, include: Model building module: Builds a model of a marine diesel-electric hybrid power system; Decision variable determination module: Determines the decision variables for optimizing the hybrid power system; MOEAD Algorithm Module: Uses the MOEAD algorithm to perform multi-objective optimization of fuel consumption and emissions in hybrid power systems.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images