Ship power system optimization scheduling method and system based on genetic algorithm

Abstract

The invention discloses a ship power system optimization scheduling method and system based on a genetic algorithm, and relates to the technical field of ship power control, and the method comprises the steps: obtaining real-time operation parameters of a ship power system, building an initial population of the genetic algorithm based on the operation parameters, and carrying out the optimization scheduling of the ship power system based on an energy consumption characteristic index and an emission characteristic index. And calculating the comprehensive fitness value of each individual, performing selection operation, interlace operation and mutation operation on the initial population to generate a new population, repeatedly performing population iterative optimization until a preset condition is met, outputting a navigational speed adjustment parameter combination, a generator set start-stop decision sequence and a power distribution scheme, and generating a ship power system control instruction set. According to the ship power system optimization scheduling method and system based on the genetic algorithm provided by the invention, the operation efficiency of the ship power system is improved, the energy consumption is reduced, and the carbon emission is reduced.

Description

Technical Field

[0001] The present application relates to the field of ship power control technology, and in particular to a ship power system optimization scheduling method and system based on genetic algorithm. Background Art

[0002] At present, most ship power control uses traditional controllers and fixed strategies, mainly controlling power output by adjusting a single parameter such as the amount of fuel. This method has obvious shortcomings on hybrid ships that need to use fuel generators and batteries at the same time: first, it is difficult to balance fuel saving and environmental protection, and one is often lost for the other; second, when encountering complex situations such as wind and waves, fixed control rules will lead to unstable power output, which is easy to cause increased equipment wear and energy waste.

[0003] Existing optimization technologies have weak comprehensive analysis capabilities for multiple data such as generator power, battery status, and propeller load. Although some studies have tried to use genetic algorithms for optimization, they often only focus on a single goal of saving fuel or reducing emissions, and the optimization strategy remains fixed. This results in the ship not being able to prioritize saving fuel when the battery is low, and not being able to quickly turn to reduce emissions when encountering sudden winds and waves, making it difficult to improve overall operating efficiency. Summary of the invention

[0004] In order to overcome the above-mentioned deficiencies of the prior art, the present application provides a system and method for displaying user interface layout information based on the Hongmeng system.

[0005] In a first aspect, the present application provides a method for optimizing the scheduling of a ship power system based on a genetic algorithm, the method comprising:

[0006] Obtain the real-time operating parameters of the ship's power system, including the main engine speed data, the output power data of the generator set, the remaining power data of the energy storage battery, and the load characteristic data of the propeller;

[0007] An initial population of the genetic algorithm is constructed based on the operating parameters, and each individual in the initial population includes the genetic coding of the speed regulation parameters, the generator set start-stop decision parameters and the power allocation ratio parameters;

[0008] Based on the energy consumption characteristic index and the emission characteristic index, the comprehensive fitness value of each individual is calculated, wherein the weight coefficient corresponding to the fusion energy consumption characteristic index is associated with the remaining power of the energy storage battery, and the weight coefficient corresponding to the emission characteristic index is associated with the fluctuation amplitude of the thruster load;

[0009] Performing selection, crossover and mutation operations on the initial population to generate a new population, wherein the mutation probability adopts an adaptive adjustment strategy based on the number of iterations;

[0010] Repeat the population iteration optimization until the preset conditions are met, output the combination of speed adjustment parameters, the start-stop decision sequence of the generator sets, and the power distribution plan, and generate the control instruction set for the ship power system.

[0011] Preferably, the value range of the speed adjustment parameter is determined according to the following formula:

[0012] V_min = V_base × (1 - |n - n_rated| / n_rated)

[0013] V_max = V_base × (1 + P_load / P_rated)

[0014] where, V_base is the reference speed adjustment range, P_load is the real-time load power of the propeller, and P_rated is the rated power of the propeller;

[0015] Encode the start-stop decision parameters of the generator sets into binary gene bits, where the value of 0 represents the shutdown state and the value of 1 represents the running state;

[0016] Determine the encoding range of the power distribution ratio according to the rated power parameters of each generator set, where the power distribution ratio needs to meet the following constraints:

[0017] Σα_i = 1, and α_i ≥ P_min_i / P_total

[0018] where, α_i is the power distribution ratio of the i-th generator set, P_min_i is its minimum allowable output power, and P_total is the total load demand.

[0019] Preferably, calculate the comprehensive fitness value through the following formula:

[0020] F = W1 × I1 + W2 × I2

[0021] where, I1 is the energy consumption characteristic index, I2 is the emission characteristic index, W1 is the weight coefficient of the energy consumption characteristic index, and W2 is the weight coefficient of the emission characteristic index.

[0022] Preferably, multiply the real-time output power value of each generator set by the corresponding unit power fuel consumption coefficient to obtain the fuel consumption; multiply the start-stop times of each generator set by the single start-stop loss coefficient to obtain the equipment loss; add the fuel consumption and the equipment loss to obtain the energy consumption characteristic index;

[0023] Multiply the real-time output power value of each generator set by the corresponding unit power carbon emission coefficient to obtain the total carbon emission; divide the measured noise value in the propeller area by the maximum noise limit to obtain the noise pollution index; multiply the total carbon emission by the noise pollution index to obtain the emission characteristic index.

[0024] Preferably, when the remaining power of the energy storage battery is lower than a preset safety threshold, the weight coefficient of the energy consumption characteristic index is increased;

[0025] When the fluctuation amplitude of the thruster load exceeds the historical average fluctuation range, the weight coefficient of the emission characteristic index is increased.

[0026] Preferably, the mutation probability of the current iteration cycle is calculated by the following formula:

[0027] P_m = P_b × exp(-G / G_max) + (σ_F / μ_F) × (1 - G / G_max)

[0028] where P_m represents the mutation probability, P_b is the basic mutation probability parameter, G is the current iteration number, G_max is the maximum iteration number, σ_F is the standard deviation of the population fitness value, and μ_F is the fitness mean;

[0029] According to the mutation probability, mutation operations are performed on the individuals in the population. Among them, the mutation operations include applying random perturbations to the ship speed adjustment parameters, flipping the states of the generator set start-stop decision parameters, and reallocating the power distribution ratio parameters.

[0030] Preferably, a digital twin simulation model of the ship power system is established, and the ship power system control instruction set is input into the digital twin model for virtual operation;

[0031] The power volatility rate and voltage deviation rate indexes during the virtual operation process are monitored in real time. When the power volatility rate exceeds the first preset value or the voltage deviation rate exceeds the second preset value, an optimization parameter reset mechanism is triggered;

[0032] The execution process of the optimization parameter reset mechanism includes regenerating the initial population individuals, adjusting the calculation parameters of the mutation probability, and restarting the genetic algorithm optimization process.

[0033] Preferably, a multi-ship collaborative optimization database is established to store various typical navigation environment characteristic parameters and the corresponding optimal gene coding schemes;

[0034] The matching degree between the current navigation environment and historical cases is calculated through a feature similarity matching algorithm. When the similarity exceeds the third preset value, the gene coding of the corresponding historical case is loaded as the initial population seed;

[0035] The historical gene coding is adjusted adaptively by using a parameter normalization processing method to make it conform to the power system parameter range of the current ship.

[0036] In a second aspect, an optimization scheduling system for a ship power system based on a genetic algorithm includes:

[0037] An operating parameter acquisition unit for acquiring real-time operating parameters of a ship power system, where the operating parameters include main engine speed data, output power data of a generator set, remaining power data of an energy storage battery, and load characteristic data of a thruster;

[0038] A gene encoding unit for constructing an initial population of a genetic algorithm based on the operating parameters, where each individual in the initial population includes gene encodings of speed adjustment parameters, generator set start-stop decision parameters, and power distribution ratio parameters;

[0039] A comprehensive fitness value calculation unit for calculating the comprehensive fitness value of each individual based on energy consumption characteristic indicators and emission characteristic indicators, where the weight coefficient corresponding to the integrated energy consumption characteristic indicator is associated with the remaining power of the energy storage battery, and the weight coefficient corresponding to the emission characteristic indicator is associated with the load fluctuation range of the thruster;

[0040] A population generation unit for performing selection operations, crossover operations, and mutation operations on the initial population to generate a new population, where the mutation probability adopts an adaptive adjustment strategy based on the number of iterations;

[0041] An instruction set generation unit for repeatedly performing population iterative optimization until a preset condition is met, outputting a speed adjustment parameter combination, a generator set start-stop decision sequence, and a power distribution plan, and generating a control instruction set for the ship power system.

[0042] Compared with the prior art, the present invention has the following features and beneficial effects:

[0043] First, by acquiring multi-source operating parameters of the ship power system in real time, the real-time state of the ship power system is comprehensively perceived, providing accurate data support for optimal scheduling. Then, a multi-dimensional initial population including speed adjustment, unit start-stop, and power distribution is constructed based on the genetic algorithm, breaking through the rigidity of the fixed rule strategy, improving the search efficiency of the solution space, and avoiding falling into local optima. Further, by dynamically weighting and fusing the dual indicators of energy consumption and emissions, an intelligent balance of multi-objective conflicts is achieved, improving fuel efficiency and reducing carbon emissions. Next, combined with the adaptive mutation probability adjustment strategy, global search and local convergence are effectively balanced, the algorithm iteration speed is increased, and the optimization stability is enhanced, so that a reliable scheduling plan can be quickly generated under complex sea conditions, reducing equipment losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is a block diagram of the steps of an optimization scheduling method for a ship power system based on a genetic algorithm mainly embodied in this embodiment.

[0045] Figure 2 is a block diagram of the structure of an optimization scheduling system for a ship power system based on a genetic algorithm mainly embodied in this embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0046] The present invention will be further described in detail below in conjunction with the following embodiments.

[0047] Referring to Figure 1 , an optimized scheduling method for a ship power system based on a genetic algorithm, the method comprising the following steps:

[0048] S1. Obtain the real-time operation parameters of the ship power system, where the operation parameters include main engine speed data, output power data of the generator set, remaining power data of the energy storage battery, and load characteristic data of the propeller.

[0049] S2. Construct an initial population of the genetic algorithm based on the operation parameters, and each individual in the initial population includes gene encodings of speed adjustment parameters, generator set start-stop decision parameters, and power distribution ratio parameters.

[0050] S3. Calculate the comprehensive fitness value of each individual based on the energy consumption characteristic index and the emission characteristic index, where the weight coefficient corresponding to the integrated energy consumption characteristic index is associated with the remaining power of the energy storage battery, and the weight coefficient corresponding to the emission characteristic index is associated with the load fluctuation range of the propeller.

[0051] S4. Perform selection operation, crossover operation, and mutation operation on the initial population to generate a new population, where the mutation probability adopts an adaptive adjustment strategy based on the number of iterations.

[0052] S5. Repeat the population iteration optimization until the preset conditions are met, output the speed adjustment parameter combination, generator set start-stop decision sequence, and power distribution plan, and generate a control instruction set for the ship power system.

[0053] First, by obtaining the multi-source operation parameters of the ship power system in real time, the real-time state of the ship power system is comprehensively perceived, providing accurate data support for optimized scheduling. Then, based on the genetic algorithm, a multi-dimensional initial population including speed adjustment, unit start-stop, and power distribution is constructed, breaking through the rigidity of the fixed rule strategy, improving the search efficiency of the solution space, and avoiding falling into local optima. Further, by dynamically weighting and fusing the dual indicators of energy consumption and emissions, the intelligent balance of multi-objective conflicts is achieved, improving fuel efficiency and reducing carbon emissions. Then, combined with the adaptive mutation probability adjustment strategy, the global search and local convergence are effectively balanced, the algorithm iteration speed is increased, and the optimization stability is enhanced, so that a reliable scheduling plan can be quickly generated under complex sea conditions, reducing equipment loss.

[0054] Specifically, the process of step S1 can be as follows: The rotational speed signal is collected in real time by a rotational speed sensor installed on the main engine shafting. After being filtered and amplified by a signal conditioning circuit, this signal is converted into a digital signal by a data acquisition card and transmitted to the central processor. The output power data of the generator set is obtained from the generator set controller through a bus, and the sampling frequency is 10 Hz. The remaining power data of the energy storage battery is obtained through the estimation algorithm of the battery management system (BMS), and this algorithm is based on the combination of the ampere-hour integration method and the open-circuit voltage method. The propeller load characteristic data includes torque signals and vibration signals, which are collected by a flange-type torque sensor and an acceleration sensor respectively, and the sampling frequency is 1 kHz. These operating parameters provide comprehensive system status information for subsequent optimal scheduling.

[0055] Specific step S2 includes the following sub-steps:

[0056] Determine the value range of the ship speed adjustment parameter according to the following formula:

[0057] V_min = V_base × (1 - |n - n_rated| / n_rated)

[0058] V_max = V_base × (1 + P_load / P_rated)

[0059] Where, V_base is the reference ship speed adjustment range, P_load is the real-time load power of the propeller, and P_rated is the rated power of the propeller;

[0060] Encode the generator set start-stop decision parameter into a binary gene bit, where the value of 0 represents the shutdown state and the value of 1 represents the operating state;

[0061] Determine the encoding range of the power distribution ratio according to the rated power parameters of each generator set, and the power distribution ratio needs to meet the following constraint conditions:

[0062] Σα_i = 1, and α_i ≥ Pmin_i / P_total

[0063] Where, α_i is the power distribution ratio of the i-th generator set, P_min_i is its minimum allowable output power, and P_total is the total load demand.

[0064] Specifically, the dynamic adjustment mechanism can effectively reflect the real-time matching relationship between the host operating state and the load demand. For example, when the host speed approaches the rated value, the speed adjustment range tends to be stable, avoiding infeasible solutions caused by speed deviation; when the load power of the thruster increases significantly, the upper speed limit expands accordingly to meet the power demand under high-load conditions. In addition, the power distribution ratio needs to satisfy the sum constraint (Σα_i = 1) and the lower limit constraint (α_i ≥ P_min_i / P_total), ensuring that the output power of each generator set meets the total load demand and avoids being lower than the minimum stable operation threshold. The mathematical expression of such constraint conditions directly embeds the physical limitations of the equipment into the encoding process of the genetic algorithm, significantly reducing the generation probability of invalid solutions. The start-stop decision parameters of the generator sets are encoded in binary, and Gray code design is introduced. The characteristic that only one bit differs between adjacent values can reduce the mutation amplitude during genetic operations (such as crossover or mutation), thereby enhancing the smooth search ability of the algorithm in the solution space. Through the comprehensive application of dynamic parameter range adjustment, physical constraint embedding, and anti-noise coding design, the proportion of feasible solutions in the initial population is significantly increased, and the convergence speed and stability of the algorithm under complex working conditions are optimized doubly, laying a high-quality search starting point for subsequent iterations.

[0065] Specifically, step S3 includes the following sub-steps:

[0066] Calculate the comprehensive fitness value through the following formula:

[0067] F = W1 × I1 + W2 × I2

[0068] Where, I1 is the energy consumption characteristic index, I2 is the emission characteristic index, W1 is the weight coefficient of the energy consumption characteristic index, and W2 is the weight coefficient of the emission characteristic index.

[0069] Multiply the real-time output power value of each generator set by the corresponding unit power fuel consumption coefficient to obtain the fuel consumption; multiply the start-stop times of each generator set by the single start-stop loss coefficient to obtain the equipment loss; add the fuel consumption and the equipment loss to obtain the energy consumption characteristic index;

[0070] Multiply the real-time output power value of each generator set by the corresponding unit power carbon emission coefficient to obtain the total carbon emissions; divide the measured noise value in the thruster area by the maximum noise limit to obtain the noise pollution index; multiply the total carbon emissions by the noise pollution index to obtain the emission characteristic index.

[0071] When the remaining power of the energy storage battery is lower than the preset safety threshold, increase the weight coefficient of the energy consumption characteristic index;

[0072] When the fluctuation amplitude of the thruster load exceeds the historical average fluctuation range, increase the weight coefficient of the emission characteristic index.

[0073] Specifically, first calculate the fuel consumption based on the real-time output power value of the generator set and the corresponding fuel consumption coefficient per unit power, where the fuel consumption coefficient per unit power is obtained by looking up the engine characteristic curve; then multiply the start-stop times of the generator set by the single start-stop loss coefficient to obtain the equipment loss amount, and this loss coefficient takes into account the thermal fatigue and mechanical wear of the unit; finally, add the fuel consumption and the equipment loss amount to obtain the energy consumption characteristic index. The calculation process of the emission characteristic index I2 includes: first calculate the total carbon emissions based on the real-time output power value of the generator set and the corresponding carbon emission coefficient per unit power, and the carbon emission coefficient takes into account the fuel type and combustion efficiency; then obtain the measured noise value in the thruster area and perform A-weighted filtering processing, divide it by the maximum allowable noise limit to obtain the noise pollution index; finally, multiply the total carbon emissions by the noise pollution index to obtain the emission characteristic index. The dynamic adjustment strategy of the weight coefficient is: when the remaining power of the energy storage battery is lower than the preset safety threshold, linearly increase the weight coefficient W1 of the energy consumption characteristic index; when the fluctuation range of the thruster load exceeds the historical average fluctuation range, use the Sigmoid function to smoothly increase the weight coefficient W2 of the emission characteristic index.

[0074] Specifically, step S4 includes the following sub-steps:

[0075] Calculate the mutation probability of the current iteration cycle through the following formula:

[0076] P_m = P_b × exp(-G / G_max) + (σ_F / μ_F) × (1 - G / G_max)

[0077] Where, P_m represents the mutation probability, P_b is the basic mutation probability parameter, G is the current iteration number, G_max is the maximum iteration number, σ_F is the standard deviation of the population fitness value, and μ_F is the fitness mean;

[0078] According to the mutation probability, perform mutation operations on the individuals in the population. Among them, the mutation operations include applying random perturbations to the speed regulation parameters, flipping the states of the generator set start-stop decision parameters, and reallocating the power distribution ratio parameters.

[0079] Specifically, this formula incorporates a dual feedback mechanism: the exponential decay term (exp(-G / G_max)) results in a relatively high initial mutation probability, promoting extensive exploration of the solution space; as the iteration progresses, the mutation probability gradually decreases to focus on local fine-tuning. Meanwhile, the fitness statistic compensation term (σ_F / μ_F) dynamically adjusts the mutation intensity according to the diversity of the population. When the population fitness tends to be consistent (σ_F is small), the mutation probability is increased to avoid premature convergence; conversely, it is decreased to maintain stability. In specific operations, the speed adjustment parameter adopts a Gaussian perturbation strategy, and the perturbation amplitude is proportional to the dynamic speed range, ensuring that the perturbation does not deviate excessively from the physical limit while effectively exploring potential optimization directions. The mutation probability of the generator set start-stop decision is positively correlated with the load volatility. When the thruster load changes drastically, the algorithm quickly responds to the dynamic working conditions by increasing the state flip probability. The power distribution ratio is redistributed through a differential evolution strategy, randomly adjusting the power of each unit while keeping the total unchanged, taking into account both global optimization and local adjustment. The comprehensive application of these technical solutions enables the algorithm to intelligently adjust the search strategy according to the iteration stage and environmental changes, avoiding being trapped in local optima and quickly converging when approaching the optimal solution. Through the deep integration of mathematical modeling and physical constraints, this solution significantly improves the efficiency and robustness of the optimal scheduling of the ship power system, providing a reliable technical guarantee for real-time control under complex sea conditions.

[0080] Specifically, the process of step S5 can be as follows: Set two termination conditions. The first is the convergence condition, which is determined to converge when the improvement amplitude of the fitness value of the optimal individual is less than 0.1% within 20 consecutive generations. The second is the maximum iteration number condition, which is set to 100 generations to ensure that the algorithm can be completed within a reasonable time. The output results include: the speed adjustment parameter combination, which is the speed change curve in the next scheduling period (which can be 15 minutes); the generator set start-stop decision sequence, which determines the start-stop time points of each unit in the next scheduling period; and the power distribution plan, which gives the specific power output values of each unit during the operation period. These parameters are transmitted to each actuator through the communication interface of the ship control system.

[0081] In some embodiments, the optimal scheduling method for a ship power system based on a genetic algorithm may further include the following steps:

[0082] Establish a digital twin simulation model of the ship power system, and input the ship power system control instruction set into the digital twin model for virtual operation;

[0083] Real-time monitor the power volatility and voltage deviation rate indicators during the virtual operation process. When the power volatility exceeds the first preset value or the voltage deviation rate exceeds the second preset value, trigger the optimization parameter reset mechanism;

[0084] The execution process of the optimization parameter reset mechanism includes regenerating the initial population individuals, adjusting the calculation parameters of the mutation probability, and restarting the genetic algorithm optimization process.

[0085] Specifically, the digital twin simulation model is constructed based on multi-body dynamics and power system simulation technology, and includes a main engine dynamics model, a dynamic characteristic model of the generator set, an equivalent circuit model of the energy storage battery, and a hydrodynamic model of the thruster. The power volatility is obtained by calculating the standard deviation of the power within a 1-second time window, and the voltage deviation rate is obtained by monitoring the percentage deviation of the bus voltage from the rated value. When any index exceeds the threshold (power volatility 5%, voltage deviation rate 3%), the optimization parameter reset mechanism will increase the initial population size by 20%, increase the basic mutation probability Pb by 50%, and retain the current optimal individual directly into the new generation population.

[0086] In some embodiments, the optimization scheduling method for a ship power system based on a genetic algorithm may further include the following steps:

[0087] Establish a multi-ship collaborative optimization database to store various typical navigation environment characteristic parameters and corresponding optimal gene coding schemes;

[0088] Calculate the matching degree between the current navigation environment and historical cases through a feature similarity matching algorithm. When the similarity exceeds the third preset value, load the gene coding of the corresponding historical case as the initial population seed;

[0089] Adopt a parameter normalization processing method to adaptively adjust the historical gene coding to make it conform to the power system parameter range of the current ship.

[0090] Specifically, the multi-ship collaborative optimization database uses a time-series database to store historical case data. Each case includes environmental characteristic parameters (such as wind speed, wave height, water flow velocity), ship state parameters (such as displacement, draft), and corresponding optimal gene coding. The feature similarity matching algorithm uses the Euclidean distance to calculate the similarity between the current environmental feature vector and historical cases. When the similarity exceeds 0.8, the historical optimal gene coding is used as the initial population seed. The parameter normalization processing includes: the normalization of the ship speed parameter is based on the Froude number similarity criterion; the normalization of the power distribution parameter is based on the percentage conversion of the rated power of the unit; the start-stop decision parameter directly inherits the start-stop mode of the same type of unit in the historical scheme.

[0091] An optimization scheduling system for a ship power system based on a genetic algorithm, by applying an optimization scheduling method for a ship power system based on a genetic algorithm as described above, includes an operating parameter acquisition unit, a gene coding unit, a comprehensive fitness value calculation unit, a population generation unit, and an instruction set generation unit, referring to Figure 2, the operating parameter acquisition unit is used to acquire the real-time operating parameters of the ship power system, and the operating parameters include the main engine speed data, the output power data of the generator set, the remaining power data of the energy storage battery, and the load characteristic data of the thruster; the gene encoding unit constructs the initial population of the genetic algorithm based on the operating parameters, and each individual in the initial population includes the gene encoding of the ship speed adjustment parameter, the generator set start-stop decision parameter, and the power distribution ratio parameter; the comprehensive fitness value calculation unit calculates the comprehensive fitness value of each individual based on the energy consumption characteristic index and the emission characteristic index, wherein the weight coefficient corresponding to the integrated energy consumption characteristic index is associated with the remaining power of the energy storage battery, and the weight coefficient corresponding to the emission characteristic index is associated with the load fluctuation range of the thruster; the population generation unit performs selection operation, crossover operation and mutation operation on the initial population to generate a new population, wherein the mutation probability adopts an adaptive adjustment strategy based on the number of iterations; the instruction set generation unit repeats the population iteration optimization until the preset condition is met, outputs the ship speed adjustment parameter combination, the generator set start-stop decision sequence and the power distribution plan, and generates the control instruction set of the ship power system.

[0092] The above are all the preferred embodiments of this application, and the protection scope of this application is not limited by this. Therefore, all equivalent changes made according to the structure, shape and principle of this application shall be covered within the protection scope of this application.

Claims

1. A method for optimizing the scheduling of a ship power system based on a genetic algorithm, characterized in that, Including the following steps: Obtain the real-time operation parameters of the ship power system, where the operation parameters include the main engine speed data, the output power data of the generator set, the remaining power data of the energy storage battery, and the load characteristic data of the thruster; Construct an initial population of the genetic algorithm based on the operation parameters, where each individual in the initial population includes gene encodings of the ship speed adjustment parameter, the generator set start-stop decision parameter, and the power distribution ratio parameter; Calculate the comprehensive fitness value of each individual based on the energy consumption characteristic index and the emission characteristic index, where the weight coefficient corresponding to the integrated energy consumption characteristic index is associated with the remaining power of the energy storage battery, and the weight coefficient corresponding to the emission characteristic index is associated with the load fluctuation range of the thruster; Perform selection operation, crossover operation, and mutation operation on the initial population to generate a new population, where the mutation probability adopts an adaptive adjustment strategy based on the number of iterations; Repeat the population iterative optimization until the preset condition is met, output the ship speed adjustment parameter combination, the generator set start-stop decision sequence, and the power distribution plan, and generate the control instruction set of the ship power system.

2. The optimized scheduling method for a ship power system based on a genetic algorithm according to claim 1, wherein The step of constructing an initial population of the genetic algorithm based on the operation parameters is specifically: Determine the value range of the ship speed adjustment parameter according to the following formula: V_min = V_base × (1 - |n - n_rated| / n_rated) V_max = V_base × (1 + P_load / P_rated) Where, V_base is the reference ship speed adjustment range, P_load is the real-time load power of the thruster, and P_rated is the rated power of the thruster; Encode the generator set start-stop decision parameter into binary gene bits, where the value of 0 represents the shutdown state and the value of 1 represents the running state; Determine the encoding range of the power distribution ratio according to the rated power parameters of each generator set, where the power distribution ratio needs to meet the following constraint conditions: Σαi = 1, and αi ≥ P_min_i / P_total Where, α_i is the power distribution ratio of the i-th generator set, P_min_i is its minimum allowable output power, and P_total is the total load demand.

3. A method for optimizing the scheduling of a ship power system based on a genetic algorithm according to claim 1, characterized in that The step of calculating the comprehensive fitness value of each individual based on the energy consumption characteristic index and the emission characteristic index is specifically: Calculate the comprehensive fitness value through the following formula: F = W1 × I1 + W2 × I2 Where, I1 is the energy consumption characteristic index, I2 is the emission characteristic index, W1 is the weight coefficient of the energy consumption characteristic index, and W2 is the weight coefficient of the emission characteristic index.

4. The optimization scheduling method for a ship power system based on a genetic algorithm according to claim 3, wherein Calculating the comprehensive fitness value of each individual based on the energy consumption characteristic index and the emission characteristic index further includes: Multiply the real-time output power value of each generator set by the corresponding unit power fuel consumption coefficient to obtain the fuel consumption; multiply the start-stop times of each generator set by the single start-stop loss coefficient to obtain the equipment loss; add the fuel consumption and the equipment loss to obtain the energy consumption characteristic index; Multiply the real-time output power value of each generator set by the corresponding unit power carbon emission coefficient to obtain the total carbon emission; divide the measured noise value in the thruster area by the maximum noise limit value to obtain the noise pollution index; multiply the total carbon emission by the noise pollution index to obtain the emission characteristic index.

5. The optimization scheduling method for a ship power system based on a genetic algorithm according to claim 4, characterized in that, The method further includes: When the remaining power of the energy storage battery is lower than a preset safety threshold, increase the weight coefficient of the energy consumption characteristic index; When the fluctuation range of the thruster load exceeds the historical average fluctuation range, increase the weight coefficient of the emission characteristic index.

6. The optimization scheduling method for a ship power system based on a genetic algorithm according to claim 1, characterized in that Among them, the steps of performing selection operation, crossover operation and mutation operation on the initial population to generate a new population are specifically: Calculate the mutation probability of the current iteration period through the following formula: P_m = P_b × e × p(-G / G_max) + (σ_F / μ_F) × (1 - G / G_max) Where, P_m represents the mutation probability, P_b is the basic mutation probability parameter, G is the current iteration number, G_max is the maximum iteration number, σ_F is the standard deviation of the population fitness value, and μ_F is the fitness mean value; According to the mutation probability, perform mutation operation on the individuals in the population. Among them, the mutation operation includes applying random perturbation to the ship speed adjustment parameter, performing state flipping on the generator set start-stop decision parameter, and reallocating the power distribution ratio parameter.

7. A method for optimizing the scheduling of a ship power system based on a genetic algorithm according to claim 1, characterized in that The method further includes: Establish a digital twin simulation model of the ship power system, and input the control instruction set of the ship power system into the digital twin model for virtual operation; Real-time monitor the power volatility and voltage deviation rate indicators during virtual operation. When the power volatility exceeds the first preset value or the voltage deviation rate exceeds the second preset value, trigger the optimization parameter reset mechanism; The execution process of the optimization parameter reset mechanism includes regenerating the initial population individuals, adjusting the calculation parameters of the mutation probability, and restarting the genetic algorithm optimization process.

8. The optimization scheduling method for a ship power system based on a genetic algorithm according to claim 1, characterized in that, The method further includes: Establish a multi-ship collaborative optimization database, and store various typical navigation environment characteristic parameters and the corresponding optimal gene coding schemes; Calculate the matching degree between the current navigation environment and historical cases through the feature similarity matching algorithm. When the similarity exceeds the third preset value, load the gene coding of the corresponding historical case as the initial population seed; Adopt the parameter normalization processing method to adaptively adjust the historical gene coding to make it conform to the power system parameter range of the current ship.

9. A ship power system optimal scheduling system based on genetic algorithm, characterized in that, The system is used to implement the genetic algorithm-based optimal scheduling method for ship power systems described in any one of claims 1-8, including: An operating parameter acquisition unit, configured to acquire the real-time operating parameters of the ship power system, and the operating parameters include main engine speed data, output power data of the generator set, remaining power data of the energy storage battery, and load characteristic data of the thruster; A gene coding unit, configured to construct an initial population of the genetic algorithm based on the operating parameters, and each individual in the initial population includes gene coding of ship speed adjustment parameters, generator set start-stop decision parameters, and power distribution ratio parameters. The comprehensive fitness value calculation unit is used to calculate the comprehensive fitness value of each individual based on the energy consumption characteristic index and the emission characteristic index, wherein the weight coefficient corresponding to the fused energy consumption characteristic index is associated with the remaining power of the energy storage battery, and the weight coefficient corresponding to the emission characteristic index is associated with the fluctuation range of the thruster load; The population generation unit is used to perform selection operation, crossover operation and mutation operation on the initial population to generate a new population, wherein the mutation probability adopts an adaptive adjustment strategy based on the number of iterations; The instruction set generation unit is used to repeatedly perform population iterative optimization until a preset condition is met, output the combination of ship speed adjustment parameters, the start-stop decision sequence of the generator set and the power distribution plan, and generate the control instruction set of the ship power system.

Images