Ship engine-propeller intelligent matching method and system based on multi-source fusion algorithm

Abstract

The invention relates to the technical field of ship propulsion system design, and particularly discloses a ship engine-propeller intelligent matching method and system based on a multi-source fusion algorithm, and the method comprises the steps: carrying out the optimization of a preset braking horsepower calculation rule based on ship related parameters, generating an optimized horsepower calculation rule, and carrying out the optimization of the optimized horsepower calculation rule; the method comprises the steps of optimizing a horsepower calculation rule, performing nonlinear coupling on the optimized horsepower calculation rule on the basis of an effective horsepower demand calculation rule to generate a coupled horsepower calculation rule, and finally performing host-propeller matching operation on the basis of a propeller map, ship design parameters, the coupled horsepower calculation rule and a matching horsepower coefficient to obtain a corresponding propeller model. The main engine-propeller matching operation is executed based on the propeller map, the ship design parameters, the coupled horsepower calculation rule and the matching horsepower coefficient, the corresponding propeller model is obtained, multi-model data fusion matching of the propeller model is achieved, and the propeller matching efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of ship propulsion system design, and particularly to a ship engine-propeller intelligent matching method and system based on a multi-source fusion algorithm. Background Art

[0002] The propulsion system of a ship is a key part in ship design, and its performance directly affects the navigation speed and economy of the ship. The matching of ship engine and propeller is an important link in the design of ship propulsion system. A reasonable matching of ship engine and propeller can improve the propulsion efficiency of the ship and reduce energy consumption. However, the existing ship engine-propeller matching technologies have the following problems:

[0003] 1. Strong dependence on experience: relying on a single formula or historical atlas, and not realizing the fusion of multi-model data.

[0004] 2. Poor dynamic adaptability: not considering the real-time influence of navigation conditions (such as wind and waves, load) on the matching effect.

[0005] 3. Low efficiency of atlas matching: large error and low efficiency in manual atlas search; the machine learning acceleration mechanism is not introduced in the iterative optimization process. Summary of the Invention

[0006] In order to overcome the above technical problems existing in the prior art, an embodiment of the present invention provides a ship engine-propeller intelligent matching method and system based on a multi-source fusion algorithm. By non-linearly coupling the optimized brake horsepower calculation rule and the effective horsepower demand calculation rule, a coupled brake horsepower calculation rule is generated, and based on the propeller atlas, the ship design parameters, the coupled brake horsepower calculation rule, and the matching horsepower coefficient, a main engine-propeller matching operation is performed to obtain the corresponding propeller model, realizing the fusion matching of multi-model data for the propeller model and improving the propeller matching efficiency.

[0007] In order to achieve the above object, an embodiment of the present invention provides a ship engine-propeller intelligent matching method based on a multi-source fusion algorithm, and the method includes:

[0008] Obtain ship design parameters and a preset brake horsepower calculation rule;

[0009] Optimize the preset brake horsepower calculation rule based on the ship design parameters to generate an optimized brake horsepower calculation rule;

[0010] Determine an effective horsepower demand calculation rule, and non-linearly couple the optimized brake horsepower calculation rule based on the effective horsepower demand calculation rule to generate a coupled brake horsepower calculation rule;

[0011] Obtain the performance parameters of the ship main engine, and determine the matching horsepower coefficient based on the performance parameters;

[0012] Obtain the propeller atlas, and perform the main engine - propeller matching operation based on the propeller atlas, the ship design parameters, the post - coupling horsepower calculation rule, and the matching horsepower coefficient to obtain the corresponding propeller model.

[0013] Preferably, optimizing the preset brake horsepower calculation rule based on the ship design parameters to generate an optimized horsepower calculation rule, including:

[0014] Determine the preset brake horsepower calculation rule, which is characterized as:

[0015]

[0016] Determine the hull resistance dynamic correction function based on the hull load and the wind - wave environment;

[0017] Optimize the preset brake horsepower calculation rule based on the hull resistance dynamic correction function to generate an optimized horsepower calculation rule, which is characterized as:

[0018]

[0019] Wherein, K represents the preset horsepower coefficient, Δ represents the ship design displacement, V represents the ship design speed, C represents the empirical constant, f(Rt,α) represents the hull resistance dynamic correction function, Rt represents the resistance correction amount, and α represents the real - time navigation state dynamic factor.

[0020] Preferably, the determination of the effective horsepower demand calculation rule includes:

[0021] Obtain the Hankel formula;

[0022] Determine the propeller thrust and torque based on the Hankel formula and the ship design speed;

[0023] Perform interpolation processing on the propeller thrust and the torque based on the propeller atlas to obtain the interpolated thrust T and the interpolated torque Q, and the interpolated thrust T and the interpolated torque Q are respectively characterized as: ,

[0024] Wherein, ρ represents the fluid density, n represents the propeller speed, D represents the propeller diameter, and J represents the advance coefficient, Determined in real - time matching based on the propeller atlas, K T represents the propeller thrust coefficient, K Q represents the propeller torque coefficient;

[0025] Generate an effective horsepower demand calculation rule based on the interpolated thrust T and the interpolated torque Q.

[0026] Preferably, the optimized horsepower calculation rule is non-linearly coupled based on the effective horsepower demand calculation rule to generate a coupled horsepower calculation rule, including:

[0027] Obtain the optimized horsepower calculation rule and the effective horsepower demand calculation rule;

[0028] Respectively obtain the dynamic weights of the optimized horsepower calculation rule and the effective horsepower demand calculation rule;

[0029] Based on the dynamic weights, the optimized horsepower calculation rule and the effective horsepower demand calculation rule, obtain the coupled horsepower calculation rule, and the coupled horsepower calculation rule is characterized as:

[0030]

[0031] where , T is the thrust after propeller interpolation, η prop is the propeller efficiency, determined by propeller diagram matching, , are the weights before adjustment.

[0032] Preferably, the performance parameters include the main engine speed, the main engine power, and the main engine torque. Determining the matching horsepower coefficient based on the performance parameters includes:

[0033] Generate a corresponding matching horsepower coefficient K m based on the main engine speed, the main engine power, and the main engine torque. The horsepower coefficient K m is characterized as:

[0034]

[0035] where P max is the rated power of the ship's main engine, M max is the maximum torque of the ship's main engine, n rated is the speed when the ship's main engine reaches the rated power, and L is a unit conversion constant.

[0036] Preferably, performing the main engine - propeller matching operation to obtain a corresponding propeller model includes:

[0037] Obtain the initial genetic algorithm and the initial weight;

[0038] Perform real-time prediction on the ship's navigation state to generate a navigation state prediction result;

[0039] Based on the navigation state prediction result, perform real-time adjustment on the initial weight to generate an adjusted weight;

[0040] Optimize the initial genetic algorithm based on the designed ship speed, the coupling rear horsepower calculation rule, and the main engine speed to generate a dynamic matching objective function, which is characterized as follows:

[0041]

[0042] where ω1 and ω2 represent the adjusted weights, η prop is the propeller efficiency, BHP engine is the engine brake horsepower, BHP prop is the propeller brake horsepower, BHP max represents the maximum brake horsepower of the ship's main engine;

[0043] Determine the optimal propeller diameter and pitch ratio based on the dynamic matching objective function;

[0044] Perform the main engine - propeller matching operation based on the optimal propeller diameter and pitch ratio to obtain the corresponding propeller model.

[0045] Preferably, the method further includes:

[0046] Obtain the long short - term memory network LSTM;

[0047] Perform real - time prediction on the ship's navigation state based on the LSTM to generate a navigation state prediction result.

[0048] Preferably, the method further includes:

[0049] After obtaining the propeller model, obtain the preset propulsion performance requirements;

[0050] Check the propeller model based on the preset propulsion performance requirements to generate a check result;

[0051] Adjust the propeller model based on the check result to obtain an adjusted propeller model.

[0052] On the other hand, the present invention also provides a ship engine - propeller intelligent matching system based on a multi - source fusion algorithm, and the system includes:

[0053] A first acquisition module, configured to acquire ship design parameters and a preset brake horsepower calculation rule;

[0054] An optimization module, configured to optimize the preset brake horsepower calculation rule based on the ship design parameters to generate an optimized horsepower calculation rule;

[0055] A coupling module, configured to determine an effective horsepower demand calculation rule, perform non-linear coupling on the optimized horsepower calculation rule based on the effective horsepower demand calculation rule, and generate a coupled horsepower calculation rule;

[0056] A second acquisition module, configured to acquire performance parameters of a ship main engine and determine a matching horsepower coefficient based on the performance parameters;

[0057] A matching module, configured to acquire a propeller atlas, and perform a main engine-propeller matching operation based on the propeller atlas, the ship design parameters, the coupled horsepower calculation rule, and the matching horsepower coefficient to obtain a corresponding propeller model.

[0058] On the other hand, the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method provided by the embodiments of the present invention is implemented.

[0059] Through the technical solution provided by the present invention, the present invention has at least the following technical effects:

[0060] By performing non-linear coupling on the optimized horsepower calculation rule and the effective horsepower demand calculation rule to generate a coupled horsepower calculation rule, and performing a main engine-propeller matching operation based on the propeller atlas, the ship design parameters, the coupled horsepower calculation rule, and the matching horsepower coefficient to obtain a corresponding propeller model, multi-model data fusion is realized to match the propeller model, and the propeller matching efficiency is improved.

[0061] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent specific implementation part. Description of the Drawings

[0062] The drawings are used to provide a further understanding of the embodiments of the present invention, and constitute a part of the specification, and are used to explain the embodiments of the present invention together with the following specific implementation manners, but do not constitute a limitation to the embodiments of the present invention. In the drawings:

[0063] Figure 1 It is a schematic flow chart of a ship engine-propeller intelligent matching method based on a multi-source fusion algorithm in the embodiments of the present invention;

[0064] Figure 2 It is a schematic structural diagram of a ship engine-propeller intelligent matching optimization system shown in the embodiments of the present invention. Detailed Description of the Invention

[0065] The following will describe in detail the specific implementation manners of the embodiments of the present invention with reference to the drawings. It should be understood that the specific implementation manners described herein are only used to illustrate and explain the embodiments of the present invention, and are not used to limit the embodiments of the present invention.

[0066] In the embodiments of the present invention, the terms "system" and "network" can be used interchangeably. "Plurality" means two or more. In view of this, in the embodiments of the present invention, "plurality" can also be understood as "at least two". "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / ", unless otherwise specified, generally represents an "or" relationship between the associated objects before and after. In addition, it should be understood that in the description of the embodiments of the present invention, words such as "first" and "second" are only used for the purpose of distinguishing descriptions, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying order.

[0067] In the actual application process of the existing ship-engine-propeller matching technology, a single formula or historical atlas is usually used for matching, and the real-time influence of the navigation conditions on the matching effect is not considered. Therefore, the existing ship-engine-propeller matching technology is prone to problems such as poor matching effect and low matching efficiency.

[0068] To solve the above problems, please refer to Figure 1 , the embodiments of the present invention provide a ship-engine-propeller intelligent matching method based on a multi-source fusion algorithm. The method includes:

[0069] Obtain the ship design parameters and the preset brake horsepower calculation rule;

[0070] Optimize the preset brake horsepower calculation rule based on the ship design parameters to generate an optimized horsepower calculation rule;

[0071] Determine the effective horsepower demand calculation rule, and perform non-linear coupling on the optimized horsepower calculation rule based on the effective horsepower demand calculation rule to generate a coupled horsepower calculation rule;

[0072] Obtain the performance parameters of the ship's main engine, and determine the matching horsepower coefficient based on the performance parameters;

[0073] Obtain the propeller atlas, and perform a main engine-propeller matching operation based on the propeller atlas, the ship design parameters, the coupled horsepower calculation rule, and the matching horsepower coefficient to obtain the corresponding propeller model.

[0074] In the existing methods for calculating the brake horsepower of ships, calculations are mainly carried out using, for example, the formula of Mitsuo Okuo, etc. The existing calculation methods rely on static parameters (such as fixed displacement Δ, ship speed V, empirical coefficient K, etc.), and do not consider the dynamic factors during the actual navigation of the ship. For example, the wind and wave level (β) will cause resistance fluctuations; the cargo distribution (γ) affects the draft and resistance of the ship; the resistance of the ship under different working conditions shows non-linear changes, etc., making the existing calculation methods have deviations, and the errors are significant under complex navigation conditions (up to more than 20%).

[0075] In a possible embodiment, first, the ship design parameters are optimized with the preset brake horsepower calculation rules. The ship design parameters include ship speed, hull displacement, dimensions, etc. That is, various factors during the actual navigation of the ship are considered to optimize the preset brake horsepower calculation rules, and the optimized horsepower calculation rules are obtained. Then, the optimized horsepower calculation rules are non-linearly coupled to generate the coupled horsepower calculation rules. Then, according to the coupled horsepower calculation rules, the horsepower demand most in line with the actual navigation process of the ship is obtained. Finally, the main engine-propeller matching operation is performed through the propeller diagram, ship design parameters, coupled horsepower calculation rules, and matching horsepower coefficient to obtain the corresponding propeller model.

[0076] By non-linearly coupling the optimized horsepower calculation rules and the effective horsepower demand calculation rules to generate the coupled horsepower calculation rules, and performing the main engine-propeller matching operation based on the propeller diagram, the ship design parameters, the coupled horsepower calculation rules, and the matching horsepower coefficient to obtain the corresponding propeller model, the multi-model data fusion matching of the propeller model is realized, and the propeller matching efficiency is improved.

[0077] However, during the actual navigation of the ship, the resistance of the ship in the fluid is changing at all times. Therefore, the brake horsepower of the ship is also changing correspondingly. That is, during the actual navigation of the ship, the substantial influence of the hull resistance on the hull needs to be considered.

[0078] To solve the above problems, further, the optimization of the preset brake horsepower calculation rules based on the ship design parameters to generate the optimized horsepower calculation rules includes:[[]]

[0079] Determine the preset brake horsepower calculation rules, which are characterized as:[[]]

[0080]

[0081] Determine the dynamic correction function of the hull resistance based on the hull load and the wind and wave environment;[[]]

[0082] Optimize the preset brake horsepower calculation rule based on the hull resistance dynamic correction function to generate an optimized horsepower calculation rule, which is characterized as:

[0083]

[0084] where K represents a preset horsepower coefficient, Δ represents the designed displacement of the ship, V represents the designed speed of the ship, C represents an empirical constant with a value range of 0.9 - 1.1, and f(Rt,α) represents the hull resistance dynamic correction function, which is predicted by an LSTM network. The input is the real-time navigation state dynamic factor α, , β is the wind and wave coefficient, γ is the load coefficient, and the output is the resistance correction amount Rt.

[0085] For example, in the embodiment of the present invention, the hull resistance dynamic correction function is characterized as: , where the resistance correction amount Rt can be predicted and generated by an LSTM network. For example, the calculation formula is: Rt = LSTM(V, β, γ, Historyt), where the input parameters are: the current speed V, the wind and wave coefficient β, the load coefficient γ, and the historical resistance sequence Historyt; the output parameter is: the resistance correction amount Rt at the future time step. The real-time navigation state dynamic factor α is set as: α = 0.2β + 0.8γ, which reflects the correction logic with the main influence of load and the secondary influence of wind and waves. The network weights are updated every 24 hours during training to ensure that the prediction error ≤ 5%. At the same time, the coincidence degree of f(Rt,α) and the measured resistance is verified in the CFD simulation (R² > 0.95). The actual navigation data comes from the ship's black box, which covers a variety of typical navigation states, and the sampling frequency of the actual navigation data is 1Hz. The actual navigation data training includes data such as speed (V), wind and wave coefficient (β), load coefficient (γ), resistance (Rt), main engine speed (n), and propeller thrust (T).

[0086] For example, in a specific embodiment, if β = 0.5 (medium wind and waves), γ = 0.7 (70% load), then: α = 0.2×0.5 + 0.8×0.7 = 0.66. If the LSTM predicts Rt = 1.2×10⁴ N, Δ = 20000 tons, and V = 10 m / s, then:

[0087]

[0088] That is, it means that the brake horsepower needs to be increased by 0.4% under the current working conditions.

[0089] In the embodiment of the present invention, in the existing Ohkubo formula, the displacement and the speed V are fixed parameters. In order to further improve the environmental adaptability and calculation accuracy, they are optimized to dynamic parameters. Specifically, the displacement is corrected in combination with the load coefficient γ: ; Dynamically correct the ship speed V in combination with the wind and wave coefficient β: .

[0090] Furthermore, the associated influence of ship size on the calculation of brake horsepower is described as follows:

[0091] According to the optimized displacement calculation formula: Δ = ρ·L·B·T·Cb, where L, B, and T are the length of the ship, the breadth of the ship, and the draft respectively, and Cb is the block coefficient, which characterizes the fullness of the hull. It can be seen that the ship size indirectly affects the brake horsepower value in the optimized horsepower calculation rule through the displacement Δ. Based on this, the wetted surface area of the ship is directly related to the length of the ship, the breadth of the ship, and the draft. The calculation formula is: S = L·(B + 2T)·k, where k is the hull form correction coefficient, and the value range is 1.05 - 1.15. The wave-making resistance coefficient Cw: is related to the hull size ratio (such as the length-to-breadth ratio L / B) and the ship form characteristics. The viscous resistance coefficient Cv: is related to the hull surface roughness and the Reynolds number (depending on the length of the ship L and the ship speed V). That is, the above parameters ultimately affect the total resistance correction amount Rt through the resistance decomposition model (such as the viscous resistance Rv, the wave-making resistance Rw, etc.), thereby correcting the brake horsepower.

[0092] By improving the existing brake horsepower calculation formula, the influence of wind and waves and load on the total resistance is dynamically reflected through the resistance correction amount; by integrating multiple factors, the comprehensive effect of the environment and load is quantified; by using a neural network to predict the resistance correction amount, the complex change law of resistance over time is captured, thereby effectively solving the dynamic adaptability problem caused by static assumptions in the traditional formula, and greatly improving the accuracy of the brake horsepower calculation. For example, under the working condition of 8 - level wind and waves, the error of the traditional formula reaches 18%, while the error is reduced to less than 3% after dynamic correction.

[0093] Furthermore, the determination of the effective horsepower demand calculation rule includes: obtaining the Hankel formula; determining the propeller thrust and torque based on the Hankel formula and the designed ship speed of the ship; performing interpolation processing on the propeller thrust and the torque based on the propeller diagram to obtain the interpolated thrust T and the interpolated torque Q. The interpolated thrust T and the interpolated torque Q are respectively characterized as: , where is characterized as the advance coefficient, ρ is characterized as the fluid density, n is characterized as the propeller speed, D is characterized as the propeller diameter, J is characterized as the advance coefficient, is determined by real - time matching based on the propeller diagram, K T is characterized as the propeller thrust coefficient, K Q is characterized as the propeller torque coefficient; generating an effective horsepower demand calculation rule based on the interpolated thrust T and the interpolated torque Q.

[0094] In a possible embodiment, first, the propeller thrust and torque are calculated based on the Hankel formula, and then efficiency interpolation is performed in combination with the propeller atlas database to obtain the interpolated propeller thrust and torque. Finally, an effective horsepower demand calculation rule is generated according to the interpolated thrust T and interpolated torque Q.

[0095] Among them, the construction method of the propeller atlas includes: using the OpenCV image recognition algorithm to perform gray processing, binarization, and contour extraction on the paper atlas to generate a digital parameter matrix; extracting the characteristic parameters of the propeller: the characteristic parameters of the propeller include the thrust coefficient of the propeller , the torque coefficient of the propeller , the disk area ratio of the propeller , where Z is the number of blades of the propeller, is the pitch ratio of the propeller; a digital feature library of the propeller atlas is established based on MATLAB, and the optimal propeller model is matched in the atlas neural network according to the characteristic parameters of the propeller that meet the power demand.

[0096] Among them, the atlas neural network adopts the ResNet-18 model, the training set contains 100,000 groups of propeller atlas parameters, and the digital feature library of the propeller atlas supports fuzzy matching, specifically, the Euclidean distance is less than or equal to 0.1. When calculating the Euclidean distance, the weight of the disk area ratio of the propeller is 0.4, the weight of the pitch ratio of the propeller is 0.3, and the weight of the number of blades of the propeller is 0.3, and the matching accuracy error is controlled within 3%.

[0097] The program for real-time matching of the propeller atlas is: input the ship speed V and the main engine speed n, and calculate the advance coefficient ; match the closest curve from the feature library through a convolutional neural network (CNN); output the matching result: propeller model, diameter D, pitch ratio P / D.

[0098] By performing efficiency interpolation on the propeller thrust and torque calculated based on the Hankel formula in combination with the propeller atlas database, the effective horsepower demand calculation rule generated by the interpolated thrust T and interpolated torque Q is more in line with the actual navigation situation, that is, the accuracy of propeller model selection is improved.

[0099] Further, non-linearly coupling the optimized horsepower calculation rule based on the effective horsepower demand calculation rule to generate a coupled horsepower calculation rule, including: obtaining the optimized horsepower calculation rule and the effective horsepower demand calculation rule; respectively obtaining the dynamic weights of the optimized horsepower calculation rule and the effective horsepower demand calculation rule; obtaining the coupled horsepower calculation rule based on the dynamic weights, the optimized horsepower calculation rule and the effective horsepower demand calculation rule, and the coupled horsepower calculation rule is characterized as:

[0100]

[0101] Where , T is the thrust after propeller interpolation, η prop is the propeller efficiency, which is determined by propeller diagram matching. , are the weights before adjustment.

[0102] In the actual data coupling process, calculate BHP 优化 and EHP respectively, and normalize EHP through the sigmoid function to limit its contribution ratio. If EHP / BHP 优化 > 1 (the propeller demand exceeds the host capacity), then automatically reduce ω2 to avoid overload; if EHP / BHP 优化 < 0.8 (the host capacity is redundant), then optimize ω2 to optimize energy efficiency.

[0103] For example, in a specific embodiment, BHP 优化 = 5000KW, EHP = 4800KW, the weights after genetic algorithm optimization are ω1 = 0.6, ω2 = 0.4; calculate the sigmoid value: sigmoid(4800 / 5000) ≈ 0.62, then the coupled horsepower is:

[0104]

[0105] Through the above optimization, not only the core contribution of the main engine braking horsepower is retained, but also it is flexibly adjusted according to the actual demand of the propeller, avoiding the rigid problem of traditional linear weighting.

[0106] The Ohkubo formula is only based on the host power demand and does not combine the actual thrust and torque of the propeller. Therefore, there is a deviation between its calculation result and the actual situation. Therefore, in the embodiment of the present invention, by non-linearly coupling the effective horsepower demand calculation rule and the optimized horsepower calculation rule, and then obtaining the coupled horsepower calculation rule, that is, the coupled horsepower calculation rule better meets the actual situation of the ship during navigation, breaks through the one-way calculation logic of the traditional formula, realizes the two-way matching of the host power and the propeller thrust, and can more accurately obtain the required propeller model.

[0107] Further, the performance parameters include the host speed, the host power, and the host torque. Determining the matching horsepower coefficient based on the performance parameters includes:

[0108] Generating a corresponding matching horsepower coefficient K based on the host speed, the host power, and the host torque m , where the horsepower coefficient K m is characterized as:

[0109]

[0110] where P max is the rated power of the ship's main engine, M max is the maximum torque of the ship's main engine, n rated is the speed when the ship's main engine reaches the rated power, and L is a unit conversion constant.

[0111] Further, performing the host-propeller matching operation to obtain a corresponding propeller model includes:

[0112] Obtaining an initial genetic algorithm and an initial weight;

[0113] Performing real-time prediction on the ship's navigation state to generate a navigation state prediction result;

[0114] Based on the navigation state prediction result, performing real-time adjustment on the initial weight to generate an adjusted weight;

[0115] Based on the ship's designed speed, the coupled horsepower calculation rule, and the host speed, optimizing the initial genetic algorithm to generate a dynamic matching objective function, which is characterized as:

[0116]

[0117] where ω 11 , ω 22 is characterized as the adjusted weight, η prop is the propeller efficiency, BHP engine is the engine brake horsepower, BHP prop is the propeller brake horsepower, BHP max is characterized as the maximum brake horsepower of the ship's main engine;

[0118] Based on the dynamic matching objective function, determining the optimal propeller diameter and pitch ratio;

[0119] Based on the optimal propeller diameter and pitch ratio, performing the host-propeller matching operation to obtain a corresponding propeller model.

[0120] In the embodiments of the present invention, the genetic algorithm optimization objective can also be based on:

[0121]

[0122] That is:

[0123] Among them, the constraint conditions are: ω 11 + ω 22 = 1, and 0.3 ≤ ω 11 , ω 22 ≤ 0.7, where ηprop is the propeller efficiency.

[0124] In a possible embodiment, constructing a dynamic objective function based on a genetic algorithm specifically includes:

[0125] Set the initial population: number of blades, pitch ratio, disk area ratio, propeller speed, diameter;

[0126] Adjust the adaptive crossover rate pc = 0.7 - 0.9, and the mutation rate pm = 0.01 - 0.05;

[0127] According to the objective function weights ω13 = 0.6, ω23 = 0.4, input the initial population and generate the optimal Pareto front solution by combining with the NSGA-II algorithm, where ω13 is the weight ratio of the fuel economy of the propeller, and ω23 is the weight ratio of the propulsion efficiency of the propeller.

[0128] Furthermore, the real-time prediction of the ship's navigation state to generate a navigation state prediction result includes: obtaining a long short-term memory network LSTM; based on the LSTM, performing real-time prediction on the ship's navigation state to generate a navigation state prediction result.

[0129] In a possible embodiment, the steps of generating a result based on LSTM for navigation state prediction are as follows: obtain data including ship speed (V), wind and wave coefficient (β), load coefficient (γ), resistance (Rt), main engine speed (n), propeller thrust (T), etc.; preprocess the obtained data. The preprocessing includes: denoising, that is, using a moving average filtering method with a window size of 5 seconds to eliminate high-frequency noise from the collected data; normalization, that is, for continuous variables such as ship speed and resistance, using the Z-score normalization formula for processing to make the data have a unified dimension and distribution characteristics; time series alignment, that is, aligning the above various types of data from multiple sources according to the time stamp, and integrating them to generate a synchronous time series matrix to ensure the consistency of different parameter data in time; sliding window segmentation, that is, using 60 seconds as a time window and a step size of 1 second, and generating an input sequence (X) and a label (Y) according to the rules. Specifically, the input X is the [V, β, γ, Rt] sequence in the first 59 seconds, and the output Y is the navigation state parameter at the 60th second, such as the resistance correction amount Rt or the ship speed change ΔV, etc.

[0130] Model construction and training phase, the model construction and training phase includes: Designing the LSTM network architecture: Input layer: Construct an input layer that can receive 60×4 time-series data. These 4 features correspond to V, β, γ, and Rt respectively, preparing a data entry for subsequent model processing. LSTM layer: Adopt a 2-layer stacked LSTM structure, with 128 neurons in each layer. The activation function is selected as tanh, and at the same time, a mechanism with a dropout rate of 0.2 is introduced to prevent model overfitting and enable the model to have the ability to learn the time-series dependence relationship of navigation states. Fully connected layer: Map the output of the LSTM layer to the prediction target. The activation function uses ReLU to further transform the features abstracted and learned by the LSTM layer into representations directly related to the prediction task. Output layer: Select the activation function according to the type of prediction task. If it is a regression task, use a linear activation function to output continuous values (such as predicting the resistance correction amount Rt, etc.); if it is a classification task, use Softmax to output classification labels (such as abnormal working condition classification).

[0131] Configure model parameters, including: Loss function: Determined according to the task type. For regression tasks, mean squared error (MSE) is selected, and for classification tasks, cross-entropy is selected to measure the difference between the model prediction result and the true value, providing an optimization direction for model training. Optimizer: Use the Adam optimizer, with the initial learning rate set to 0.001, and the learning rate decays by 10% every 50 training rounds to balance the fast convergence in the early stage of training and the fine-tuning requirements in the later stage, helping the model find the optimal parameters.

[0132] Batch size and training iterations: The batch size is set to 32, which means that each time the model updates parameters, it is calculated in batches of 32 sets of data; train for 500 epochs to allow the model to continuously optimize its own parameters during multiple repeated data learning processes.

[0133] Data division and dynamic weight update, including: Data division: Divide the historical data according to a ratio. The training set accounts for 70% and is used for the basic training and learning of the model; the validation set accounts for 15% and is used for hyperparameter tuning during training, such as trying different network structure depths, dropout ratios, etc., to find the optimal model configuration; the test set accounts for 15% and is used to evaluate the generalization ability of the model after the model training is completed, judging the prediction accuracy of the model for unseen data.

[0134] Dynamic weight update: Each time new data is accessed, adopt an incremental learning strategy and only fine-tune the weights of the fully connected layer to maintain the adaptability of the model to the current environmental changes, avoid the model forgetting important features learned before due to new data, and ensure prediction real-time performance

[0135] During the actual prediction stage, the actual prediction stage includes: an online inference process, including: data stream access: the system receives sampling data from various ship sensors in real time and caches this data for subsequent processing. Preprocessing: Immediately perform denoising and normalization operations on the received real-time data, and generate a 60×4 input matrix according to the previously established rules to meet the model input requirements. Prediction execution: Send the preprocessed input matrix into the trained LSTM model, and the model performs computational inference based on the learned navigation state rules, and outputs the navigation state prediction results for the next 1 second, such as specific values such as Rt or the ship speed V, or classification labels for abnormal working conditions. Result publication: Publish the predicted results to the dynamic correction module and the genetic algorithm optimization module through ROS (Robot Operating System) to provide data support for real-time decision-making during ship navigation and achieve intelligent navigation control. Delay control, during the entire real-time prediction process, strictly control the single inference time to ensure that it is less than or equal to 10 ms to meet the real-time requirements of ship navigation and ensure that the prediction results can be used in a timely manner to adjust the ship operation state.

[0136] Further, the method further includes: after obtaining the propeller model, obtaining a preset propulsion performance requirement; checking the propeller model based on the preset propulsion performance requirement to generate a check result; and adjusting the propeller model based on the check result to obtain an adjusted propeller model.

[0137] In a possible embodiment, propeller checking is a key link to ensure that it meets the preset propulsion performance requirements. In the embodiment of the present invention, the preset propulsion performance requirements include, but are not limited to: propulsion efficiency (the propulsion efficiency (ηprop) of the propeller at different ship speeds needs to reach the design threshold (ηprop≥0.65)), energy economy (the energy consumption per unit voyage does not exceed the preset value), cavitation performance (no significant cavitation phenomenon occurs in the propeller at the rated speed), vibration and noise (the hull vibration acceleration caused by the propeller ≤0.1m / s², underwater radiated noise ≤110dB), structural strength and durability (the fatigue life of the propeller material ≥108 cycles, and the corrosion resistance meets the IMO standard), dynamic response ability (when the propeller is in an emergency acceleration / deceleration condition, the response time ≤10s, and the thrust fluctuation ≤5%), matching the power and speed of the main engine (the power absorbed by the propeller needs to match the rated power of the main engine), and environmental adaptability (in specific sea conditions, the decrease in propulsion efficiency ≤15%) and other indicators. The specific process is as follows:

[0138] Data Input: Obtain propeller model parameters such as diameter D, pitch ratio P / D, disk area ratio, number of blades Z, etc. At the same time, obtain preset performance thresholds, including specific requirements in aspects such as propulsion efficiency, energy economy, cavitation performance, vibration and noise, structural strength and durability, dynamic response ability, power and speed matching the main engine, and environmental adaptability.

[0139] Performance Calculation: Use CFD (Computational Fluid Dynamics), FEA (Finite Element Analysis) or atlas matching tools for calculation. For example, calculate the propulsion efficiency based on the propeller atlas and CFD simulation; calculate the cavitation number through cavitation tests and empirical formulas; calculate the fuel consumption in combination with the main engine power curve, etc.

[0140] Verification and Comparison: Compare the calculation results with the preset requirements to generate a verification report, specifying whether each performance index "passes". If not, subsequent adjustments are required. For example, in a case of a container ship, the propulsion efficiency of the MAU5 - 80 propeller is 0.63 < 0.65 and the cavitation number σ = 0.28 < 0.3, not meeting the preset requirements.

[0141] Dynamic Adjustment (if verification fails)

[0142] Determine Optimization Goals: Set improvement goals for the unqualified performance indicators, such as increasing the propulsion efficiency to ηprop ≥ 0.65 and increasing the cavitation number to σ ≥ 0.3.

[0143] Formulate Adjustment Strategies: Adopt strategies such as increasing the pitch ratio, decreasing the diameter, increasing the number of blades, etc. to optimize the propeller parameters.

[0144] Algorithm Optimization: Use the genetic algorithm to determine the range of optimization variables and the objective function. For example, the optimization variables are D ∈ [6.0, 6.5]m, P / D ∈ [1.1, 1.2], Z ∈ {5, 6}; the objective function is MinimizeF = w13×(0.65 - ηprop)+w23×(0.3 - σ) (weights w13 = 0.6, w23 = 0.4), and set constraint conditions such as fuel consumption ≤ 200g / kWh and vibration acceleration ≤ 0.1m / s².

[0145] Obtain Optimization Results: Obtain the optimal parameter combination and predicted performance. For example, in a case of a container ship, the optimal parameter combination is D = 6.2m, P / D = 1.15, Z = 6; the predicted performance is η prop = 0.66, σ = 0.32, fuel consumption = 198g / kWh, vibration acceleration 0.09m / s².

[0146] Re - verification: Re - verify each performance index of the adjusted propeller, such as verifying the propulsion efficiency by CFD and measuring the cavitation number through tests, etc., to ensure that all performances meet the standards and determine the final propeller model.

[0147] In the embodiments of the present invention, by combining CFD simulation, cavitation tests and measured data, key performance indicators are quantitatively evaluated, and propeller parameters are optimized through a genetic algorithm to balance efficiency, cavitation and vibration, thereby effectively improving the accuracy and compliance of various indicators, ensuring that all performances meet the standards, and meeting the actual needs of the enterprise.

[0148] Further, please refer to Figure 2 , this embodiment also provides a ship engine-propeller intelligent matching system based on a multi-source fusion algorithm, and the system includes:

[0149] A first acquisition module, configured to acquire ship design parameters and a preset brake horsepower calculation rule;

[0150] An optimization module, configured to optimize the preset brake horsepower calculation rule based on the ship design parameters to generate an optimized horsepower calculation rule;

[0151] A coupling module, configured to determine an effective horsepower demand calculation rule, and perform non-linear coupling on the optimized horsepower calculation rule based on the effective horsepower demand calculation rule to generate a coupled horsepower calculation rule;

[0152] A second acquisition module, configured to acquire performance parameters of a ship main engine, and determine a matching horsepower coefficient based on the performance parameters;

[0153] A matching module, configured to acquire a propeller atlas, and perform a main engine-propeller matching operation based on the propeller atlas, the ship design parameters, the coupled horsepower calculation rule and the matching horsepower coefficient to obtain a corresponding propeller model.

[0154] Furthermore, the embodiments of the present invention also provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method described in the embodiments of the present invention is implemented.

[0155] The optional embodiments of the present invention have been described in detail above in conjunction with the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above embodiments. Within the scope of the technical concept of the embodiments of the present invention, various simple modifications can be made to the technical solutions of the embodiments of the present invention, and these simple modifications all belong to the protection scope of the embodiments of the present invention.

[0156] In addition, it should be noted that, in the above specific embodiments, the various specific technical features described can be combined in any appropriate manner without conflict. To avoid unnecessary repetition, the embodiments of the present invention do not separately describe various possible combination methods.

[0157] Those skilled in the art can understand that all or part of the steps in implementing the methods of the above embodiments can be completed by instructing relevant hardware through a program, and this program is stored in a storage medium, including several instructions for causing a single-chip microcomputer, a chip or a processor to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs.

[0158] In addition, any combinations can be made among various different implementation manners of the embodiments of the present invention, as long as they do not violate the idea of the embodiments of the present invention, and they should also be regarded as the content disclosed by the embodiments of the present invention.

Claims

1. A ship engine-propeller intelligent matching method based on a multi-source fusion algorithm, characterized in that The method includes: Obtaining ship design parameters and a preset brake horsepower calculation rule; Optimizing the preset brake horsepower calculation rule based on the ship design parameters to generate an optimized horsepower calculation rule; Determining an effective horsepower demand calculation rule, and nonlinearly coupling the optimized horsepower calculation rule based on the effective horsepower demand calculation rule to generate a coupled horsepower calculation rule; Obtaining the performance parameters of the ship's main engine, and determining a matching horsepower coefficient based on the performance parameters; Obtaining a propeller atlas, and performing a main engine - propeller matching operation based on the propeller atlas, the ship design parameters, the coupled horsepower calculation rule, and the matching horsepower coefficient to obtain a corresponding propeller model.

2. The method according to claim 1, characterized in that, The optimizing the preset brake horsepower calculation rule based on the ship design parameters to generate an optimized horsepower calculation rule includes: Determining the preset brake horsepower calculation rule, which is characterized as: ， Determining a hull resistance dynamic correction function based on the hull load and the wind and wave environment; Optimizing the preset brake horsepower calculation rule based on the hull resistance dynamic correction function to generate an optimized horsepower calculation rule, which is characterized as: ， Where, K represents a preset horsepower coefficient, Δ represents the ship design displacement, V represents the ship design speed, C represents an empirical constant, f(Rt,α) represents the hull resistance dynamic correction function, Rt represents the resistance correction amount, and α represents the real - time navigation state dynamic factor.

3. The method according to claim 1, wherein The determining the effective horsepower demand calculation rule includes: Obtaining the Hankel formula; Determining the propeller thrust and torque based on the Hankel formula and the ship design speed; Interpolate the propeller thrust and the torque based on the propeller atlas to obtain the interpolated thrust T and the interpolated torque Q, where the interpolated thrust T and the interpolated torque Q are respectively characterized as: , Among them, ρ represents the fluid density, n represents the propeller rotational speed, D represents the propeller diameter, and J represents the advance coefficient. It is determined by real-time matching based on the propeller atlas, K T represents the thrust coefficient of the propeller, and K Q represents the torque coefficient of the propeller. Generating an effective horsepower demand calculation rule based on the interpolated thrust T and the interpolated torque Q.

4. The method according to claim 2, wherein The nonlinearly coupling the optimized horsepower calculation rule based on the effective horsepower demand calculation rule to generate a coupled horsepower calculation rule includes: Obtaining the optimized horsepower calculation rule and the effective horsepower demand calculation rule; Respectively obtaining the dynamic weights of the optimized horsepower calculation rule and the effective horsepower demand calculation rule; Obtaining a coupled horsepower calculation rule based on the dynamic weights, the optimized horsepower calculation rule, and the effective horsepower demand calculation rule, which is characterized as: ， Among them , T is the thrust after propeller interpolation, and η prop is the propeller efficiency, which is determined by propeller diagram matching, , are the weights before adjustment.

5. The method according to claim 2, wherein The performance parameters include the main engine speed, the main engine power, and the main engine torque. The determining the matching horsepower coefficient based on the performance parameters includes: Generate a corresponding matching horsepower coefficient K based on the host speed, the host power, and the host torque m , the horsepower coefficient K m is characterized as: ， Among them, P max is the rated power of the ship's main engine, M max is the maximum torque of the ship's main engine, n rated is the rotational speed when the ship's main engine reaches the rated power, and L is the unit conversion constant.

6. The method according to claim 5, wherein The performing the main engine - propeller matching operation to obtain a corresponding propeller model includes: Obtaining an initial genetic algorithm and an initial weight; Performing real - time prediction on the navigation state of the ship to generate a navigation state prediction result; Adjusting the initial weight in real - time based on the navigation state prediction result to generate an adjusted weight; Optimizing the initial genetic algorithm based on the ship design speed, the coupled horsepower calculation rule, and the main engine speed to generate a dynamic matching objective function, which is characterized as: ， Among them, ω 11 , ω 22 is characterized as the adjusted weight, η prop is the propeller efficiency, BHP engine is the engine brake horsepower, BHP prop is the propeller brake horsepower, BHP max is characterized as the maximum brake horsepower of the ship's main engine; Determining the optimal propeller diameter and pitch ratio based on the dynamic matching objective function. Perform the main engine - propeller matching operation based on the optimal propeller diameter and pitch ratio to obtain the corresponding propeller model.

7. The method according to claim 6, wherein The real - time prediction of the ship's navigation state to generate a navigation state prediction result includes: Obtain the long short - term memory network (LSTM); Based on the LSTM, perform real - time prediction on the ship's navigation state to generate a navigation state prediction result.

8. The method according to any one of claims 1-7, characterized in that, The method further includes: After obtaining the propeller model, obtain the preset propulsion performance requirements; Check the propeller model based on the preset propulsion performance requirements to generate a check result; Adjust the propeller model based on the check result to obtain an adjusted propeller model.

9. A ship engine-propeller intelligent matching system based on a multi-source fusion algorithm, characterized in that, The system includes: A first acquisition module, configured to acquire ship design parameters and a preset brake horsepower calculation rule; An optimization module, configured to optimize the preset brake horsepower calculation rule based on the ship design parameters to generate an optimized horsepower calculation rule; A coupling module, configured to determine an effective horsepower demand calculation rule, and perform non - linear coupling on the optimized horsepower calculation rule based on the effective horsepower demand calculation rule to generate a coupled horsepower calculation rule; A second acquisition module, configured to acquire the performance parameters of the ship's main engine and determine a matching horsepower coefficient based on the performance parameters; A matching module, configured to acquire a propeller diagram, and perform a main engine - propeller matching operation based on the propeller diagram, the ship design parameters, the coupled horsepower calculation rule, and the matching horsepower coefficient to obtain the corresponding propeller model.

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

Images