A ship hybrid power capacity matching method and system suitable for multi-navigation features

Abstract

The present application relates to the technical field of ship power, and particularly relates to a ship hybrid power capacity matching method and system suitable for multiple navigation characteristics, the method comprising: obtaining a target data set, extracting a hybrid power capacity feature and a ship navigation feature from the target data set; obtaining an optimal capacity configuration based on the hybrid power capacity feature and the ship navigation feature; for the optimal capacity configuration, obtaining a capacity matching scheme in combination with an uncertainty condition, and quantifying the robustness of the capacity matching scheme under the uncertainty condition.

Description

Technical Field

[0001] This invention relates to the field of marine propulsion technology, and in particular to a method and system for matching the hybrid power capacity of ships to adapt to multiple navigation characteristics. Background Technology

[0002] The application of hybrid power technology in the marine sector is a rapidly developing trend. It combines traditional power systems with one or more alternative energy / storage systems, aiming to improve efficiency, reduce emissions, and enhance operational flexibility. Examples of hybrid systems include diesel / gas turbine-electric hybrid systems. Common applications include ferries and ro-ro passenger ships, offshore engineering vessels, cargo ships, and cruise ships.

[0003] Existing ship hybrid power capacity matching typically employs fixed operating point optimization during the design process, neglecting dynamic changes and uncertainties during navigation. Separating capacity design from subsequent operation optimization results in suboptimal solutions and lacks robustness metrics for the matching results. Summary of the Invention

[0004] This invention considers uncertainties in actual navigation during the hybrid power capacity configuration stage and quantifies these uncertainties, thereby obtaining the optimal capacity configuration rather than a suboptimal solution.

[0005] The technical solution proposed in this invention is: a method for matching the hybrid power capacity of ships to adapt to multiple navigation characteristics, the method comprising: Obtain the target dataset and extract hybrid power capacity features and ship navigation features from the target dataset; The optimal capacity configuration is obtained based on the hybrid power capacity characteristics and ship navigation characteristics. For optimal capacity configuration, a capacity matching scheme is obtained by combining uncertainty conditions, and the robustness of the capacity matching scheme under uncertainty conditions is quantified.

[0006] Preferably, the hybrid power capacity characteristics include: maximum battery capacity, maximum battery discharge power, maximum battery charging power, generator output power, maximum demand power, and propulsion power; The ship navigation characteristics include: ship structural characteristics and navigation uncertainty characteristics. The ship structural characteristics include the ship's gross weight and ship shape. The navigation uncertainty characteristics include environmental uncertainty characteristics, operational uncertainty characteristics, and system uncertainty characteristics. The method of obtaining the optimal capacity configuration based on hybrid power capacity characteristics and ship navigation characteristics includes: Construct a constraint sub-model to provide physical constraints for optimal capacity configuration; The goal is to find the optimal capacity configuration with the minimum total cost of ownership over the entire lifecycle.

[0007] Preferably, the construction of the constraint sub-model includes: Constructing a ship motion and resistance sub-model: in, Indicates the weight of the ship. Indicates the quality of the attached water. Indicates speed, express Total thrust of the ship at any given moment express Total ship resistance at any given moment; in, , Indicates the ship's unloaded weight. This indicates the weight of the non-energy-consuming load. This indicates the weight of the energy-consuming load. and This indicates the non-energy load weight and the energy load weight. .

[0008] Preferably, the construction of the constraint sub-model further includes: Constructing an energy flow sub-model for a hybrid power system, including: ;in, This indicates the battery's maximum capacity, maximum battery discharge power, engine rated power, and maximum auxiliary power supply system power. This indicates the power required for energy-consuming loads; Indicates the generator's power generation efficiency; Indicates the maximum required power; , Indicates periodic weight; Indicates basic energy consumption; Indicates redundant power. This indicates the generator's rated power and the battery's power. , Indicates the power of the auxiliary power supply system; Indicates the maximum charging power. Maximum discharge power; express Battery energy storage at all times Indicates battery aging parameters; This represents the loss coefficient.

[0009] Preferably, the construction of the constraint sub-model further includes: Construct a task and runtime constraint sub-model, including: Divide the routes into Each segment State feature set ; Indicates flight segment The starting position, Indicates flight segment The finish line Indicates flight segment Starting time, Indicates flight segment End time, Indicates the running model type.

[0010] Preferred options also include: A comprehensive uncertainty model is constructed to classify and quantify emergencies into corresponding uncertainty scenarios, including: Let the uncertainty vector for each flight segment be... ; Among them, the environmental uncertainty vector , This indicates the time error in wind and wave prediction. ; Indicates the deviation from the starting point of the flight segment. Indicates the deviation at the end of the flight segment; Indicates the predicted time of occurrence of wind and waves. Indicates the actual time of the storm; Operational uncertainty vector ,in, Indicates the time error at the start of the flight segment. Indicates the time error at the end of the flight segment; System uncertainty vector ,in, This indicates the probability of engine failure. This indicates the probability of battery failure.

[0011] Preferably, the process of finding the optimal capacity configuration includes: Construct a set of capacity configuration decision variables ;in, Indicates the number of generators; Construct the objective optimization function ,in, Capital expenditures under the set of capacity allocation decision variables ; Indicates cost per unit capacity. Indicates cost per unit of power. Indicates fuel cost per unit of power. This indicates the cost of a single generator; This represents the set of uncertainty vectors that include all flight segments; Indicates the cost of uncertainty; , indicating in the uncertainty vector set Within this framework, we find the uncertainty vector that maximizes operating costs, and then use the operating costs corresponding to that uncertainty vector. As a cost of uncertainty; ; This indicates the unit mass cost of supplemental fuel. In order to cope with uncertainty The quality of the supplementary fuel, This represents the unit delay penalty cost. Represents a symbolic function. , These represent the time error at the start of the flight segment and the time error at the end of the flight segment, respectively. Solving Convert to solution ,include: Given a ; will give and The input is fed into a pre-trained neural network, which outputs an uncertainty vector for each flight segment. The corresponding operating costs; Find the maximum value and its corresponding uncertainty vector among all the output operating costs; Utilize the already obtained ,Will and Input into a pre-trained optimized model, output value; renew Repeat the above steps, and after multiple iterations, obtain the result that... Minimum set of capacity configuration decision variables ; Will Substitute the values ​​into the energy flow sub-model of the hybrid power system and determine whether the conditions are met. If so, then... As the optimal capacity configuration, otherwise, adjust the neural network parameters, including the weights and biases of the convolutional layer filters and the weights of the fully connected layers; Using the adjusted neural network, repeat the above steps until the set of capacity configuration decision variables that satisfy the energy flow sub-model of the hybrid power system is obtained, i.e., the optimal capacity configuration. .

[0012] Preferably, for the optimal capacity configuration, the process of obtaining a capacity matching scheme in conjunction with uncertainty conditions, and quantifying the robustness of the capacity matching scheme under uncertainty conditions, includes: Obtaining capacity matching solutions includes: Let the integrated state vector for each flight segment be... ;in, Indicates flight segment Average speed within the area; Represents a timestamp; Indicates flight segment Inside Battery energy storage at any given time; The state vector Control vector and uncertainty vector Input the pre-trained convolutional neural network to obtain flight segments. The future moment Predicted state vector ; in, Indicates flight segment Internal operation control vector, ;in, Representing flight segments Inside At any given moment, the battery power, generator output power, auxiliary power supply system power, and commanded speed are all measured. ; Will , and Substitute the energy flow sub-model of the hybrid power system to determine if it holds true. If it does not hold true, adjust the operation control vector. After multiple iterations, the result was obtained. , and Under the given conditions, the operating control vector of the energy flow sub-model of the hybrid power system is satisfied; The optimal capacity matching is then ; The adjusted operation control vector is , Indicates the learning rate; The robustness of quantification capacity matching under uncertainty conditions includes: For each uncertainty vector , then, in Defined task success vector in uncertain scenarios ;in, Indicates the propagation type indicator coefficient. Among them, the on-time arrival indicator feature Battery safety indicator features , , Indicates the minimum and maximum energy storage of the battery; Passenger loss indicator features ; Indicates the percentage of passengers lost; The success rate of a task in a single uncertain scenario is ; Success rate of missions along the route ; The mission success rate of flight routes represents the robustness of capacity matching under conditions of uncertainty, including: if If the capacity configuration and capacity matching are robust, then the system is determined to be robust; otherwise, it iterates through all the mission success vectors of all segments, finds the mission success vector with the lowest vector value, and identifies the segments that affect the mission success rate.

[0013] A ship hybrid power capacity matching system adapted to multiple navigation characteristics, the system being used to execute the aforementioned ship hybrid power capacity matching method adapted to multiple navigation characteristics.

[0014] A computer-readable storage medium storing a computer program that is executed by a processor to implement the aforementioned method for matching the hybrid power capacity of a ship to adapt to multiple navigation characteristics.

[0015] The beneficial effects of this invention are: 1. This invention unifies and optimizes the capacity configuration (such as battery and generator selection) and capacity matching (power allocation and speed control) processes, solving problems such as unrecoverable capacity shortages and excessive redundancy costs that are easily caused by traditional technologies. By constructing a comprehensive uncertainty model (three types of uncertainty vectors: environment, operation, and system), the uncertainty scenarios in the actual operation phase are considered during capacity configuration design, giving the capacity configuration inherent robustness.

[0016] 2. This invention employs a dual-constraint approach based on physical and economic factors, and a two-layer optimization method. In the upper layer, the goal is to minimize the total lifecycle cost of ownership, thereby finding the optimal hybrid power capacity configuration under uncertainty. In the lower layer, given the capacity configuration, the operation control vector is dynamically adjusted through a pre-trained neural network model. The elements within the operation control vector are the allocated hybrid power capacity and speed, thus achieving adaptive capacity allocation under uncertain scenarios. Attached Figure Description

[0017] Figure 1 This is a flowchart of a ship hybrid power capacity matching method adapted to multiple navigation characteristics according to the present invention. Detailed Implementation

[0018] The following description is intended to disclose the present invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious modifications will occur to those skilled in the art. The basic principles of the invention defined in the following description can be applied to other embodiments, modifications, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the invention.

[0019] It is understood that the term "a" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element can be one, while in another embodiment, the number of the element can be multiple, and the term "a" should not be understood as a limitation on the number.

[0020] refer to Figure 1 The technical solution provided by this invention is: a method for matching the hybrid power capacity of ships to adapt to multiple navigation characteristics, the method comprising: Step 1: Obtain the target dataset and extract hybrid power capacity features and ship navigation features from it. The hybrid power capacity features include: maximum battery capacity, maximum battery discharge power, maximum battery charging power, generator output power, maximum power demand, and propulsion power. The ship navigation features include: ship structural features and navigation uncertainty features. The ship structural features include the ship's gross weight and shape; the navigation uncertainty features include environmental uncertainty features, operational uncertainty features, and system uncertainty features.

[0021] Step 2: Obtain the optimal capacity configuration based on hybrid power capacity characteristics and ship navigation characteristics, specifically including the following steps: Step 2.1: Construct a constraint sub-model to provide physical constraints for optimal capacity configuration. Specifically: A ship motion and resistance sub-model is constructed to describe the relationship between ship speed, position, and propulsion power.

[0022] The ship motion and resistance sub-model is as follows: in, Indicates the weight of the ship. Indicates the quality of the attached water. Indicates speed, express Total thrust of the ship at any given moment express The total resistance of a ship at any given time includes static resistance, wind resistance, and water flow resistance.

[0023] in, , Indicates the ship's unloaded weight. This refers to the weight of non-energy-consuming cargo, such as the cargo carried on a freighter that does not require energy. This refers to the weight of an energy-consuming load, such as passengers on a cruise ship or in a hotel. and This indicates the non-energy load weight and the energy load weight. ; Cargo ships have a high proportion of non-energy-consuming cargo. Very large, close to 1, cruise ships have a high energy consumption-to-weight ratio. It is very large, close to 1, which is used to distinguish different types of ships and types of cargo loaded on ships.

[0024] A hybrid power system energy flow model is constructed to describe the real-time flow and balance of energy among the battery, propeller motor, generator, and load. The hybrid power system energy flow model is as follows: ; in, This indicates the battery's maximum capacity, maximum battery discharge power, engine rated power, and maximum auxiliary power supply system power. In this embodiment, the power required for energy-consuming loads is approximately 0, and the total power required is approximately equal to the power required for energy-consuming loads. Indicates the generator's power generation efficiency; Indicates the maximum required power. , Indicates periodic weight; This refers to basic energy consumption, such as the energy consumption of infrastructure within a hotel on a cruise ship.

[0025] Indicates redundant power. This indicates the generator's rated power and the battery's power. , This indicates the power output of auxiliary power supply systems. Examples include solar power and shore power (provided by the port). Indicates the maximum charging power. Maximum discharge power; express Battery energy storage at the current moment. Indicates battery aging parameters; This represents the loss coefficient.

[0026] Construct a task and operational constraint sub-model to transform abstract navigation tasks into mathematical constraints on state and control, including: Divide the routes into Each segment State feature set ; in, Indicates flight segment The starting position, Indicates flight segment The finish line Indicates flight segment Starting time, Indicates flight segment End time, This indicates the operating model type, including fuel operating model, hybrid operating mode, and pure electric operating mode.

[0027] For example, cruise ships operate in pure electric mode when entering scenic areas or ports. , This indicates a silent or low operating speed to meet the emission and noise requirements of the scenic area.

[0028] For example, when cargo ships enter a port for loading and unloading, they can connect to shore power and operate in pure electric mode or hybrid mode. In order to meet emission requirements.

[0029] A comprehensive uncertainty model is constructed to classify and quantify emergencies into corresponding uncertainty scenarios, including: Let the uncertainty vector for each flight segment be... ; Among them, the environmental uncertainty vector , This indicates the time error in wind and wave prediction. If there are no winds or waves in the sailing segment, the value is 0.

[0030] Indicates the deviation from the starting point of the flight segment. Indicates the deviation at the end of the flight segment; Indicates the predicted time of occurrence of wind and waves. This indicates the actual time when the wind and waves occurred.

[0031] Operational uncertainty vector ,in, Indicates the time error at the start of the flight segment. Indicates the time error at the end of the flight segment; System uncertainty vector ,in, This indicates the probability of engine failure. The probability of battery failure can be obtained based on the historical failure probability distribution of the battery.

[0032] Step 2.2: Find the optimal capacity configuration with the goal of minimizing the total cost of ownership over the entire lifecycle.

[0033] The fundamental flaw of traditional methods is decoupling. They first design capacity based on typical operating conditions and then formulate capacity matching strategies for a given system, neglecting issues such as: insufficient capacity leading to irremediable policy changes; excessive capacity redundancy resulting in wasted lifecycle costs; and the coupling effect of uncertainty on capacity and policy. Therefore, in this embodiment, we construct a two-layer optimization network. The upper layer optimizes capacity configuration to minimize the total lifecycle cost of ownership; the lower layer searches for the optimal control scheme, i.e., the capacity matching scheme, under different uncertainties given the capacity configuration. Specifically: Construct a set of capacity configuration decision variables ;in, Indicates the number of generators; To minimize the total cost of ownership over the entire lifecycle, an objective optimization function is constructed. ,in, Capital expenditures under the set of capacity allocation decision variables ; Indicates cost per unit capacity. Indicates cost per unit of power. Indicates fuel cost per unit of power. This indicates the cost of a single generator; This represents the set of uncertainty vectors that include all flight segments; Indicates the cost of uncertainty; , indicating in the uncertainty vector set Within this framework, we find the uncertainty vector that maximizes operating costs, and then use the operating costs corresponding to that uncertainty vector. As a cost of uncertainty.

[0034] ; This indicates the unit mass cost of supplemental fuel. In order to cope with uncertainty The quality of the supplementary fuel, This represents the unit delay penalty cost. This represents a symbolic function; the value is 1 if the condition within the parentheses is met, and 0 otherwise. , These represent the time error at the start of the flight segment and the time error at the end of the flight segment, respectively.

[0035] Solving Convert to solution ,include: Given a ; will give and The input is fed into a pre-trained neural network, which outputs an uncertainty vector for each flight segment. The corresponding operating costs (in uncertain scenarios); Find the maximum value and its corresponding uncertainty vector among all the output operating costs; Utilize the already obtained ,Will and Input to the pre-trained optimized model, internal, output Value. In this embodiment, a Bayesian optimization model trained using historical dynamic design data is used.

[0036] renew Repeat the above steps, and after multiple iterations, obtain the result that... Minimum set of capacity configuration decision variables ; Will Substitute the values ​​into the energy flow sub-model of the hybrid power system and determine whether the conditions are met. If so, then... As the optimal capacity configuration, otherwise, adjust the neural network parameters, including the weights and biases of the convolutional layer filters and the weights of the fully connected layers; Using the adjusted neural network, repeat the above steps until the set of capacity configuration decision variables that satisfy the energy flow sub-model of the hybrid power system is obtained, i.e., the optimal capacity configuration. .

[0037] Step 3: For the optimal capacity configuration, considering the uncertainty conditions, obtain the capacity matching scheme and quantify the robustness of the capacity matching scheme under uncertainty conditions. This includes the following steps: Obtaining capacity matching solutions includes: Let the integrated state vector for each flight segment be... ;in, Indicates flight segment Average speed within the area; Represents a timestamp; Indicates flight segment Inside Battery energy storage at any given time; The state vector Control vector and uncertainty vector Input the pre-trained convolutional neural network to obtain flight segments. The future moment Predicted state vector ; in, Indicates flight segment Internal operation control vector, ;in, Representing flight segments Inside The battery power, generator output power, auxiliary power supply system power, and commanded speed at any given time.

[0038] because ,Will , and Substitute the energy flow model of the hybrid power system into the equation and determine if it holds true. If it does not, adjust the operation control vector.

[0039] After multiple iterations, the result was obtained. , and Under the given conditions, the operating control vector of the energy flow sub-model of the hybrid power system is satisfied; The optimal capacity matching is then The adjustment method for the operation control vector is based on a self-learning algorithm, and the adjusted operation control vector is: , This represents the learning rate.

[0040] The robustness of quantification capacity matching under uncertainty conditions includes: For each uncertainty vector , then, in Defined task success vector in uncertain scenarios ;in, Indicates the propagation type indicator coefficient. ; 0 represents a cargo ship, and 1 represents a cruise ship.

[0041] Among them, the on-time arrival indication feature Battery safety indicator features , , Indicates the minimum and maximum energy storage of the battery; Passenger loss indicator features ; This indicates the percentage of passengers lost (usually greater than 0.95).

[0042] The success rate of a task in a single uncertain scenario is ; mission success rate of the route .

[0043] The mission success rate of flight routes represents the robustness of capacity matching under conditions of uncertainty, including: if If so, the capacity configuration and capacity matching are robust. Otherwise, iterate through all the mission success vectors of all segments and find the mission success vector with the lowest vector value to identify the segments that affect the mission success rate.

[0044] The present invention also provides a ship hybrid power capacity matching system adapted to multiple navigation characteristics, the system being used to execute the aforementioned ship hybrid power capacity matching method adapted to multiple navigation characteristics.

[0045] The present invention also provides a computer-readable storage medium storing a computer program that is executed by a processor to implement the aforementioned method for matching hybrid power capacity of ships with multiple navigation characteristics.

[0046] The processes described above with reference to the flowcharts in the embodiments disclosed in this invention can be implemented as computer software programs. The embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), it performs the functions defined in the methods of this application. It should be noted that the computer-readable medium described above in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wire segments, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless segments, wire segments, optical fibers, RF, etc., or any suitable combination thereof.

[0047] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation that may be implemented in systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0048] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are merely examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functions and structural principles of the present invention have been shown and explained in the embodiments. Without departing from the principles described, the implementation of the present invention may have any changes or modifications.

Claims

1. A method for matching the hybrid power capacity of ships to adapt to multiple navigation characteristics, characterized in that, The method includes: Obtain the target dataset and extract hybrid power capacity features and ship navigation features from it. The hybrid power capacity features include: maximum battery capacity, maximum battery discharge power, and maximum battery charging power, generator output power, maximum power demand, and propulsion power. The ship navigation features include: ship structural features and navigation uncertainty features. The ship structural features include the ship's gross weight and ship shape. The navigation uncertainty features include environmental uncertainty features, operational uncertainty features, and system uncertainty features. Optimal capacity configuration is obtained based on hybrid power capacity characteristics and ship navigation characteristics, including: A constraint sub-model is constructed to provide physical constraints for optimal capacity configuration; the constraint sub-model includes a ship motion and resistance sub-model, a hybrid power system energy flow sub-model, and a task and operation constraint sub-model; the optimal capacity configuration is sought with the goal of minimizing the total life cycle cost of ownership; For optimal capacity configuration, considering uncertainty conditions, a capacity matching scheme is obtained, and the robustness of the capacity matching scheme under uncertainty conditions is quantified; this includes: obtaining the capacity matching scheme, including: Let the integrated state vector for each flight segment be... ;in, Indicates flight segment Average speed within the area; Represents a timestamp; Indicates flight segment Inside Battery energy storage at any given time; Indicates each flight segment The set of state features; The state vector Control vector and uncertainty vector Input the pre-trained convolutional neural network to obtain flight segments. The future moment Predicted state vector The uncertainty vector Includes: Environmental uncertainty vector Operational uncertainty vector and system uncertainty vector ; in, Indicates flight segment Internal operation control vector, ;in, Representing flight segments Inside At any given moment, the battery power, generator output power, auxiliary power supply system power, and commanded speed are all measured. ； Will , and Substitute the energy flow sub-model of the hybrid power system to determine if it holds true. If it does not hold true, adjust the operation control vector. Indicates the optimal capacity configuration; After multiple iterations, the result was obtained. , and Under the given conditions, the operating control vector of the hybrid power system energy flow sub-model is satisfied; The optimal capacity matching is then ; The adjusted operation control vector is , This represents the learning rate.

2. The method for matching the hybrid power capacity of a ship to adapt to multiple navigation characteristics according to claim 1, characterized in that, The construction of the constraint sub-model includes: Constructing a ship motion and resistance sub-model: in, Indicates the weight of the ship. Indicates the quality of the attached water. Indicates speed, express Total thrust of the ship at any given moment express Total ship resistance at any given moment; in, , Indicates the ship's unloaded weight. This indicates the weight of the non-energy-consuming load. This indicates the weight of the energy-consuming load. and This indicates the non-energy load weight and the energy load weight. .

3. The method for matching the hybrid power capacity of a ship to adapt to multiple navigation characteristics according to claim 2, characterized in that, The construction of the constraint sub-model also includes: Constructing an energy flow sub-model for a hybrid power system, including: ;in, This indicates the battery's maximum capacity, maximum battery discharge power, engine rated power, and maximum auxiliary power supply system power. This indicates the power required for energy-consuming loads; Indicates the generator's power generation efficiency; Indicates the maximum required power; , Indicates periodic weight; Indicates basic energy consumption; Indicates redundant power. This indicates the generator's rated power and the battery's power. , Indicates the power of the auxiliary power supply system; Indicates the maximum charging power. Maximum discharge power; express Battery energy storage at all times Indicates battery aging parameters; This represents the loss coefficient.

4. The method for matching the hybrid power capacity of a ship to adapt to multiple navigation characteristics according to claim 3, characterized in that, The construction of the constraint sub-model also includes: Construct a task and runtime constraint sub-model, including: Divide the routes into Each segment State feature set ; Indicates flight segment The starting position, Indicates flight segment The finish line Indicates flight segment Starting time, Indicates flight segment End time, Indicates the running model type.

5. A method for matching the hybrid power capacity of a ship to adapt to multiple navigation characteristics, as described in claim 4, is characterized in that, Also includes: A comprehensive uncertainty model is constructed to classify and quantify emergencies into corresponding uncertainty scenarios, including: Let the uncertainty vector for each flight segment be... ; Among them, the environmental uncertainty vector , This indicates the time error in wind and wave prediction. ; Indicates the deviation from the starting point of the flight segment. Indicates the deviation at the end of the flight segment; Indicates the predicted time of occurrence of wind and waves. Indicates the actual time of the storm; Operational uncertainty vector ,in, Indicates the time error at the start of the flight segment. Indicates the time error at the end of the flight segment; System uncertainty vector ,in, This indicates the probability of engine failure. This indicates the probability of battery failure.

6. The method for matching the hybrid power capacity of a ship to adapt to multiple navigation characteristics according to claim 5, characterized in that, The process of finding the optimal capacity configuration includes: Construct a set of capacity configuration decision variables ;in, Indicates the number of generators; Construct the objective optimization function ,in, Capital expenditures under the set of capacity allocation decision variables ; Indicates cost per unit capacity. Indicates cost per unit of power. Indicates fuel cost per unit of power. This indicates the cost of a single generator; This represents the set of uncertainty vectors that include all flight segments; Indicates the cost of uncertainty; , indicating in the uncertainty vector set Within this framework, we find the uncertainty vector that maximizes operating costs, and then use the operating costs corresponding to that uncertainty vector. As a cost of uncertainty; ; This indicates the unit mass cost of supplemental fuel. In order to cope with uncertainty The quality of the supplementary fuel, This represents the unit delay penalty cost. Represents a symbolic function. , These represent the time error at the start of the flight segment and the time error at the end of the flight segment, respectively. Solving Convert to solution ,include: Given a ; will give and The input is fed into a pre-trained neural network, which outputs an uncertainty vector for each flight segment. The corresponding operating costs; Find the maximum value and its corresponding uncertainty vector among all the output operating costs; Utilize the already obtained ,Will and The input is fed into a pre-trained optimization model, and after multiple iterations, an optimal result is obtained. Minimum set of capacity configuration decision variables ; Will Substitute the values ​​into the energy flow sub-model of the hybrid power system and determine whether the conditions are met. If so, then... As the optimal capacity configuration, otherwise, adjust the neural network parameters, including the weights and biases of the convolutional layer filters and the weights of the fully connected layers; Using the adjusted neural network, repeat the above steps until the set of capacity configuration decision variables that satisfy the energy flow sub-model of the hybrid power system is obtained, i.e., the optimal capacity configuration. .

7. A method for matching the hybrid power capacity of a ship to accommodate multiple navigation characteristics, as described in claim 6, is characterized in that, The process of obtaining a capacity matching scheme for the optimal capacity configuration, taking into account uncertainty conditions, and quantifying the robustness of the capacity matching scheme under uncertainty conditions includes: The robustness of quantification capacity matching under uncertainty conditions includes: For each uncertainty vector , then, in Defined task success vector in uncertain scenarios ;in, Indicates the propagation type indicator coefficient. Among them, the on-time arrival indicator feature Battery safety indicator features , , Indicates the minimum and maximum energy storage of the battery; Indicates the time error at the start of the flight segment. Indicates the time error at the end of the flight segment; Passenger loss indicator features ; Indicates the percentage of passengers lost; The mission success rate of the flight is calculated based on on-time arrival indication characteristics, battery safety indication characteristics, and passenger loss indication characteristics. ; The mission success rate of flight routes represents the robustness of capacity matching under conditions of uncertainty, including: if If the capacity configuration and capacity matching are robust, then the system is determined to be robust; otherwise, it iterates through all the mission success vectors of all segments, finds the mission success vector with the lowest vector value, and identifies the segments that affect the mission success rate.

8. A ship hybrid power capacity matching system adapted to multiple navigation characteristics, characterized in that, The system is used to execute a ship hybrid power capacity matching method adapted to multiple navigation characteristics as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement a ship hybrid power capacity matching method adapted to multiple navigation characteristics as described in any one of claims 1-7.

Images