Multi-target zero-carbon ship energy management and control method, system, equipment, medium and product

Abstract

The invention discloses a multi-target zero-carbon ship energy management and control method, system, equipment, medium and product, and relates to the field of ship energy management and control, and the method comprises the steps: constructing a working condition-recession quantitative characterization model according to fuel cell attenuation experiment data and an HDBSCAN clustering algorithm; constructing a ship multi-source power system model according to the working condition-recession quantitative characterization model and the real ship vehicle data; the ship multi-source power system model comprises a fuel cell coupling degradation model, a lithium battery multi-mechanism degradation model and a superconducting energy storage electrothermal coupling model; based on the power balance constraint and the operation constraint of the ship multi-source power system, establishing an objective function of the ship multi-source power system model; and in combination with the TCN prediction model, an MPC multi-target energy management strategy is determined according to the target function, energy management is performed according to the MPC multi-target energy management strategy, multi-target collaborative optimization is realized, multi-target collaborative optimization can be realized, and energy waste is avoided.

Description

Technical Field

[0001] This application relates to the field of ship energy management, and in particular to a multi-objective zero-carbon ship energy management method, system, equipment, medium and product. Background Technology

[0002] Shipping is the most important and carbon-efficient mode of transportation in global trade, currently accounting for about 3% of global CO2 emissions. The International Maritime Organization (IMO) points out that without control, global shipping CO2 emissions are projected to increase by 250% by 2050, reaching 18% of total global emissions. Carbon reduction in shipping has become an inevitable trend for the global shipping industry. On April 11, 2025, the IMO approved the draft amendment to the International Convention for the Prevention of Pollution from Ships, mandating the implementation of the IMO's net-zero emissions framework. This is the world's first framework combining mandatory emission limits across the entire industry with greenhouse gas pricing. Developing green shipping by integrating new energy technologies with ship electrical systems can effectively alleviate the energy crisis and environmental pollution problems, and is more conducive to achieving the strategic goal of "carbon neutrality" by 2060.

[0003] Fuel cells, as clean and efficient power generation devices, boast advantages such as high energy conversion efficiency, low noise operation, and near-zero pollution emissions. Their main byproduct is water, thus, when applied to navigation propulsion systems, they can effectively reduce emissions of greenhouse gases and air pollutants such as carbon dioxide and nitrogen oxides, significantly contributing to improving the atmospheric environment of ports and shipping routes. Meanwhile, lithium batteries, with their high energy conversion efficiency, excellent instantaneous power response, and long cycle life, can achieve pollution-free operation under electric drive, providing stable and clean energy support for shipping systems. Using fuel cells and lithium batteries as the core energy source for ship propulsion can not only effectively reduce dependence on traditional fossil fuels and minimize environmental damage during ship operation, but also play a crucial role in addressing global energy shortages and promoting the green and low-carbon transformation of the shipping industry. However, in the complex and ever-changing real-world scenarios of ship operation, ensuring the stable lifespan of fuel cells and lithium batteries and reducing their total life-cycle costs remain key challenges that need to be addressed.

[0004] Superconducting energy storage systems (SMES), as a novel marine propulsion energy source, possess unique advantages such as near 100% charge / discharge efficiency, extremely high power density, and millisecond-level rapid response. They can provide or absorb high-power electrical energy under transient conditions, ensuring the stability and safety of the ship's electrical system. Unlike fuel cells, which primarily provide continuous power, and lithium batteries, which mainly provide medium- to long-term energy support, superconducting energy storage is better suited for handling short-term impact loads and rapid dynamic adjustments, demonstrating an irreplaceable role in high-power fluctuations, start-up and shutdown conditions, and power quality management. Therefore, applying superconducting energy storage in conjunction with fuel cells and lithium batteries in marine propulsion systems can not only improve the system's flexibility and robustness and effectively extend the lifespan of fuel cells and lithium batteries, but also achieve the goal of multi-energy complementarity and optimized operation in green shipping.

[0005] Based on the respective advantages of fuel cells, lithium batteries, and superconducting energy storage, the synergy of the three as a marine power system can achieve efficient complementarity: fuel cells provide continuous and clean basic power, lithium batteries are responsible for medium- and long-term energy support and smooth load fluctuations, while superconducting energy storage can quickly adjust power under transient conditions, alleviate sudden loads and start-stop shocks, thereby significantly improving the system's dynamic response capability, energy utilization efficiency, and overall reliability, forming a stable, efficient, and green multi-source power supply system.

[0006] Based on the characteristics of the aforementioned multi-source propulsion systems for ships, refined energy management of each energy unit is necessary to ensure the safety and economy of ship operation. Since fuel cells, lithium batteries, and superconducting energy storage differ in power response speed, energy capacity, and lifespan, the system must rationally allocate the output of each energy source to meet both the ship's instantaneous and continuous load demands while avoiding overload or deep cycling of a single energy source, thereby extending the overall system lifespan. Among these, fuel cells and batteries, as core energy sources, are significantly affected by power fluctuations, frequent load changes, and high-rate operation. Therefore, energy management strategies must not only focus on energy balance and efficiency optimization but also prioritize controlling the output power fluctuations of fuel cells and batteries to slow down their degradation rate and achieve safe, efficient, and sustainable multi-source propulsion operation for ships.

[0007] Existing collaborative solutions suffer from inaccurate fuel cell lifespan modeling, lack of consideration for multi-objective optimization, and inadequate optimization strategies, resulting in suboptimal results. Furthermore, these issues arise due to the simplistic modeling and basic optimization methods used, leading to poor multi-objective collaborative optimization and energy waste. Summary of the Invention

[0008] The purpose of this application is to provide a multi-objective zero-carbon ship energy management method, system, equipment, medium and product to solve the problem of energy waste caused by poor multi-objective collaborative optimization.

[0009] To achieve the above objectives, this application provides the following solution: Firstly, this application provides a multi-objective zero-carbon ship energy management method, including: A quantitative characterization model of operating conditions and degradation was constructed based on fuel cell degradation experimental data and the HDBSCAN clustering algorithm. A multi-source power system model for ships is constructed based on the aforementioned operating condition-degradation quantitative characterization model and actual ship vehicle data; wherein, the multi-source power system for ships includes fuel cells, batteries and superconducting energy storage; the multi-source power system model for ships includes a fuel cell coupled degradation model, a lithium battery multi-mechanism degradation model and a superconducting energy storage electrothermal coupling model; Based on the power balance constraints and operational constraints of the ship's multi-source power system, an objective function for the ship's multi-source power system model is established. By combining the TCN prediction model, the MPC multi-objective energy management strategy is determined according to the objective function, and energy management is carried out according to the MPC multi-objective energy management strategy to achieve multi-objective collaborative optimization.

[0010] Secondly, this application provides a multi-objective zero-carbon ship energy management system, comprising: The operating condition-degradation quantitative characterization model construction module is used to construct an operating condition-degradation quantitative characterization model based on fuel cell degradation experimental data and the HDBSCAN clustering algorithm. The ship multi-source power system model construction module is used to construct a ship multi-source power system model based on the operating condition-degradation quantitative characterization model and ship real vehicle data; wherein, the ship multi-source power system includes fuel cells, batteries and superconducting energy storage; the ship multi-source power system model includes a fuel cell coupling degradation model, a lithium battery multi-mechanism degradation model and a superconducting energy storage electrothermal coupling model; The objective function establishment module is used to establish the objective function of the ship's multi-source power system model based on the power balance constraints and operational constraints of the ship's multi-source power system. The energy management module is used to combine the TCN prediction model, determine the MPC multi-objective energy management strategy according to the objective function, and perform energy management according to the MPC multi-objective energy management strategy to achieve multi-objective collaborative optimization.

[0011] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described multi-objective zero-carbon ship energy management method.

[0012] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described multi-objective zero-carbon ship energy management method.

[0013] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the above-described multi-objective zero-carbon ship energy management method.

[0014] According to the specific embodiments provided in this application, this application has the following technical effects: This application constructs a quantitative characterization model of operating conditions and degradation using a density-based hierarchical clustering algorithm (HDBSCAN). Combined with real-vehicle ship data, it builds a multi-source ship propulsion system model including a fuel cell coupled degradation model, a lithium battery multi-mechanism degradation model, and a superconducting magnetic energy storage electrothermal coupling model. Furthermore, it incorporates a time convolutional network (TCN) prediction model. Based on the objective function of the multi-source ship propulsion system model, it determines a multi-objective model predictive control (MPC) energy management strategy for energy management, achieving multi-objective collaborative optimization. This strategy comprehensively considers the durability, economy, and reliability of the multi-source ship propulsion system, enabling refined system lifespan management and achieving the goal of using fuel cells as the primary baseload power source, lithium batteries as the primary energy buffer, and superconducting magnetic energy storage systems (Superconducting Magnetic Energy Storage System) as the primary energy source. Storage (MES) serves as a multi-source collaborative management and control mechanism for power buffers. By combining TCN and MPC, this application can achieve collaborative optimization of multiple objectives such as fuel cell lifespan, hydrogen consumption, power fluctuation, and load demand, thereby avoiding energy waste. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A schematic flowchart of a multi-objective zero-carbon ship energy management method provided in an embodiment of this application; Figure 2A flowchart of the MPC multi-objective energy management strategy provided in an embodiment of this application; Figure 3 This is a schematic diagram of the UI curve in a cyclic operating condition experiment provided in one embodiment of this application; Figure 4 A schematic diagram of the power-time curve in a cyclic operating condition experiment is provided for one embodiment of this application; Figure 5 This is a schematic diagram of HDBSCAN clustering results provided in an embodiment of this application; Figure 6 This is a schematic diagram of an MPC that integrates TCN according to an embodiment of this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0018] To make the objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] like Figures 1-2 As shown in the figure, this application provides a multi-objective zero-carbon ship energy management method, including: S1: Construct a quantitative characterization model of operating conditions and degradation based on fuel cell degradation experimental data and the HDBSCAN clustering algorithm.

[0020] S2: Construct a multi-source power system model for ships based on the operating condition-degradation quantitative characterization model and actual ship vehicle data; wherein, the multi-source power system for ships includes fuel cells, batteries and superconducting energy storage; the multi-source power system model for ships includes a fuel cell coupled degradation model, a lithium battery multi-mechanism degradation model and a superconducting energy storage electrothermal coupling model.

[0021] S3: Based on the power balance constraints and operational constraints of the ship's multi-source power system, establish the objective function of the ship's multi-source power system model.

[0022] S4: Combining the TCN prediction model, determine the MPC multi-objective energy management strategy according to the objective function, and perform energy management according to the MPC multi-objective energy management strategy to achieve multi-objective collaborative optimization.

[0023] In an exemplary embodiment, S1 specifically includes: S11: Obtain the UI curve of a healthy battery under operating conditions, extract the ohmic segment curve data, and determine the curve slope; the curve slope is the internal resistance value of the fuel cell at different times.

[0024] S12: Determine the internal resistance difference between the UI curves corresponding to the acquisition frequency based on the internal resistance value; the internal resistance difference between the UI curves is the attenuation amount after each acquisition.

[0025] S13: Use the HDBSCAN clustering algorithm to perform unsupervised clustering on the operating condition data to determine the different types of clustering results corresponding to the different operating conditions of the fuel cell; the clustering results include noise, initial operating condition, low operating condition, medium operating condition and high operating condition.

[0026] S14: Based on the clustering results, using the time spent operating under low, medium, and high operating conditions as independent variables and the internal resistance difference as the dependent variable, a linear fitting relationship is constructed to determine the operating condition-attenuation quantitative characterization model.

[0027] In practical applications, starting from a healthy battery (0 hours of operation) to 2200 hours, the UI curve of the fuel cell operating under steady-state cyclic conditions is collected every 200 hours, and the ohmic segment curve data is extracted, such as... Figure 3 As shown, the slope of the curve is obtained, which represents the internal resistance of the fuel cell at different times: Further obtain the internal resistance difference between the UI curves every 200 hours after time 0: This internal resistance difference can represent the amount of decay after every 200 hours.

[0028] Simultaneously, operating conditions were collected every 200 hours from 0h to 2200h, resulting in 11 cyclic operating condition experiments. Data was collected every 20 seconds, totaling 732,939 data points. Some power operating condition data are shown below. Figure 4 As shown. Furthermore, the HDBSCAN method is used to analyze the above operating condition data (i.e.... Figure 4 Unsupervised clustering is performed on the power operating condition data shown, as shown in equation (1), where, For mutual reachability, The distance between two points is given by 'max', which indicates taking the maximum value. The core distance of point a is the distance from point a to its k-th nearest neighbor. For the minimum cluster size parameter, Let p be the k-th nearest neighbor. Let p be the distance between point p and its k-th nearest neighbor. For cluster stability value, For clusters, For points in a cluster, This indicates that for all points in cluster C Perform summation, The distance threshold when point x leaves cluster C. The distance threshold for adding point x to cluster C; then, the different operating conditions of the fuel cell are obtained, and the clustering results are as follows. Figure 5 As shown, -1 represents noise, 0 represents the initial operating condition, and 1, 2, and 3 represent low, medium, and high operating conditions, respectively.

[0029] (1) According to equation (1), we get Figure 4 The clustering results for the -1, 0, 1, 2, and 3 operating conditions are statistically analyzed in each cycle, and the internal resistance difference in that cycle is used for fitting. The internal resistance difference, which characterizes the PEMFC decay, is used as the dependent variable, and the operating time under each operating condition is used as the dependent variable, thus obtaining a quantitative model of operating condition-decay.

[0030] Obtain the low, medium, and high operating time for each cycle in the 11 operating cycles, using the operating time in low, medium, and high conditions as the independent variable, and the internal resistance difference as the variable: Using the dependent variable, a linear fitting relationship is constructed to obtain the working condition-deterioration quantitative model, as shown in equation (2), where Indicates the degradation value of fuel cells, These represent the operating time under low, medium, and high operating conditions, respectively. These represent the degradation coefficients for low, medium, and high operating conditions, respectively: (2) In one exemplary embodiment, the ship's multi-source propulsion system model is constructed as follows: First, the operating conditions of fuel cells are classified and their degradation is quantified, as shown in equation (3), where Represents the minimum mutually reachable distance from point x to cluster C. , The final cluster label, the decay value after classification. It is obtained by calculation using equation (4).

[0031] (3) Define the power fluctuation degradation of fuel cells Thus, a fuel cell coupled degradation model is obtained. As shown in equation (4), where, Indicates the operating condition category corresponding to the cluster label. The decay value under the operating conditions corresponding to the cluster label. Let represent the output power of the fuel cell at time t. Further, the hydrogen consumption model of the fuel cell is defined as shown in equation (5), where... This completes the model construction of the ship's multi-source power system, which includes hydrogen consumption.

[0032] (4) (5) For the marine lithium battery power system model, the battery SOC is first dynamically updated, as shown in equation (6), where The state of charge of the battery at time t, For battery power, This refers to the battery capacity.

[0033] (6) Next, a multi-mechanism degradation model for lithium batteries is established, as shown in equation (7), where, For battery degradation, For battery cycle degradation, For SOC offset degradation, For battery charge / discharge rate degradation, SOC is updated according to equation (6).

[0034] (7) For shipboard superconducting energy storage components, an energy state update model is established, as shown in equation (8), where Let SMES energy be the energy at time t. For SMES power, For SMES capacity.

[0035] (8) Next, a heat loss model for ship superconducting energy storage is established, as shown in equation (9), where For superconducting coil current, For coil inductance, For resistance heat loss, The equivalent resistance for superconducting energy storage. This is for static heat leakage in superconducting energy storage.

[0036] (9) Further, a ship superconducting energy storage cooling model is established, as shown in equation (10), where For cooling power, The coefficient of performance is the cooling factor. The current temperature. To set the temperature.

[0037] (10) A ship superconducting temperature update model, namely the superconducting energy storage electrothermal coupling model, is established based on the ship superconducting energy storage heat loss model and the ship superconducting energy storage cooling model, as shown in equation (11), where, For hot melting, The minimum allowable temperature, This is the maximum permissible temperature.

[0038] (11) The power balance constraint of the ship's multi-source propulsion system is established as shown in equation (12), where, This is the total load requirement.

[0039] (12) The operational constraints of the ship's multi-source propulsion system are further clarified, as shown in equation (13), where , These represent the minimum and maximum power of the fuel cell.

[0040] (13) Finally, the objective function of the ship's multi-source propulsion system (MPC) is established, as shown in equation (14), where These are, respectively, fuel cell degradation weight, battery degradation weight, hydrogen consumption weight, SMES power change weight, fuel cell power change weight, battery power change weight, and load non-compliance penalty weight; For changes in fuel cell power; This refers to changes in battery power. For load power requirements; The power provided.

[0041] (14) The first three terms are equations (4), (5), and (7), the fourth and fifth terms are the power fluctuations of each component, i.e. the power difference between the preceding and following time points, and the last term is the difference between the power provided by the system and the required power.

[0042] In practical applications, the MPC energy management method for zero-carbon ship multi-source propulsion systems is as follows: First, the TCN model is established, as shown in equation (15), where, The input sequence is the current load demand data, where T is the time step and d is the dimension of the input features. For the first Layer at time Feature representation, For convolution kernel weights, For bias, The kernel size is [size]. For expansion rate, The input layer is equal to the original sequence. For activation function, For residual connection, For the process The output after layer stacking For the predicted output of the fully connected layer, This is the output layer weight matrix. This is the output layer bias vector.

[0043] (15) Furthermore, the energy management optimization strategy for the ship's multi-source propulsion system is solved in MPC using a sequential quadratic programming method, as shown in equation (16), where To optimize variables, To obtain the optimal solution, Let be the objective function, i.e., equation (14). For inequality constraints, This is an equality constraint.

[0044] (16) The final energy allocation result is as follows Figure 6 As shown in the figure, the fuel cell provides stable high power output, the battery supports frequent load changes, and the superconducting energy storage provides support under sudden load changes.

[0045] This application also provides a multi-objective zero-carbon ship energy management system, including: The operating condition-degradation quantitative characterization model construction module is used to construct an operating condition-degradation quantitative characterization model based on fuel cell degradation experimental data and the HDBSCAN clustering algorithm.

[0046] The ship multi-source power system model construction module is used to construct a ship multi-source power system model based on the operating condition-degradation quantitative characterization model and ship real vehicle data; wherein, the ship multi-source power system includes fuel cells, batteries and superconducting energy storage; the ship multi-source power system model includes a fuel cell coupled degradation model, a lithium battery multi-mechanism degradation model and a superconducting energy storage electrothermal coupling model.

[0047] The objective function establishment module is used to establish the objective function of the ship's multi-source power system model based on the power balance constraints and operational constraints of the ship's multi-source power system.

[0048] The energy management module is used to combine the TCN prediction model, determine the MPC multi-objective energy management strategy according to the objective function, and perform energy management according to the MPC multi-objective energy management strategy to achieve multi-objective collaborative optimization.

[0049] This application uses fuel cells, batteries, and superconducting energy storage as the multi-source power system of the ship. The fuel cell bears the base load power, the lithium battery smooths out short- and medium-term power fluctuations, and the SMES responds to transient peak loads. The functions are allocated based on the differences in the technical characteristics of each component to avoid overload of a single component and maximize the overall efficiency and lifespan of the system.

[0050] By combining the design degradation calculation logic with the actual operating conditions of components, a refined fuel cell life modeling that integrates HDBSCAN operating condition classification is proposed to improve the accuracy of life assessment and optimization. Combined with the TCN-based MPC multi-objective energy management strategy, long-life, high-stability, and low-cost energy management of ship multi-source power systems can be achieved.

[0051] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments. The computer device can be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, memory, and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device stores data to be processed. The I / O interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with an external terminal via a network connection. When the computer program is executed by the processor, it implements the above-described methods.

[0052] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0053] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0054] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0055] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0056] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by hardware related to computer program instructions. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0057] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0058] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0059] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A multi-objective zero-carbon ship energy management method, characterized in that, include: A quantitative characterization model of operating conditions and degradation was constructed based on fuel cell degradation experimental data and the HDBSCAN clustering algorithm. A multi-source power system model for ships is constructed based on the aforementioned operating condition-degradation quantitative characterization model and actual ship vehicle data; wherein, the multi-source power system for ships includes fuel cells, batteries and superconducting energy storage; the multi-source power system model for ships includes a fuel cell coupled degradation model, a lithium battery multi-mechanism degradation model and a superconducting energy storage electrothermal coupling model; Based on the power balance constraints and operational constraints of the ship's multi-source power system, an objective function for the ship's multi-source power system model is established. By combining the TCN prediction model, the MPC multi-objective energy management strategy is determined according to the objective function, and energy management is carried out according to the MPC multi-objective energy management strategy to achieve multi-objective collaborative optimization.

2. The multi-objective zero-carbon ship energy management method according to claim 1, characterized in that, Based on fuel cell degradation experimental data and the HDBSCAN clustering algorithm, a quantitative characterization model of operating conditions and degradation was constructed, specifically including: The UI curve of a healthy battery under operating conditions is obtained, and the ohmic segment curve data is extracted to determine the curve slope; the curve slope is the internal resistance value of the fuel cell at different times. The internal resistance difference between the UI curves corresponding to the sampling frequency is determined based on the internal resistance value; the internal resistance difference between the UI curves is the attenuation amount after each sampling. The HDBSCAN clustering algorithm is used to perform unsupervised clustering on the operating condition data to determine different types of clustering results corresponding to different operating conditions of the fuel cell; the clustering results include noise, initial operating condition, low operating condition, medium operating condition and high operating condition. Based on the clustering results, a linear fitting relationship is constructed with the time spent operating under low, medium, and high operating conditions as independent variables and the internal resistance difference as the dependent variable, to determine the operating condition-attenuation quantitative characterization model.

3. The multi-objective zero-carbon ship energy management method according to claim 1, characterized in that, The fuel cell coupling degradation model for: in, , For the power fluctuation degradation of fuel cells, Let be the output power of the fuel cell at time t+1. Let be the output power of the fuel cell at time t; , This indicates the operating condition category corresponding to the cluster label. This represents the decay value under the operating conditions corresponding to the cluster label.

4. The multi-objective zero-carbon ship energy management method according to claim 3, characterized in that, The lithium battery multi-mechanism degradation model for: in, Due to battery cycle degradation, , For battery power, For battery capacity, , All are battery cycle degradation coefficients; SOC offset degradation, , SOC The battery is in its state of charge. For battery charge / discharge rate degradation, .

5. The multi-objective zero-carbon ship energy management method according to claim 4, characterized in that, The superconducting energy storage electrothermal coupling model is as follows: in, For temperature difference; Cooling power; For power loss; For hot melting; For time intervals; The temperature at time t+1; Let t be the temperature at time t; Minimum allowable temperature; This is the maximum permissible temperature.

6. The multi-objective zero-carbon ship energy management method according to claim 5, characterized in that, The objective function J for: in, These are, respectively, fuel cell degradation weight, battery degradation weight, hydrogen consumption weight, SMES power change weight, fuel cell power change weight, battery power change weight, and load non-compliance penalty weight; This refers to hydrogen consumption. For changes in fuel cell power; This refers to changes in battery power. For load power requirements; The power provided.

7. A multi-objective zero-carbon ship energy management system, characterized in that, include: The operating condition-degradation quantitative characterization model construction module is used to construct an operating condition-degradation quantitative characterization model based on fuel cell degradation experimental data and the HDBSCAN clustering algorithm. The ship multi-source power system model construction module is used to construct a ship multi-source power system model based on the operating condition-degradation quantitative characterization model and ship real vehicle data; wherein, the ship multi-source power system includes fuel cells, batteries and superconducting energy storage; the ship multi-source power system model includes a fuel cell coupling degradation model, a lithium battery multi-mechanism degradation model and a superconducting energy storage electrothermal coupling model; The objective function establishment module is used to establish the objective function of the ship's multi-source power system model based on the power balance constraints and operational constraints of the ship's multi-source power system. The energy management module is used to combine the TCN prediction model, determine the MPC multi-objective energy management strategy according to the objective function, and perform energy management according to the MPC multi-objective energy management strategy to achieve multi-objective collaborative optimization.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the multi-objective zero-carbon ship energy management method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the multi-objective zero-carbon ship energy management method as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the multi-objective zero-carbon ship energy management method as described in any one of claims 1-6.

Images