A method and system for evaluating adjustable power margin of a multi-energy power system of a ship

Abstract

The application relates to the technical field of ship energy management, and particularly relates to a ship multi-energy power system adjustable power margin evaluation method and system. The method obtains ship multi-energy power system operation state data, identifies a current sailing working condition and predicts load demand in an evaluation time domain; in combination with the load prediction result, a power source adjustable power boundary model, a load side regulation model and a system safety constraint model are respectively constructed to determine power source regulation capacity, load regulation range and system operation constraint boundary; on this basis, system adjustable power margin is calculated, and power regulation duration, response rate and margin reliability are further evaluated to generate a ship multi-energy power system adjustable power margin evaluation result. The application realizes dynamic and accurate evaluation of the adjustable power margin of the ship multi-energy power system, thereby improving the reliability of power regulation decision, system operation safety and energy utilization efficiency.

Description

Technical Field

[0001] This application relates to the field of ship energy management technology, and in particular to a method and system for evaluating the adjustable power margin of a ship's multi-energy propulsion system. Background Technology

[0002] In related technologies, with the continuous improvement of the green, low-carbon, electrified, and intelligent levels of ships, ship propulsion systems are gradually evolving from traditional single-engine diesel propulsion to multi-energy coordinated power supply. Such systems typically include fuel cells, lithium batteries, supercapacitors, diesel generators, shore power interfaces, DC buses, power electronic converters, propulsion motors, and auxiliary loads. A ship energy management system coordinates the power of different energy units to meet the needs of propulsion loads, auxiliary loads, and safe ship operation. Compared to traditional propulsion systems, multi-energy ship propulsion systems are characterized by diverse energy types, complex power flow, significant differences in equipment response characteristics, and numerous operational constraints.

[0003] However, existing energy management methods for multi-energy propulsion systems on ships lack online assessment of the system's adjustable power margin before power allocation. Current methods typically allocate power based on current load demand, equipment rated power, battery state of charge, or preset control rules, making it difficult to accurately determine the actual safe power range that each energy unit can safely adjust up or down under current operating conditions. Factors such as fuel cell ramp rate, temperature, and hydrogen / oxygen supply status; lithium battery SOC, temperature, and BMS power limiting strategies; supercapacitor remaining energy; and diesel generator startup status and minimum stable power all affect the true adjustable capability. If rated power or fixed rules are still used as the allocation basis, it can easily lead to problems such as power command inaction, fuel cell response lag, battery overcharging and over-discharging, converter overload, DC bus voltage fluctuations, or insufficient propulsion power. Furthermore, propulsion and auxiliary loads fluctuate significantly during port entry / exit, acceleration, deceleration, turning, reversing, or emergency maneuvering. Traditional energy management methods struggle to predict power support capacity, duration, and response rate at different time scales, resulting in insufficient perception of system safety margins.

[0004] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0005] The main objective of this application is to propose a method and system for evaluating the adjustable power margin of a ship's multi-energy propulsion system, so as to achieve dynamic and accurate evaluation of the adjustable power margin of the ship's multi-energy propulsion system, thereby improving the reliability of power regulation decisions, system operation safety and energy utilization efficiency.

[0006] To achieve the above objectives, one aspect of this application proposes a method for evaluating the adjustable power margin of a ship's multi-energy propulsion system, the method comprising the following steps: Acquire operational status data of ship multi-energy propulsion systems; Based on the operational status data, the current operating condition of the ship is identified, and the load demand within the preset evaluation time domain is predicted to obtain the load prediction result. Based on the operating status data and the load prediction results, an adjustable power boundary model for each power source is constructed to obtain the adjustable power boundary for each power source. Based on the operational status data and the load forecast results, a load-side adjustment model is constructed to obtain the load adjustment boundary. Based on the adjustable power boundary and the load adjustment boundary, a system safety constraint model is constructed to obtain the system operation constraint boundary; Based on the adjustable power boundary, the load prediction results, the load adjustment boundary, and the system operation constraint boundary, calculate the system adjustable power margin; Based on the adjustable power margin of the system, the power regulation duration, response rate, and margin reliability are determined, and an adjustable power margin evaluation result is generated.

[0007] In some embodiments, the operating status data includes power source status data, energy storage status data, load status data, power network status data, and navigation condition data.

[0008] In some embodiments, the step of identifying the ship's current operating condition based on the operating status data and predicting the load demand within a preset assessment time domain to obtain a load prediction result includes: Based on the operational status data, operating condition characteristic parameters are extracted; these parameters include ship speed, propulsion power, propulsion motor speed, control commands, load change rate, and historical operational data. Based on the aforementioned operating condition characteristic parameters, the current operating status of the ship is identified, and an operating condition identification result is generated. Based on the operating condition identification results, the operating status data, and historical operating data, a load demand prediction model is constructed. Based on the load demand prediction model, the propulsion load demand and auxiliary load demand within the preset evaluation time domain are predicted to obtain the load prediction results. Based on the load forecast results, the total load demand forecast results for the corresponding evaluation time domain are generated.

[0009] In some embodiments, the step of constructing adjustable power boundary models for each power source based on the operating status data and the load prediction results, to obtain the adjustable power boundaries for each power source, includes: Based on the operating status data, the status parameters of each power source are extracted; the status parameters of each power source include the rated power parameters, real-time output power parameters, operating status parameters and power regulation constraint parameters of each power source. Based on the power source state parameters and the load prediction results, adjustable power boundary models for each power source are established; the adjustable power boundary models for each power source include adjustable power boundary models for fuel cells, lithium batteries, supercapacitors, and diesel generators. Based on the adjustable power boundary models of each power source, the adjustable power boundary of the fuel cell, the adjustable power boundary of the lithium battery, the adjustable power boundary of the supercapacitor, and the adjustable power boundary of the diesel generator are determined respectively. The adjustable power boundaries of each power source are integrated to generate the adjustable power boundaries of each power source.

[0010] In some embodiments, the step of constructing a load-side adjustment model based on the operating status data and the load forecast results to obtain the load adjustment boundary includes: Based on the operational status data and the load forecast results, load-side status parameters are extracted; the load-side status parameters include driving load parameters, auxiliary load parameters, load priority parameters, and load regulation constraint parameters. Based on the load-side state parameters and the load forecast results, a load-side adjustment model is established; Based on the load-side adjustment model, the adjustable power range and the power reduction range on the load side are determined. Based on the adjustable power range and the power reduction range on the load side, a load adjustment boundary is generated.

[0011] In some embodiments, the step of constructing a system safety constraint model based on the adjustable power boundary and the load adjustment boundary to obtain the system operation constraint boundary includes: Based on the adjustable power boundary, the load prediction results, and the load adjustment boundary, system operation constraint parameters are extracted; the system operation constraint parameters include DC bus voltage parameters, DC bus current parameters, converter capacity parameters, power balance parameters, and equipment operation limit parameters; Based on the system operation constraint parameters, a system safety constraint model is constructed; Based on the system safety constraint model, the DC bus power balance constraint boundary, the DC bus voltage constraint boundary, and the converter operation constraint boundary are determined. Based on the DC bus power balance constraint boundary, the DC bus voltage constraint boundary, and the converter operation constraint boundary, the system operation constraint boundary is generated.

[0012] In some embodiments, calculating the system adjustable power margin based on the adjustable power boundary, the load forecast result, the load adjustment boundary, and the system operating constraint boundary includes: The effective adjustable power of the system is determined based on the adjustable power boundary, the load adjustment boundary, and the system operation constraint boundary. Based on the effective regulation power of the system and the load prediction results, the system upward power margin and the system downward power margin are calculated under different evaluation time domains respectively. Based on the system's upward and downward power margins under different evaluation time domains, margin aggregation calculations are performed to generate the system's adjustable power margin.

[0013] In some embodiments, the formula for calculating the system's power margin is as follows: ; in, This indicates the system-level power margin adjustment; t represents the current evaluation time. Indicates the duration of power margin; Represents the allowable upward power limit under system constraints; i represents the first... One energy unit; Indicates the first The credibility coefficient of each energy unit; Indicates the first The response speed correction factor for each energy unit; Indicates the first Duration correction factor for each energy unit; Indicates the first Each energy unit at the current moment Duration Internal power margin adjustment; This indicates that power can be reduced for non-critical loads; The formula for calculating the system's power margin is as follows: ; in, This indicates a system-level power margin reduction. This represents the allowable power reduction boundary under system constraints; Indicates the first Each energy unit at the current moment Duration Internal power margin; This indicates that the load power can be increased or the power can be absorbed.

[0014] In some embodiments, determining the power regulation duration, response rate, and margin confidence based on the system's adjustable power margin, and generating an adjustable power margin assessment result, includes: Based on the adjustable power margin of the system and the adjustable power boundaries of each power source, the power adjustment duration is determined and the power adjustment duration result is generated. Based on the adjustable power margin of the system, the power ramping capability and dynamic response characteristics of each power source, the system power regulation response rate is determined and the response rate evaluation result is generated. Based on the load forecast results, equipment operating status, historical response data, and operating condition identification results, a margin reliability evaluation model is constructed. Based on the margin credibility evaluation model, the credibility of the adjustable power margin of the system is evaluated to obtain the margin credibility result. Based on the power regulation duration result, the response rate evaluation result, the margin confidence result, and the system adjustable power margin, an adjustable power margin evaluation result is generated.

[0015] To achieve the above objectives, another aspect of this application proposes an adjustable power margin assessment system for a ship's multi-energy propulsion system, the system comprising: The data acquisition module is used to acquire the operating status data of the ship's multi-energy propulsion system; The load forecasting module is used to identify the current operating conditions of the ship based on the operating status data, and to forecast the load demand within a preset evaluation time domain to obtain the load forecasting result. The first construction module is used to construct an adjustable power boundary model for each power source based on the operating status data and the load prediction results, so as to obtain the adjustable power boundary of each power source. The second construction module is used to construct a load-side adjustment model based on the operating status data and the load prediction results, and obtain the load adjustment boundary. The third construction module is used to construct a system safety constraint model based on the adjustable power boundary and the load adjustment boundary, and obtain the system operation constraint boundary; The power margin calculation module is used to calculate the adjustable power margin of the system based on the adjustable power boundary, the load prediction result, the load adjustment boundary, and the system operation constraint boundary. The result generation module is used to determine the power adjustment duration, response rate, and margin confidence based on the adjustable power margin of the system, and generate adjustable power margin evaluation results.

[0016] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0017] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0018] To achieve the above objectives, another aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0019] The embodiments of this application include at least the following beneficial effects: This application provides a method and system for assessing the adjustable power margin of a ship's multi-energy propulsion system. This scheme acquires the operating status data of the ship's multi-energy propulsion system and combines it with the identification of the current operating conditions and the prediction of load demand within a preset assessment time domain to achieve early perception of the future power demand change trend of the ship, avoiding the lag in assessment results caused by static judgment based solely on instantaneous operating data. By constructing adjustable power boundary models and load-side adjustment models for each power source respectively, the system's adjustable power capability can be characterized from both the energy supply and energy consumption sides, improving the completeness and accuracy of the adjustable power margin assessment. Simultaneously, a system safety constraint model is constructed based on the adjustable power boundary and load adjustment boundary, incorporating power source output limits, load adjustment limits, and system operation safety requirements into the assessment process. This makes the calculated system adjustable power margin more consistent with actual operating conditions, reducing the risk of equipment damage or system instability caused by over-limit adjustments. Furthermore, by determining the power adjustment duration, response rate, and margin reliability based on the system's adjustable power margin, a multi-dimensional adjustable power margin assessment result can be generated, providing a reliable basis for ship energy management, power allocation, emergency response, and load reduction, thereby improving the operational safety, adjustment flexibility, and energy utilization efficiency of the ship's multi-energy propulsion system. Attached Figure Description

[0020] Figure 1 This is a flowchart illustrating a method for evaluating the adjustable power margin of a ship's multi-energy propulsion system, as provided in an embodiment of this application. Figure 2 This is a schematic diagram of the structure of the multi-energy propulsion system for new energy ships provided in the embodiments of this application; Figure 3 yes Figure 1 A flowchart illustrating step S3 in the process; Figure 4 yes Figure 1 A flowchart illustrating step S6 in the process; Figure 5 This is a schematic diagram of a module of an adjustable power margin assessment system for a multi-energy propulsion system of a ship, provided in an embodiment of this application. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0022] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0023] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0025] Before providing a detailed description of the embodiments of this application, some of the nouns and terms involved in the embodiments of this application will be explained first. The nouns and terms involved in the embodiments of this application are subject to the following interpretations.

[0026] The FC side refers to the fuel cell side, which is the power supply side of the ship's multi-energy power system with the fuel cell system as the main body. It includes the fuel cell stack and its output end, the FC-DC / DC converter connection end and related status monitoring units. It is used to provide a relatively stable power output to the DC bus. Its adjustable power capability is affected by factors such as fuel cell output power, stack voltage, stack current, stack temperature, hydrogen and oxygen supply status and ramp rate. A DC / DC converter is a device used to boost, buck, or bidirectionally convert DC power, enabling energy units of different voltage levels, such as fuel cells, lithium batteries, and supercapacitors, to perform power matching and energy exchange with the DC bus, and to achieve up-regulation, down-regulation, charging, or discharging control according to power regulation commands. AC / DC rectifiers are devices that convert AC power from diesel generator sets or shore power interfaces into DC power, which is then connected to the DC bus to achieve power conversion and transmission between AC power supply and the ship's DC power distribution system. EMS refers to the ship's energy management system, which is used to collect operating status data of fuel cells, lithium batteries, supercapacitors, diesel generator sets, shore power interfaces, DC buses, propulsion loads and auxiliary loads, and to perform energy scheduling, power allocation and operation control based on load demand, system constraints and power margin assessment results. SOC refers to the state of charge of a lithium battery, which represents the ratio between the current remaining capacity of the lithium battery and its rated capacity. It is an important parameter for judging the discharge capacity, recharge capacity, adjustable power boundary of a lithium battery, and whether the power limiting strategy of the BMS is triggered.

[0027] This application provides a method and system for assessing the adjustable power margin of a ship's multi-energy propulsion system. This method acquires the operating status data of the ship's multi-energy propulsion system and combines it with current operating condition identification and load demand prediction within a preset assessment time domain. This allows for early perception of future power demand trends, avoiding the lag in assessment results caused by static judgments based solely on instantaneous operating data. By constructing adjustable power boundary models and load-side adjustment models for each power source, the system's adjustable power capability can be characterized from both the energy supply and consumption sides, improving the completeness and accuracy of the adjustable power margin assessment. Simultaneously, a system safety constraint model is constructed based on the adjustable power boundary and load adjustment boundary, incorporating power source output limits, load adjustment limits, and system operational safety requirements into the assessment process. This ensures that the calculated adjustable power margin better reflects actual operating conditions, reducing the risk of equipment damage or system instability due to over-limit adjustments. Furthermore, by determining the power adjustment duration, response rate, and margin reliability based on the system's adjustable power margin, a multi-dimensional adjustable power margin assessment result can be generated, providing a reliable basis for ship energy management, power allocation, emergency response, and load reduction, thereby improving the operational safety, adjustment flexibility, and energy utilization efficiency of the ship's multi-energy propulsion system.

[0028] This application provides a method for assessing the adjustable power margin of a ship's multi-energy propulsion system, relating to the field of ship energy management technology. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or vehicle-mounted terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application implementing the method for assessing the adjustable power margin of a ship's multi-energy propulsion system, but is not limited to the above forms.

[0029] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0030] Figure 1 This is an optional flowchart of a method for evaluating the adjustable power margin of a ship's multi-energy propulsion system, provided in an embodiment of this application. Figure 1 The method may include, but is not limited to, steps S1 to S7: S1: Acquire operational status data of the ship's multi-energy propulsion system; this operational status data includes power source status data, energy storage status data, load status data, power network status data, and navigation condition data.

[0031] In this embodiment, the ship's multi-energy propulsion system operating status data is collected in real time through the ship's energy management system, fuel cell controller, battery management system, supercapacitor management unit, diesel generator controller, shore power interface monitoring unit, DC bus monitoring device, propulsion motor controller, converter controller, load monitoring unit, and navigation status acquisition device. This power source status data includes fuel cell output power, stack voltage, stack current, stack temperature, cooling water temperature, hydrogen pressure, air flow rate, oxygen excess coefficient, diesel generator operating status, diesel generator current power, maximum available power, minimum stable power, start-up status, start-up time, ramp rate, shore power connection status, and available shore power.

[0032] refer to Figure 2 As shown, Figure 2 This is a schematic diagram of the multi-energy propulsion system for new energy ships, used to illustrate the connection relationships and power flow between various power sources, energy storage units, converters, DC buses, load terminals, and the ship's energy management system.

[0033] Specifically, the fuel cell system is connected to the DC bus via an FC-side DC / DC converter, the lithium battery system is connected to the DC bus via a battery-side DC / DC converter, and the supercapacitor system is connected to the DC bus via a supercapacitor-side DC / DC converter. The fuel cell system primarily provides a relatively stable base power supply, the lithium battery system provides short- to medium-term power support and energy regulation, and the supercapacitor system provides transient power compensation and bus voltage fluctuation suppression. The diesel generator set is connected to the DC bus via an AC / DC rectifier and can serve as a backup or supplementary power source for medium- to long-term power support; the shore power interface can supply power to the DC bus during berthing or under specific operating conditions.

[0034] The DC bus serves as the core channel for the collection and distribution of power from multiple energy sources. It receives electrical energy from fuel cells, lithium batteries, supercapacitors, diesel generator sets, and shore power interfaces, and distributes power to propulsion and auxiliary loads. The propulsion inverter connects the DC bus to the propulsion motor, converting the DC bus power into the necessary energy to drive the ship's propulsion system. The auxiliary load distribution unit connects the DC bus to auxiliary equipment such as pumps, air conditioners, and lighting, supplying power to the ship's auxiliary loads.

[0035] The ship's Energy Management System (EMS) is used to monitor and coordinate the operation status of fuel cell systems, lithium battery systems, supercapacitor systems, diesel generator sets, shore power interfaces, DC buses, propulsion loads, and auxiliary loads. In the embodiments of this application, the EMS can perform operating condition identification, load prediction, adjustable power boundary modeling for each power source, load-side adjustment boundary determination, system safety constraint verification, and system adjustable power margin calculation based on the status data of each power source, energy storage status data, load status data, power network status data, and navigation condition data. This yields evaluation results such as upward adjustment power margin, downward adjustment power margin, power adjustment duration, response rate, and margin reliability, providing a basis for the safe operation and power allocation of the ship's multi-energy propulsion system.

[0036] Energy storage status data includes lithium battery SOC, battery voltage, battery current, battery temperature, maximum allowable charging power, maximum allowable discharging power, BMS power limiting status, supercapacitor terminal voltage, remaining energy, maximum allowable charging power, and maximum allowable discharging power. Load status data includes propulsion load power, auxiliary load power, critical load power, non-critical auxiliary load power, propulsion motor speed, propulsion motor torque, and propeller load. Power network status data includes DC bus voltage, DC bus current, bus power fluctuation, DC / DC converter power, current, temperature, and capacity limits, AC / DC converter power, current, temperature, and capacity limits, and propulsion inverter power, current, temperature, and capacity limits. Navigation status data includes ship speed, heading, maneuvering commands, target speed, route plan, wind speed, wind direction, wave height, current speed, water depth, and historical load data.

[0037] The sampling period can be set to 0.1 seconds, 1 second, 5 seconds, 10 seconds, 30 seconds, or 1 minute according to system requirements. For scenarios with rapid load fluctuations, a sampling period of 0.1 to 5 seconds is preferred; for conventional energy management scenarios, a sampling period of 5 seconds to 1 minute is preferred.

[0038] After data collection, the operational status data from different sources undergoes timestamp alignment, unit standardization, outlier removal, and missing value compensation. For example, a unified power benchmark conversion is performed for fuel cell output power, lithium battery charging and discharging power, supercapacitor power, and propulsion load power; short-term lost sensor data can be compensated using interpolation of nearby sampled values ​​or the average of historical data under the same operating conditions; data that significantly exceeds the physical limits of the equipment is marked as an anomaly and is not directly included in subsequent margin calculations. Through these processes, an operational status dataset corresponding to the current assessment time is formed.

[0039] S2: Based on operational status data, identify the current operating conditions of the ship and predict the load demand within the preset assessment time domain to obtain the load prediction results; This includes identifying the ship's current operating conditions based on operational status data and predicting load demand within a preset assessment time domain to obtain load prediction results, including: S21: Extract operating condition characteristic parameters based on operational status data; these operating condition characteristic parameters include ship speed, propulsion power, propulsion motor speed, maneuvering commands, load change rate, and historical operating data; S22: Based on the operating condition characteristic parameters, identify the current operating status of the ship and generate the operating condition identification result; S23: Construct a load demand forecasting model based on the operating condition identification results, operating status data, and historical operating data; S24: Based on the load demand forecasting model, the advance load demand and auxiliary load demand within the preset assessment time domain are predicted to obtain the load forecasting results; S25: Based on the load forecast results, generate the total load demand forecast results for the corresponding assessment time domain.

[0040] In this embodiment, operating condition characteristic parameters are extracted based on operational status data to characterize the ship's operational status. These parameters include ship speed, heading, target speed, propulsion power, propulsion motor speed, propulsion motor torque, maneuvering commands, load change rate, shore power connection status, auxiliary load power, and historical operational data. Specifically, data from different sources are synchronized in time and correlated in status, mapping propulsion power, propulsion motor speed, ship speed, and maneuvering commands to the same evaluation time. Combined with historical load change patterns under similar operating conditions, a feature dataset is formed for operating condition identification and load prediction.

[0041] Based on operational condition characteristic parameters, the current operating status of the vessel is identified, generating operational condition identification results. Specifically, rule-based judgment, threshold judgment, or classification models can be used to identify the current operating status. These operational condition identification results include berthing, departure, arrival, low-speed navigation, cruising, acceleration, deceleration, turning, reversing, and emergency operation conditions. For example, when the vessel speed is below a preset threshold, shore power is connected, and propulsion power is close to zero, it is identified as berthing; when the rate of change of propulsion power increases, the propulsion motor speed continuously increases, and the target speed is higher than the current speed, it is identified as acceleration; when propulsion power decreases rapidly and the propulsion motor speed decreases, it is identified as deceleration; and when maneuvering commands change frequently or the side thrusters are engaged, it is identified as turning or maneuvering.

[0042] After obtaining the operating condition identification results, a load demand prediction model is constructed based on the operating condition identification results, operating status data, and historical operating data. Specifically, corresponding load prediction strategies are invoked according to different operating conditions: under cruise conditions, stable load demand is predicted based on current speed, propulsion power, and historical cruise load data; under acceleration, reversing, or turning conditions, short-term propulsion load fluctuations are predicted by combining control commands, propulsion power change rate, and propulsion motor speed change trend; under berthing conditions, the focus is on predicting auxiliary load demands such as air conditioning, ventilation, pump sets, domestic electricity, and energy storage charging; under emergency conditions, priority is given to predicting critical load demands such as navigation and communication, control systems, fire protection systems, and cooling systems.

[0043] Based on the load demand forecasting model, rolling forecasts are performed on the propulsion load demand and auxiliary load demand within a preset assessment time domain to obtain load forecasting results. These results include the propulsion load forecast value, auxiliary load forecast value, load change trend, load peak value, peak occurrence time, and forecast reliability at each forecast time within the assessment time domain. Furthermore, the propulsion load forecasting results and auxiliary load forecasting results at the same forecast time are time-aligned and summarized to generate the total load demand forecasting results for the corresponding assessment time domain. This provides input for subsequent adjustable power boundary modeling of each power source, determination of load-side adjustment boundaries, and calculation of the system's adjustable power margin.

[0044] Specifically, the calculation formula for the load demand forecasting model is as follows: ; in, This represents the predicted total ship load. This indicates the predicted load value. This represents the predicted auxiliary load value; k represents the prediction step number.

[0045] S3: Based on the operating status data and load forecast results, construct the adjustable power boundary model of each power source to obtain the adjustable power boundary of each power source. Among them, reference Figure 3 As shown, based on operating status data and load forecast results, adjustable power boundary models for each power source are constructed, resulting in adjustable power boundaries for each power source, including: S31: Based on the operating status data, extract the status parameters of each power source; the status parameters of each power source include the rated power parameters, real-time output power parameters, operating status parameters and power regulation constraint parameters of each power source; S32: Based on the power source state parameters and load prediction results, establish adjustable power boundary models for each power source; these adjustable power boundary models include adjustable power boundary models for fuel cells, lithium batteries, supercapacitors, and diesel generators. S33: Based on the adjustable power boundary models of each power source, determine the adjustable power boundary of the fuel cell, the adjustable power boundary of the lithium battery, the adjustable power boundary of the supercapacitor, and the adjustable power boundary of the diesel generator respectively. S34: Integrate the adjustable power boundaries of each power source to generate the adjustable power boundaries of each power source.

[0046] In this embodiment, power source status parameters of the fuel cell, lithium battery, supercapacitor, and diesel generator are extracted based on operational status data. These power source status parameters include rated power, real-time output power, operating status, and power regulation constraints. Specifically, fuel cell parameters include stack temperature, hydrogen and oxygen supply status, minimum stable power, and ramp rate; lithium battery parameters include SOC, battery temperature, maximum allowable charge / discharge power, and BMS power limiting status; supercapacitor parameters include terminal voltage, remaining energy, and maximum charge / discharge power; and diesel generator parameters include startup status, startup time, current power, maximum available power, and minimum stable power.

[0047] Based on the power source state parameters and load forecast results, adjustable power boundary models for fuel cells, lithium batteries, supercapacitors, and diesel generators are established respectively. Specifically, the load change trend, peak demand, and duration in the load forecast results are used as demand constraints, and the output capacity, response speed, and operating limitations of each power source are used as power supply constraints to determine the adjustable capacity and adjustable capacity of each power source within the preset evaluation time domain.

[0048] Based on the adjustable power boundary models of each power source, the adjustable power boundaries of each power source are determined separately. For fuel cells, the rise and fall power boundaries are determined under normal operating conditions, and derating corrections are made when there are abnormalities in temperature, hydrogen supply, or cooling. For lithium batteries, the charge and discharge boundaries are determined based on SOC, temperature, and BMS limits. For supercapacitors, the short-term adjustment boundary is determined based on terminal voltage and remaining energy. For diesel generators, the adjustable boundary is determined based on operating conditions, start-up time, and ramping capability. Finally, the rise and fall boundaries, response delays, and durations of each power source are integrated to generate the adjustable power boundaries for each power source.

[0049] Specifically, the process of constructing the adjustable power boundary model for a fuel cell is as follows: For fuel cell systems, an adjustable power boundary model is established, considering rated power, minimum stable power, ramp rate, temperature conditions, hydrogen supply conditions, oxygen supply conditions, and DC / DC converter capacity. The maximum available power of the fuel cell at a future time t+k is expressed as: ; in, This represents the maximum usable power of the fuel cell. This is the rated maximum power of the fuel cell. The allowable power is determined by the stack temperature and cooling conditions. The allowable power is determined by the hydrogen supply pressure and hydrogen flow rate. The permissible power is determined by the air supply and the oxygen excess coefficient. This allows for the transmission of power to the DC / DC converter on the fuel cell side.

[0050] The power margin for fuel cells is: ; The power margin for fuel cells is: ; in, To increase the power margin of the fuel cell, To reduce the power margin of fuel cells, This represents the current output power of the fuel cell. For the minimum stable power of the fuel cell, Due to the power-up rate limitation of fuel cells, To limit the rate of power reduction of the fuel cell, k is the prediction step number. This represents the time length between adjacent prediction times.

[0051] When the temperature, pressure, humidity, cooling status, or fault condition of the fuel cell do not meet the operating requirements, the adjustable power margin of the fuel cell is derating, and the correction factor is denoted as follows. Its value ranges from 0 to 1. The corrected power margin for the fuel cell is: ; in, This indicates an upward adjustment in the power margin of the fuel cell; This represents the derating correction factor for fuel cells, used to characterize the impact of the current operating state of the fuel cell on its adjustable power capability.

[0052] Specifically, the construction process of the adjustable power boundary model for lithium batteries is as follows: For lithium battery systems, an adjustable power boundary model is established that considers SOC, battery temperature, voltage, current rate, BMS limit, and DC / DC converter capacity.

[0053] The maximum allowable discharge power of a lithium battery is expressed as follows: ; The maximum allowable charging power of a lithium battery is expressed as follows: ; in, and These are the maximum allowable discharge power and the maximum allowable charging power of the lithium battery, respectively. and These are the rated maximum discharge and charging power of the lithium battery, respectively. and The discharge and charge power are limited by the SOC. and Power limitations determined by battery temperature. and Power limitation for BMS output, Capacity limitations of the battery-side DC / DC converter.

[0054] The discharge support power of a lithium battery over a duration τ for: ; The rechargeable power absorbed by a lithium battery over a duration τ for: ; in, For the battery's rated capacity, This represents the current state of charge of the lithium battery. and These are the lower and upper limits of the battery's permissible State of Charge (SOC). and These are discharge efficiency and charging efficiency, respectively.

[0055] Specifically, the construction process of the adjustable power boundary model for supercapacitors is as follows: For supercapacitor systems, an adjustable power boundary model is established that considers terminal voltage, remaining energy, maximum charge / discharge power, and converter capacity.

[0056] Supercapacitors can release energy for: ; Supercapacitors can absorb energy for: ; in, This is the equivalent capacitance of a supercapacitor. This is the current terminal voltage. and These are the minimum and maximum allowable voltages, respectively.

[0057] Supercapacitor discharge power over duration τ for: ; The supercapacitor can absorb power during a duration τ. for: ; in, and These refer to the maximum permissible discharge power and the maximum permissible charging power of the supercapacitor. and Supercapacitors can release energy and absorb energy. and This refers to the discharge efficiency and charging efficiency of the supercapacitor.

[0058] Supercapacitors are primarily used for power margin assessment at the second or short minute level, and are preferred for propulsion load surges, bus voltage fluctuation suppression, and dynamic compensation of fuel cells.

[0059] Specifically, the construction process of the adjustable power boundary model for diesel generators is as follows: For hybrid-powered ships with diesel generators, an adjustable power boundary model is established that considers online status, start-up time, maximum power, minimum stable power, and ramp rate.

[0060] When the diesel generator is in operation, its power margin is: ; in, This indicates the power margin of the diesel generator. This indicates the maximum usable power of the diesel generator; This indicates the actual output power of the diesel generator; This indicates the limit on the rate of increase of power output of a diesel generator.

[0061] Its power reduction margin is: ; in, This indicates the power margin of the diesel generator. This indicates the minimum stable power of the diesel generator; This indicates the rate limit for reducing the power output of a diesel generator.

[0062] When the diesel generator is not running, its available power needs to take into account the start-up delay: ; in, Indicates the future duration of the diesel generator The ability to increase power output is then available; This indicates the time required for the diesel generator to start and stably connect to the grid.

[0063] S4: Based on the operating status data and load forecast results, construct a load-side adjustment model and obtain the load adjustment boundary; Based on operational status data and load forecasting results, a load-side adjustment model is constructed to obtain the load adjustment boundary, including: S41: Based on the operating status data and load forecast results, extract the load-side status parameters; these load-side status parameters include the driving load parameters, auxiliary load parameters, load priority parameters, and load regulation constraint parameters. S42: Establish a load-side regulation model based on load-side state parameters and load forecast results; S43: Based on the load-side adjustment model, determine the adjustable power range and the power reduction range on the load side; S44: Generate load adjustment boundaries based on the adjustable power range and the power reduction range on the load side.

[0064] In this embodiment, load-side state parameters are extracted based on operational status data and load forecast results. These load-side state parameters include propulsion load parameters, auxiliary load parameters, load priority parameters, and load regulation constraint parameters. Specifically, propulsion load parameters include propulsion motor power, propulsion motor speed, propulsion motor torque, ship speed, control commands, and propulsion power change rate; auxiliary load parameters include real-time power and operational status of air conditioning, ventilation, pump sets, domestic power, lighting, cooling systems, navigation and communication equipment, and fuel cell auxiliary systems; load priority parameters are used to distinguish between critical and non-critical loads; and load regulation constraint parameters include minimum safe power supply requirements, reduceable duration, delayable operating time, and regulation response time.

[0065] Based on load-side state parameters and load forecast results, a load-side adjustment model is established. Specifically, according to the different attributes of propulsion load, critical auxiliary load, and non-critical auxiliary load, the adjustability of each type of load within a preset evaluation time domain is determined. Propulsion load is mainly limited by navigation mission, minimum speed, maneuvering safety, and propulsion equipment capacity, and is usually not directly reduced, but adjusted by limiting the rate of change of propulsion power or smoothing acceleration commands. Critical auxiliary loads include navigation and communication, control systems, fire protection systems, and cooling systems, which are usually maintained at a minimum safe power supply. Non-critical auxiliary loads include some air conditioning, ventilation, domestic hot water, lighting, and non-critical pump sets, which can participate in short-term reduction, delayed start-up, or early operation without affecting the safe operation of the ship.

[0066] Based on the load-side adjustment model, the adjustable power range and the power reduction range on the load side are determined. Specifically, when load forecast results indicate an increase in future propulsion load or insufficient system power margin, the power reduction range for non-critical auxiliary loads is determined, and combined with propulsion power change rate constraints, a load reduction or smoothing adjustment capability is formed. When load forecast results indicate a decrease in future load or surplus power in the system, the power range for loads that can be operated in advance or increased is determined to improve the system's ability to absorb surplus power. Finally, the adjustable power range, power reduction range, adjustment duration, response time, and load priority on the load side are unified and organized to generate a load adjustment boundary, providing a basis for subsequent system safety constraint models and system adjustable power margin calculations.

[0067] Specifically, ship loads are divided into propulsion loads, critical auxiliary loads, and non-critical auxiliary loads. Propulsion loads include main propulsion motors, side thrusters, etc., and their power adjustment is limited by speed, maneuvering safety, and navigation mission requirements. The adjustable range of propulsion loads is expressed as follows: ; in, To increase load power, The minimum permissible propulsion power is determined by minimum speed, handling safety, and the navigation mission. The maximum permissible propulsion power is determined by the propulsion motor capacity, inverter capacity, and available power of the power source.

[0068] Key auxiliary loads include navigation and communication systems, control systems, fire suppression systems, bilge pumps, cooling systems, fuel cell auxiliary systems, etc., which generally do not participate in load reduction or only participate in load reduction under emergency strategies.

[0069] Non-critical auxiliary loads include some air conditioning, ventilation, domestic hot water, lighting, galley power, and non-critical pump sets, which can be temporarily reduced or delayed in operation without affecting ship safety. Power reduction for non-critical auxiliary loads is permitted. for: ; in, For auxiliary load baseline power, Minimum auxiliary load power to meet basic functional and safety requirements.

[0070] S5: Based on the adjustable power boundary and load adjustment boundary, construct a system safety constraint model to obtain the system operation constraint boundary; Among them, based on the adjustable power boundary and load adjustment boundary, a system safety constraint model is constructed to obtain the system operation constraint boundary, including: S51: Based on the adjustable power boundary, load forecast results, and load adjustment boundary, extract the system operation constraint parameters; the system operation constraint parameters include DC bus voltage parameters, DC bus current parameters, converter capacity parameters, power balance parameters, and equipment operation limit parameters; S52: Construct a system safety constraint model based on system operation constraint parameters; S53: Based on the system safety constraint model, determine the DC bus power balance constraint boundary, DC bus voltage constraint boundary, and converter operation constraint boundary; S54: Generate system operation constraint boundaries based on DC bus power balance constraint boundaries, DC bus voltage constraint boundaries, and converter operation constraint boundaries.

[0071] In this embodiment, system operating constraint parameters are extracted based on adjustable power boundaries, load forecasting results, and load regulation boundaries. These system operating constraint parameters include DC bus voltage parameters, DC bus current parameters, converter capacity parameters, power balance parameters, and equipment operating limit parameters. Specifically, the DC bus voltage parameter is used to determine whether the bus voltage is close to its upper or lower limit; the DC bus current parameter is used to determine whether the bus transmission capacity meets power regulation requirements; the converter capacity parameters include capacity limits for the fuel cell-side DC / DC converter, battery-side DC / DC converter, supercapacitor-side DC / DC converter, diesel generator rectifier unit, and propulsion inverter; the power balance parameters characterize the matching relationship between power source output power, energy storage charging and discharging power, propulsion load, auxiliary load, and system losses; and the equipment operating limit parameters include power source safe operating boundaries, energy storage charging and discharging limits, critical load power supply requirements, and load regulation limits.

[0072] Based on system operation constraints, a system safety constraint model is constructed. Specifically, the adjustable power boundaries of each power source are used as the power supply side input, and the load forecast results and load adjustment boundaries are used as the load side input. Combined with DC bus voltage, current, converter capacity, and equipment operating limitations, the model determines whether the adjustable capabilities of each power source can be safely executed at the system level. When the load forecast results indicate an increase in propulsion or auxiliary loads, the system safety constraint model determines whether the bus voltage can be maintained within the allowable range, whether each converter has sufficient transmission margin, and whether the power supply to critical loads will be affected. When the load forecast results indicate a decrease in load or the existence of surplus power, the model determines whether the energy storage charging absorption capacity, the power source load reduction capacity, and the load increase capacity meet the power balance requirements.

[0073] Based on the system safety constraint model, the DC bus power balance constraint boundary, DC bus voltage constraint boundary, and converter operation constraint boundary are determined. Specifically, the DC bus power balance constraint boundary limits the balancing range between power source output, energy storage charging and discharging, propulsion load, auxiliary load, and system losses; the DC bus voltage constraint boundary limits the bus voltage to not exceed the upper limit and not fall below the lower limit during power adjustment; the converter operation constraint boundary limits the transmission power, current, and temperature of each power electronic converter, rectifier unit, and propulsion inverter to not exceed the safe operating range. Finally, the above constraint boundaries are uniformly checked and integrated to generate the system operation constraint boundary, which limits the maximum executable range of the subsequent system adjustable power margin.

[0074] Specifically, for new energy ship propulsion systems using DC buses, the DC bus power balance constraint should be met: ; in, For fuel cell power, For lithium battery power, For supercapacitor power, This refers to the input power of the diesel generator after rectification. For shore power input power, To increase load power, For auxiliary load power, This is for system losses.

[0075] The DC bus voltage constraint is: ; The power constraints for each converter are as follows: ; in, This is the DC bus voltage. and These are the minimum allowable voltage and the maximum allowable voltage for the DC bus, respectively. To transfer power to the j-th converter, Its maximum allowable power.

[0076] When the DC bus voltage approaches the lower limit, the system reduces the upward adjustment power margin assessment value and prioritizes the use of lithium batteries, supercapacitors, or diesel generators for support; when the DC bus voltage approaches the upper limit, the system reduces the margin for further increasing power supply and prioritizes the assessment of energy storage charging absorption capacity or load-side capacity.

[0077] S6: Calculate the adjustable power margin of the system based on the adjustable power boundary, load forecast results, load adjustment boundary and system operation constraint boundary; Among them, reference Figure 4 As shown, based on the adjustable power boundary, load forecast results, load adjustment boundary, and system operation constraint boundary, the adjustable power margin of the system is calculated, including: S61: Determine the effective adjustable power of the system based on the adjustable power boundary, load regulation boundary, and system operation constraint boundary; S62: Based on the system's effective regulation power and load prediction results, calculate the system's upward power margin and downward power margin under different evaluation time domains respectively; S63: Based on the system's upward and downward power margins under different evaluation time domains, perform margin aggregation calculations to generate the system's adjustable power margin.

[0078] In this embodiment, the effective adjustable power of the system is determined based on the adjustable power boundary, load regulation boundary, and system operation constraint boundary. Specifically, the upward and downward adjustable power boundaries of the fuel cell, lithium battery, supercapacitor, and diesel generator at the current evaluation moment are first read, and then checked in conjunction with the range of non-critical auxiliary load reduction, the range of load increase, and the constraints of DC bus, converter, and power balance. The adjustable capability of the power source that does not meet the system operation constraints is not included in the effective adjustable power; the adjustable capability limited by bus voltage, current, or converter capacity is corrected according to the system operation constraint boundary, thereby obtaining the effective upward and downward adjustable power that can be safely executed at the system level.

[0079] Based on the system's effective power regulation and load forecast results, the system's upward and downward power margins are calculated under different assessment time domains. Specifically, in the second-level, minute-level, and long-term assessment time domains, the system's effective upward power is compared with the future load increase demand to determine the upward power margin that the system can additionally support the increase in propulsion or auxiliary loads; the system's effective downward power is compared with the future load decrease or surplus power absorption demand to determine the downward power margin that the system can safely reduce load, absorb energy through energy storage, or increase transferable loads. For the short-term assessment time domain, the rapid response capability of supercapacitors and lithium batteries is the primary consideration; for the medium- and long-term assessment time domains, the fuel cell's ramp-up capability, the diesel generator's power supply capability after startup, and the continuous support capability of energy storage are further considered.

[0080] Based on the system's upward and downward power margins under different evaluation time domains, margin aggregation calculations are performed to generate the system's adjustable power margin. Specifically, the margin contributions of different power sources at different time scales are uniformly organized and comprehensively verified in conjunction with response delay, duration, load regulation capability, and system operating constraints to avoid overestimating the margin due to simply adding up the instantaneous capabilities of each power source. The final generated system adjustable power margin includes the current upward power margin, the current downward power margin, the margin change results under different evaluation time domains, the main margin contribution sources, and the main limiting factors, providing a basis for subsequently determining the power regulation duration, response rate, and margin reliability.

[0081] Specifically, the formula for calculating the system's power margin is as follows: ; in, This indicates the system-level power margin adjustment; t represents the current evaluation time. Indicates the duration of power margin; Represents the allowable upward power limit under system constraints; i represents the first... One energy unit; Indicates the first The credibility coefficient of each energy unit; Indicates the first The response speed correction factor for each energy unit; Indicates the first Duration correction factor for each energy unit; Indicates the first Each energy unit at the current moment Duration Internal power margin adjustment; This indicates that power can be reduced for non-critical loads; The formula for calculating the system's power margin is as follows: ; in, This indicates a system-level power margin reduction. This represents the allowable power reduction boundary under system constraints; Indicates the first Each energy unit at the current moment Duration Internal power margin; This indicates that the load power can be increased or the power can be absorbed.

[0082] S7: Based on the system's adjustable power margin, determine the power regulation duration, response rate, and margin reliability, and generate adjustable power margin evaluation results.

[0083] Specifically, based on the system's adjustable power margin, the power regulation duration, response rate, and margin reliability are determined, generating adjustable power margin evaluation results, including: S71: Based on the system's adjustable power margin and the adjustable power boundaries of each power source, determine the power adjustment duration and generate the power adjustment duration result; S72: Based on the system's adjustable power margin, the power ramping capability of each power source, and the dynamic response characteristics, determine the system's power regulation response rate and generate response rate evaluation results. S73: Construct a margin reliability evaluation model based on load forecasting results, equipment operating status, historical response data, and operating condition identification results; S74: Based on the margin credibility evaluation model, the credibility of the adjustable power margin of the system is evaluated to obtain the margin credibility result; S75: Based on the power regulation duration results, response rate evaluation results, margin confidence results, and system adjustable power margin, generate adjustable power margin evaluation results.

[0084] In this embodiment, the power regulation duration is determined based on the system's adjustable power margin and the adjustable power boundaries of each power source. Specifically, the adjustable power boundaries of the fuel cell, lithium battery, supercapacitor, and diesel generator are read in different evaluation time domains, and combined with the system's upward and downward power margins, the duration for which the system can continuously support or absorb power under the target power regulation amount is determined. For supercapacitors, the focus is on determining their support time in the second or short minute range; for lithium batteries, the focus is on determining their continuous regulation time affected by SOC, temperature, and charge / discharge limitations; for fuel cells and diesel generators, the focus is on determining their continuous power supply capability after ramping up or grid connection, thereby generating the power regulation duration result.

[0085] Based on the system's adjustable power margin, the power ramping capability of each power source, and its dynamic response characteristics, the system's power regulation response rate is determined. Specifically, based on the response delay, power increase rate, power decrease rate, and actual operating status of the supercapacitor, lithium battery, fuel cell, and diesel generator, the system's comprehensive response capability in both upward and downward adjustment directions is determined. For short-term load surge scenarios, the rapid response capability of the supercapacitor and lithium battery is evaluated first; for medium- to long-term load growth scenarios, the ramping capability of the fuel cell and the power ramping capability of the diesel generator after startup are further evaluated; for load decrease or surplus power scenarios, the energy storage charging absorption capability, fuel cell load reduction capability, and diesel generator load reduction capability are evaluated, thereby generating response rate evaluation results.

[0086] Specifically, this embodiment not only outputs the power margin at a certain moment, but also outputs power margin curves for different durations. The duration may include: 5 seconds; 30 seconds; 1 minute; 5 minutes; 15 minutes; 30 minutes; 1 hour.

[0087] For each duration τ, calculate separately: and This forms the system's adjustable power margin curve. Simultaneously, the system calculates the upward adjustment response rate. and reduce response rate : ; ; in, and These represent the upward and downward adjustment response rates for the i-th power source or adjustable load, respectively. For different power sources, the response rate is determined according to their actual dynamic characteristics. Supercapacitors have the fastest response, followed by lithium batteries, while fuel cells and diesel generators are relatively slower.

[0088] Based on load forecasting results, equipment operating status, historical response data, and operating condition identification results, a margin reliability evaluation model is constructed, and the reliability of the system's adjustable power margin is assessed. Specifically, load forecasting error, navigation condition stability, fuel cell health status, lithium battery SOC and temperature safety margin, supercapacitor remaining energy, diesel generator starting reliability, DC bus voltage margin, historical power response deviation, and sensor data integrity are used as reliability evaluation factors. When the forecasting error is small, the equipment status is stable, and the historical response deviation is low, a higher reliability is determined; when the equipment is close to the operating boundary, operating condition switching is frequent, or data integrity is poor, the reliability level is reduced.

[0089] Specifically, considering the uncertainties of the ship's operating environment and equipment status, this invention conducts a reliability evaluation of the adjustable power margin. The reliability evaluation factors include: Load forecasting error; sea state variation; navigation condition stability; fuel cell health status; lithium battery SOC and temperature safety margin; supercapacitor remaining energy margin; diesel generator starting reliability; DC bus voltage distance limit margin; historical power response deviation; communication and sensor data integrity.

[0090] Credibility coefficient It can be represented as: ; in, For load forecasting error, For the health status of the fuel cell, For battery health status, For DC bus safety margin, Historical response error The credibility level can be divided into three levels: high, medium, and low. High credibility means that the assessment results can be directly used for energy management strategies; medium credibility means that it can be used for energy management strategies but a certain safety margin should be retained; low credibility means that the assessment results are not suitable for direct use in large power regulation and should be put into conservative control or manual verification mode.

[0091] The corrected system power margin is:

[0092] The corrected system power margin is:

[0093] in, This indicates that the power margin of the system has been increased after the confidence level correction; This represents the system's credibility coefficient. This indicates that the power margin of the system has been reduced after the credibility correction.

[0094] Finally, based on the power regulation duration results, response rate evaluation results, margin confidence results, and system adjustable power margin, an adjustable power margin assessment result is generated. This adjustable power margin assessment result includes the current upward power margin, the current downward power margin, the duration under different evaluation time domains, the system upward response rate, the system downward response rate, the margin confidence level, the main limiting factors, and recommended control actions. When the upward power margin is insufficient, it is recommended to increase fuel cell output, increase energy storage discharge, call supercapacitor compensation, start diesel generators, or reduce non-critical loads; when the downward power margin is insufficient, it is recommended to reduce power source output, increase energy storage charging, or start transferable loads in advance.

[0095] Please see Figure 5 This application also provides an adjustable power margin assessment system for a ship's multi-energy propulsion system, the system comprising: The data acquisition module is used to acquire the operating status data of the ship's multi-energy propulsion system; The load forecasting module is used to identify the current operating conditions of the ship based on the operating status data, and to forecast the load demand within a preset assessment time domain to obtain the load forecasting results. The first construction module is used to construct the adjustable power boundary model of each power source based on the operating status data and load prediction results, and obtain the adjustable power boundary of each power source. The second construction module is used to build a load-side adjustment model based on operating status data and load forecast results, and obtain the load adjustment boundary. The third construction module is used to construct a system safety constraint model based on the adjustable power boundary and load adjustment boundary, and obtain the system operation constraint boundary. The power margin calculation module is used to calculate the adjustable power margin of the system based on the adjustable power boundary, load forecast results, load adjustment boundary and system operation constraint boundary. The results generation module is used to determine the power regulation duration, response rate, and margin confidence based on the system's adjustable power margin, and generate adjustable power margin evaluation results.

[0096] It is understood that the content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0097] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0098] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0099] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0100] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0101] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0102] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0103] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0104] This application provides a method and system for assessing the adjustable power margin of a ship's multi-energy propulsion system. This method acquires the operating status data of the ship's multi-energy propulsion system and combines it with current operating condition identification and load demand prediction within a preset assessment time domain. This allows for early perception of future power demand trends, avoiding the lag in assessment results caused by static judgments based solely on instantaneous operating data. By constructing adjustable power boundary models and load-side adjustment models for each power source, the system's adjustable power capability can be characterized from both the energy supply and consumption sides, improving the completeness and accuracy of the adjustable power margin assessment. Simultaneously, a system safety constraint model is constructed based on the adjustable power boundary and load adjustment boundary, incorporating power source output limits, load adjustment limits, and system operational safety requirements into the assessment process. This ensures that the calculated adjustable power margin better reflects actual operating conditions, reducing the risk of equipment damage or system instability due to over-limit adjustments. Furthermore, by determining the power adjustment duration, response rate, and margin reliability based on the system's adjustable power margin, a multi-dimensional adjustable power margin assessment result can be generated, providing a reliable basis for ship energy management, power allocation, emergency response, and load reduction, thereby improving the operational safety, adjustment flexibility, and energy utilization efficiency of the ship's multi-energy propulsion system.

[0105] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0106] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0107] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0108] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0109] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for evaluating the adjustable power margin of a ship's multi-energy propulsion system, characterized in that, The method includes the following steps: Acquire operational status data of ship multi-energy propulsion systems; Based on the operational status data, the current operating condition of the ship is identified, and the load demand within the preset evaluation time domain is predicted to obtain the load prediction result. Based on the operating status data and the load prediction results, an adjustable power boundary model for each power source is constructed to obtain the adjustable power boundary for each power source. Based on the operational status data and the load forecast results, a load-side adjustment model is constructed to obtain the load adjustment boundary. Based on the adjustable power boundary and the load adjustment boundary, a system safety constraint model is constructed to obtain the system operation constraint boundary; Based on the adjustable power boundary, the load prediction results, the load adjustment boundary, and the system operation constraint boundary, calculate the system adjustable power margin; Based on the adjustable power margin of the system, the power regulation duration, response rate, and margin reliability are determined, and an adjustable power margin evaluation result is generated.

2. The method according to claim 1, characterized in that, The operational status data includes power source status data, energy storage status data, load status data, power network status data, and navigation condition data.

3. The method according to claim 1, characterized in that, The process of identifying the ship's current operating condition based on the operational status data and predicting the load demand within a preset assessment time domain to obtain load prediction results includes: Based on the operational status data, operating condition characteristic parameters are extracted; these parameters include ship speed, propulsion power, propulsion motor speed, control commands, load change rate, and historical operational data. Based on the aforementioned operating condition characteristic parameters, the current operating status of the ship is identified, and an operating condition identification result is generated. Based on the operating condition identification results, the operating status data, and historical operating data, a load demand prediction model is constructed. Based on the load demand prediction model, the propulsion load demand and auxiliary load demand within the preset evaluation time domain are predicted to obtain the load prediction results. Based on the load forecast results, the total load demand forecast results for the corresponding evaluation time domain are generated.

4. The method according to claim 1, characterized in that, Based on the operating status data and the load prediction results, an adjustable power boundary model for each power source is constructed to obtain the adjustable power boundary for each power source, including: Based on the operating status data, the status parameters of each power source are extracted; the status parameters of each power source include the rated power parameters, real-time output power parameters, operating status parameters and power regulation constraint parameters of each power source. Based on the power source state parameters and the load prediction results, adjustable power boundary models for each power source are established; the adjustable power boundary models for each power source include adjustable power boundary models for fuel cells, lithium batteries, supercapacitors, and diesel generators. Based on the adjustable power boundary models of each power source, the adjustable power boundary of the fuel cell, the adjustable power boundary of the lithium battery, the adjustable power boundary of the supercapacitor, and the adjustable power boundary of the diesel generator are determined respectively. The adjustable power boundaries of each power source are integrated to generate the adjustable power boundaries of each power source.

5. The method according to claim 1, characterized in that, Based on the operating status data and the load forecast results, a load-side adjustment model is constructed to obtain the load adjustment boundary, including: Based on the operational status data and the load forecast results, load-side status parameters are extracted; the load-side status parameters include driving load parameters, auxiliary load parameters, load priority parameters, and load regulation constraint parameters. Based on the load-side state parameters and the load forecast results, a load-side adjustment model is established; Based on the load-side adjustment model, the adjustable power range and the power reduction range on the load side are determined. Based on the adjustable power range and the power reduction range on the load side, a load adjustment boundary is generated.

6. The method according to claim 1, characterized in that, Based on the adjustable power boundary and the load adjustment boundary, a system safety constraint model is constructed to obtain the system operation constraint boundary, including: Based on the adjustable power boundary, the load prediction results, and the load adjustment boundary, system operation constraint parameters are extracted; the system operation constraint parameters include DC bus voltage parameters, DC bus current parameters, converter capacity parameters, power balance parameters, and equipment operation limit parameters; Based on the system operation constraint parameters, a system safety constraint model is constructed; Based on the system safety constraint model, the DC bus power balance constraint boundary, the DC bus voltage constraint boundary, and the converter operation constraint boundary are determined. Based on the DC bus power balance constraint boundary, the DC bus voltage constraint boundary, and the converter operation constraint boundary, the system operation constraint boundary is generated.

7. The method according to claim 1, characterized in that, The calculation of the system's adjustable power margin based on the adjustable power boundary, the load forecast result, the load adjustment boundary, and the system operation constraint boundary includes: The effective adjustable power of the system is determined based on the adjustable power boundary, the load adjustment boundary, and the system operation constraint boundary. Based on the effective regulation power of the system and the load prediction results, the system upward power margin and the system downward power margin are calculated under different evaluation time domains respectively. Based on the system's upward and downward power margins under different evaluation time domains, margin aggregation calculations are performed to generate the system's adjustable power margin.

8. The method according to claim 7, characterized in that, The formula for calculating the system's power margin is as follows: ； in, This indicates the system-level power margin adjustment; t represents the current evaluation time. Indicates the duration of the power margin; Represents the allowable upward power limit under system constraints; i represents the first... One energy unit; Indicates the first The credibility coefficient of each energy unit; Indicates the first Response speed correction factor for each energy unit; Indicates the first Duration correction factor for each energy unit; Indicates the first Each energy unit at the current moment Duration Internal power margin adjustment; This indicates that power can be reduced for non-critical loads; The formula for calculating the system's power margin is as follows: ； in, This indicates a system-level power margin reduction. This represents the allowable downward power limit under system constraints; Indicates the first Each energy unit at the current moment Duration Internal power margin; This indicates that the load power can be increased or the power can be absorbed.

9. The method according to claim 1, characterized in that, The process of determining the power adjustment duration, response rate, and margin reliability based on the system's adjustable power margin, and generating an adjustable power margin evaluation result, includes: Based on the adjustable power margin of the system and the adjustable power boundaries of each power source, the power adjustment duration is determined and the power adjustment duration result is generated. Based on the adjustable power margin of the system, the power ramping capability and dynamic response characteristics of each power source, the system power regulation response rate is determined and the response rate evaluation result is generated. Based on the load forecast results, equipment operating status, historical response data, and operating condition identification results, a margin reliability evaluation model is constructed. Based on the margin credibility evaluation model, the credibility of the adjustable power margin of the system is evaluated to obtain the margin credibility result. Based on the power regulation duration result, the response rate evaluation result, the margin confidence result, and the system adjustable power margin, an adjustable power margin evaluation result is generated.

10. A system for evaluating the adjustable power margin of a ship's multi-energy propulsion system, characterized in that, The system includes: The data acquisition module is used to acquire the operating status data of the ship's multi-energy propulsion system; The load forecasting module is used to identify the current operating conditions of the ship based on the operating status data, and to forecast the load demand within a preset evaluation time domain to obtain the load forecasting result. The first construction module is used to construct an adjustable power boundary model for each power source based on the operating status data and the load prediction results, so as to obtain the adjustable power boundary of each power source. The second construction module is used to construct a load-side adjustment model based on the operating status data and the load prediction results, and obtain the load adjustment boundary. The third construction module is used to construct a system safety constraint model based on the adjustable power boundary and the load adjustment boundary, and obtain the system operation constraint boundary; The power margin calculation module is used to calculate the adjustable power margin of the system based on the adjustable power boundary, the load prediction result, the load adjustment boundary, and the system operation constraint boundary. The result generation module is used to determine the power adjustment duration, response rate, and margin confidence based on the adjustable power margin of the system, and generate adjustable power margin evaluation results.

Images