FSRU ship energy consumption and carbon emission intelligent management and control system based on route big data

Abstract

The invention relates to the technical field of ship energy consumption control, and particularly discloses an FSRU ship energy consumption and carbon emission intelligent management and control system based on route big data, and the system comprises a route big data collection unit which is used for obtaining the multi-source data of an FSRU ship in the full-route-segment navigation process, and transmitting the multi-source data to an FSRU ship. The multi-source data at least comprises ship operation data, route environment data, carbon capture data and waste heat data; wherein the FSRU ship is a floating type storage regasification device ship; and the data preprocessing unit is connected with the airline big data acquisition unit and is used for cleaning the multi-source data and outputting preprocessed data. According to the method, the staged cooperative control model is established, the unique working condition requirements of the FSRU ship in different operation stages such as berthing, loading and unloading, offshore cruising and open sea navigation can be accurately identified and adapted, the limitation of a traditional single control strategy in variable scenes is overcome, and refinement and dynamics of energy distribution and emission control are achieved.

Description

Technical Field

[0001] This invention relates to the field of ship energy consumption control technology, and in particular to an intelligent management and control system for energy consumption and carbon emissions of FSRU ships based on route big data. Background Technology

[0002] As a key piece of equipment in the liquefied natural gas (LNG) industry chain, the floating storage and regasification unit (FSRU) possesses unique complexities in its function and operation mode. Unlike traditional LNG carriers, FSRUs not only undertake transportation tasks during long-distance ocean voyages but also need to anchor in designated sea areas for extended periods to perform LNG storage and regasification operations. This results in a dual nature of its energy system, characterized by navigation and operation, and a diverse range of energy-consuming units, primarily including: the ship's main engine for navigation, the regasification unit for regasification operations, and auxiliary generators providing power to the entire ship. The energy consumption proportions and operating conditions of these units vary significantly across different operational phases. Against this backdrop, existing energy consumption and carbon emission management technologies for FSRU vessels mainly face the following challenges: First, there is a close energy and material coupling relationship between the FSRU's power system, regasification system, onboard carbon capture system (if equipped), and waste heat recovery system. For example, the regasification process consumes a large amount of heat energy, while the exhaust gas from the main engine and generator contains considerable waste heat resources; CO2 desorption during carbon capture also consumes heat energy. Existing technologies often control and manage these subsystems independently, ignoring their synergistic potential, resulting in low overall energy utilization efficiency and suboptimal emission reduction effects.

[0003] Secondly, the complete operational cycle of an FSRU includes several significantly different phases, such as berthing and loading / unloading, near-shore cruising, and open-sea voyages. During the berthing phase, the main energy consumption comes from regasification and onboard daily use; during near-shore cruising, speed and course change frequently; and during open-sea voyages, complex and ever-changing sea conditions must be addressed. Existing management methods typically employ a fixed, static control logic, which cannot dynamically adjust the operating parameters of each energy-consuming unit according to the specific operational phase of the vessel and the real-time changing external environment, leading to unnecessary energy waste and carbon emissions under varying operating conditions. Summary of the Invention

[0004] This invention aims to at least partially address one of the technical problems in related technologies. Therefore, the objective of this invention is to propose an intelligent management and control system for FSRU vessel energy consumption and carbon emissions based on route big data, in order to improve the energy efficiency of FSRU vessels.

[0005] To achieve the above objectives, a first aspect of the present invention proposes an intelligent management and control system for FSRU ship energy consumption and carbon emissions based on route big data, comprising: The route big data acquisition unit is used to acquire multi-source data of the FSRU vessel during the entire voyage. The multi-source data includes at least vessel operation data, route environment data, carbon capture data, and waste heat data. The FSRU vessel is a floating storage and regasification unit vessel. The data preprocessing unit is connected to the route big data acquisition unit and is used to clean, standardize and perform multi-source fusion processing on the multi-source data, and output the preprocessed data. The phased collaborative control unit is connected to the data preprocessing unit. Its core is to establish a phased carbon emission optimization model based on the operation phase of the FSRU vessel, and solve the model based on the preprocessed data to generate carbon capture parameter adjustment instructions, power parameter adjustment instructions, and waste heat utilization path adjustment instructions. The operation phase includes the berthing and loading / unloading phase, the near-shore cruising phase, and the open-sea navigation phase. A carbon capture unit is used to receive the carbon capture parameter adjustment command and regulate the adsorbent circulation rate and CO2 desorption process. The power control unit is used to receive the power parameter adjustment command and regulate the engine power and the natural gas flow of the regasification unit. The waste heat utilization unit is used to receive the waste heat utilization path adjustment command and coordinate the distribution of exhaust waste heat from the regasification device and the engine. The comprehensive evaluation unit is used to evaluate the energy efficiency and carbon intensity of FSRU vessels based on the preprocessed data and the control results of the phased collaborative control unit.

[0006] To achieve the above objectives, a second aspect of the present invention proposes an intelligent management method for energy consumption and carbon emissions of FSRU vessels based on route big data, comprising the following steps: S1. Acquire multi-source data of the FSRU vessel during the entire voyage, wherein the multi-source data includes at least vessel operation data, route environment data, carbon capture data, and waste heat data; wherein the FSRU vessel is a floating storage and regasification unit vessel. S2. The multi-source data obtained in step S1 is cleaned, standardized, and fused to output the pre-processed data. S3. Establish a phased carbon emission optimization model based on the operational phase of the FSRU vessel, and solve the model based on the preprocessed data output in step S2 to generate carbon capture parameter adjustment instructions, power parameter adjustment instructions, and waste heat utilization path adjustment instructions; the operational phase includes the berthing and loading / unloading phase, the near-shore cruising phase, and the open-sea navigation phase. S4. Based on the carbon capture parameter adjustment command, power parameter adjustment command, and waste heat utilization path adjustment command generated in step S3, perform the following operations respectively: Adjusting the adsorbent circulation rate of the carbon capture unit and Desorption process; Regulate the engine power of the power control unit and the natural gas flow rate of the regasification unit; The waste heat from the regasification unit and the engine exhaust gas in the waste heat utilization unit is distributed collaboratively. S5. Based on the preprocessed data output from step S2 and the collaborative control execution results from step S4, evaluate the energy efficiency and carbon intensity of the FSRU vessel: To achieve the above objectives, a third aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory. When the computer program is executed by the processor, it implements the above-described intelligent management and control method for FSRU ship energy consumption and carbon emissions based on route big data.

[0007] This invention presents an intelligent management and control system for FSRU vessel energy consumption and carbon emissions based on route big data. By establishing a phased collaborative control model, it can accurately identify and adapt to the unique operating conditions of FSRU vessels during different operational phases, such as berthing and loading / unloading, near-shore cruising, and deep-sea voyages. This overcomes the limitations of traditional single control strategies in variable scenarios, achieving refined and dynamic energy allocation and emission control. More importantly, this invention does not optimize each subsystem in isolation, but rather achieves global collaborative control of the power system, regasification unit, carbon capture unit, and waste heat utilization unit through deep integration and analysis of route big data. In particular, it intelligently matches exhaust waste heat resources with the energy requirements of the carbon capture process, significantly improving the comprehensive utilization efficiency of shipboard energy. Ultimately, this invention constructs a complete technical system from multi-source data perception and intelligent modeling decision-making to collaborative closed-loop control, transforming the management of vessel energy consumption and carbon emissions from passive and discrete monitoring to proactive, holistic, and intelligent management, thereby comprehensively improving the energy efficiency and green shipping performance of FSRU vessels. Attached Figure Description

[0008] Figure 1 This is a schematic diagram of the intelligent management and control system for FSRU ship energy consumption and carbon emissions based on route big data provided by the present invention; Figure 2 This is a flowchart illustrating the intelligent management and control method for FSRU ship energy consumption and carbon emissions based on route big data provided by the present invention. Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0009] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0010] The following description, with reference to the accompanying drawings, describes an intelligent management and control system, method, and electronic device for FSRU ship energy consumption and carbon emissions based on route big data, according to embodiments of the present invention.

[0011] Example 1:

[0012] Figure 1 This is a schematic diagram of the intelligent management and control system for energy consumption and carbon emissions of FSRU vessels based on route big data, according to an embodiment of the present invention. The FSRU vessel is a floating storage and regasification unit vessel. The system includes: a route big data acquisition unit, a data preprocessing unit, a phased collaborative control unit, a carbon capture unit, a power control unit, a waste heat utilization unit, and a comprehensive evaluation unit.

[0013] The route big data acquisition unit is the perception foundation of the entire system. Its core responsibility is to comprehensively, in real-time, and accurately capture various status and environmental information involved in the entire mission lifecycle of the FSRU vessel, including port berthing, near-shore navigation, and ocean shipping. In this embodiment, this unit is a distributed data acquisition network, consisting of multiple sensors and data interfaces deployed at various key locations on the vessel. The multi-source data it collects is systematically divided into at least four dimensions: 1. Ship Operation Data: This is the core data reflecting the ship's own operational status, such as engine fuel consumption collected through the main engine monitoring system. (Unit: kg / h), rotational speed, load; natural gas flow rate collected through the regasification unit. (Unit: m³ / h), BOG (evaporative oxygen) production rate; real-time speed obtained through Automatic Identification System (AIS) and GPS. (Unit: knots), heading, latitude and longitude, etc.

[0014] 2. Route Environmental Data: This is a key external factor affecting ship energy consumption. Examples include real-time wind speed, wind direction, ocean current speed and direction, and significant wave height collected by shipboard weather stations, anemometers, current meters, wave height meters, and other equipment. This data is crucial for accurately modeling ship resistance under actual sea conditions.

[0015] 3. Carbon Capture Data: If the FSRU vessel is equipped with an onboard carbon capture system (CCS), this unit will collect its operational data through a dedicated sensor array, such as the CO2 concentration at the absorber inlet measured by a gas analyzer. and export CO2 concentration Used to calculate real-time carbon capture efficiency The operating frequency of the adsorbent (or absorbent liquid) circulation pump, obtained through the feedback signal from the frequency converter, is used to calculate the adsorbent circulation rate. .

[0016] 4. Waste Heat Data: To achieve cascaded energy utilization, this unit is also responsible for monitoring the ship's main waste heat sources, especially the exhaust pipes of the main engine and generator sets. Thermocouple temperature sensors and Pitot tube flow meters installed on the exhaust ducts can obtain the exhaust gas temperature in real time. and traffic This allows for the calculation of the recoverable waste heat power.

[0017] All of this data is collected and transmitted to the data preprocessing unit via a shipboard industrial Ethernet or CAN bus network at a preset frequency, such as on a second or minute basis.

[0018] The data preprocessing unit is a crucial bridge connecting raw sensor data with upper-level intelligent decision-making models. Its necessity stems from the fact that raw data collected from the front end often suffers from noise, outliers, missing data, inconsistent units, and different physical dimensions, making it unsuitable for direct use in precise mathematical modeling and analysis. Therefore, this unit executes a series of standardized data processing procedures to output high-quality, reliable preprocessed data. This unit typically consists of a shipboard high-performance industrial computer (IPC) or server and dedicated algorithm software running on it. Its core processing steps include: Data cleaning: Outliers or anomalies that may appear in the collected data due to momentary sensor malfunctions or strong electromagnetic interference are automatically identified and removed using statistical methods, such as the 3σ criterion. For the removed data points or missing data caused by communication interruptions, time series interpolation algorithms or prediction models based on historical similar operating conditions are used to fill in the gaps, ensuring the integrity and continuity of the data.

[0019] Data Standardization: Due to the significant differences in units and numerical ranges of different physical quantities—for example, fuel consumption might be hundreds of kg / h, while CO2 concentration might be a few parts per million (ppm)—it is necessary to normalize or standardize the data to avoid the large numerical range dominating the model results during subsequent model training and solving. This embodiment preferably uses the Z-score standardization method to convert the data of each dimension into a standard normal distribution with a mean of 0 and a standard deviation of 1, ensuring that all features are on the same order of magnitude.

[0020] Multi-source fusion: To provide the control model with a macroscopic indicator that comprehensively reflects the ship's overall energy efficiency status, this unit also performs feature-level multi-source data fusion. Through a pre-defined fusion function, multiple key, independent physical quantities are integrated into one or more comprehensive features. This not only reduces the input dimensionality of the model but also enhances its generalization ability.

[0021] The preprocessed, structured, high-quality data is fed into the system's decision-making core: the phased collaborative control unit. This unit recognizes that FSRU vessels have distinct operational phases throughout their lifecycle, each with different energy consumption characteristics and optimization objectives. Therefore, it abandons the traditional one-size-fits-all control strategy and adopts a more adaptive phased optimization logic. This unit first analyzes the vessel's GPS position, speed, and port operation plans to automatically determine whether the vessel is currently in the berthing / loading / unloading phase, the near-shore cruising phase, or the open-sea navigation phase. Subsequently, the unit invokes the optimization model matching the current phase. Its core is a phased carbon emission optimization model. The model's objective function has a unified mathematical form, but its internal parameters are dynamically adjusted according to different phases. The objective function is expressed as: ; Meanwhile, the model must be solved under the premise of ensuring the safe and stable operation of the ship, therefore it includes a series of constraints:

[0022]

[0023]

[0024] in: : Represents the net carbon emissions of an FSRU vessel per unit time (unit: kg / h), which is the ultimate goal of this system optimization, and its minimization is pursued; This indicates the fuel consumption of the ship's main engine or generator set (unit: kg / h), provided in real time by the data acquisition unit. : Indicates the natural gas flow rate consumed by the regasification unit (unit: m³ / h), provided in real time by the data acquisition unit; : Represents the carbon emission coefficient of fuel (unit: kgCO2 / kgfuel). This coefficient depends on the type of fuel oil used and is a relatively stable physical parameter preset in the system; : This represents the carbon emission factor of natural gas (unit: kgCO2 / m³gas). This factor depends on the composition of LNG and is also a preset physical parameter. : Represents the real-time capture efficiency of the shipborne carbon capture system. It is a dimensionless number between 0 and 1, determined by the data preprocessing unit based on... and Calculated; This is an operational phase influencing factor, a dimensionless weighting coefficient. It takes different values ​​depending on the ship's phase to adjust the focus of the optimization objective function. For example, during long-range voyages, this factor may primarily relate to speed and sea state; while during berthing, it may place more emphasis on regasification efficiency. : Represents the ship's speed (unit: knots), and is a key adjustable parameter of the power control unit; and These represent the minimum safe speed and the maximum design speed of a ship, respectively, which constitute the safety boundary for speed adjustment; and : These represent the minimum and maximum stable operating flow rates of the regasification unit, respectively; : Represents the circulation rate of the adsorbent in the carbon capture system, and is a key adjustable parameter of the carbon capture unit; and : These represent the minimum and maximum allowable rates of adsorbent circulation, respectively.

[0025] The phased collaborative control unit inputs the preprocessed real-time data into the aforementioned model and solves it using built-in optimization algorithms (such as sequential quadratic programming and particle swarm optimization). The result is not a single numerical value, but a set of optimal control parameter settings. Based on this, the unit generates three types of mutually coordinated adjustment commands: carbon capture parameter adjustment commands, power parameter adjustment commands, and waste heat utilization path adjustment commands. These commands are then sent to the corresponding execution units.

[0026] The carbon capture unit, power control unit, and waste heat recovery unit are the system's actuators, responsible for translating the digital control commands issued by the phased collaborative control unit into actual operations on the ship's physical equipment.

[0027] Carbon capture unit: Upon receiving a carbon capture parameter adjustment command, its internal PLC or DCS system adjusts the speed of the adsorbent circulation pump to achieve the optimal circulation rate required by the command. At the same time, it will also adjust the heat energy supply for the CO2 desorption process according to the coordination signal of the waste heat utilization unit, so as to achieve the target capture rate with the lowest energy consumption.

[0028] Power Control Unit: Upon receiving a power parameter adjustment command, it sends instructions via an interface to the ship's main engine remote control system or power plant management system (PMS). For example, it adjusts the main engine's speed or pitch to achieve the target speed. Alternatively, adjust the settings of the LNG pumps and heaters in the regasification unit to achieve the target natural gas flow rate. .

[0029] Waste heat recovery unit: Upon receiving a waste heat recovery path adjustment command, it controls the opening of the electric or pneumatic three-way regulating valve installed on the exhaust gas pipeline. The command will clearly specify what proportion of the exhaust gas waste heat should be directed to the reboiler of the carbon capture system for CO2 desorption, and what proportion should be directed to other places that require heat energy, such as LNG storage tank preheating or domestic hot water, thereby achieving optimized distribution and efficient utilization of heat energy throughout the ship.

[0030] Finally, the comprehensive evaluation unit conducts a closed-loop evaluation and quantitative analysis of the overall management effectiveness. This unit continuously receives preprocessed data and records control commands issued by the phased collaborative control units and the feedback status of each execution unit. Based on this information, it calculates a series of key performance indicators, such as the actual energy utilization rate of this voyage, the achieved average carbon capture efficiency, and most importantly, the real-time carbon intensity (CII) rating of the voyage. These evaluation results are not only presented in the form of visual charts on the crew's operating interface to provide decision support, but more importantly, they are stored as historical data for the self-learning and iterative updates of the optimization model, thereby enabling the system's management performance to continuously improve over time and with data accumulation.

[0031] Example 2: In Example 1, the route big data collection unit, data preprocessing unit, and phased collaborative control unit were introduced. This example will provide an in-depth analysis of the specific composition, working principle, and internal algorithm logic of these three units.

[0032] I. Route Big Data Collection Unit To achieve accurate modeling and optimization of FSRU ship energy consumption and carbon emissions, high-quality, multi-dimensional data input is a primary prerequisite. The route big data acquisition unit in this embodiment specifically consists of the following four specialized sensor groups: 1. Ship Operation Sensor Group: This sensor group is the core for acquiring the ship's own dynamics.

[0033] The measurement of engine fuel consumption F is achieved by installing high-precision Coriolis mass flow meters in pairs on the fuel supply and return manifolds of the main engine and each generator set. The system reads the instantaneous mass flow rates of the supply and return manifolds in real time and calculates the difference (supply and return fuel volume) to obtain the actual fuel mass consumed by the engine. This measurement method eliminates errors caused by changes in fuel temperature and density, ensuring highly accurate baseline data for energy consumption calculations.

[0034] Measurement of natural gas flow rate G in the regasification unit: An industrial-grade ultrasonic or vortex flow meter is installed on the pipeline that supplies natural gas to the external environment from the regasification unit. This flow meter directly measures the standard volumetric flow rate of the supplied natural gas and transmits the data in real time to the shipboard monitoring system via a data interface, such as Modbus or 4-20mA signal.

[0035] Measurement of ship speed V: This system simultaneously collects and integrates two speed signals. The first is the surface speed (STW) measured by a Doppler log, which reflects the relative speed between the ship and the water, and is the direct basis for calculating the ship's hydrodynamic resistance. The second is the ground speed (SOG) obtained through the Global Positioning System (GPS) or the BeiDou Navigation Satellite System (BDS), which reflects the ship's absolute speed relative to the Earth. The vector difference between the surface speed and the ground speed is crucial for calculating the influence of ocean currents.

[0036] 2. Route Environment Sensor Group: This sensor group is responsible for quantifying the external environmental factors that affect ship energy consumption.

[0037] GPS Positioning Module and Acquisition of Voyage S: In addition to providing SOG and latitude / longitude information, the high-precision differential GPS (DGPS) module is used to accurately record the ship's track. By integrating continuous positioning points, the system can calculate the ship's mileage in real time. .

[0038] Wind speed W and wind direction measurement: A two-dimensional or three-dimensional ultrasonic anemometer is installed on the bridge or at the highest point of the mainmast of the FSRU vessel. This location minimizes the interference of the superstructure with airflow. The instrument measures relative wind speed and relative wind direction. The system integrates ground speed / heading information provided by GPS and calculates the true wind speed W and true wind direction in real time through vector synthesis calculations. The true wind is a core parameter for calculating the ship's wind resistance.

[0039] Measurement of ocean current velocity H and direction: Although it can be directly measured using an Acoustic Doppler Current Profiler (ADCP), in practical engineering applications, a more common and cost-effective method is indirect calculation. The system obtains the ground speed / heading vector provided by GPS and the water speed / heading vector provided by a log and gyrocompass. The difference between these two vectors is the equivalent ocean current velocity at that navigation point. And the direction of flow.

[0040] Wave height (Hw) measurement: The effective wave height, wave period, and wave direction encountered by the ship are measured in real time using a microwave radar wave gauge installed at the bow or side of the ship. These data are key inputs for calculating the additional drag added to the ship in the waves.

[0041] 3. Carbon Capture Sensor Assembly: This sensor assembly is used to accurately monitor the operational performance of the shipborne carbon capture system (CCS).

[0042] CO2 concentration and Measurement: Online CO2 analyzers based on the non-dispersive infrared (NDIR) principle were installed at the flue gas inlet and the purified flue gas outlet pipes of the carbon capture and absorption tower. The difference between these two concentration values ​​was used to calculate the carbon capture efficiency. The direct basis for this calculation is as follows: .

[0043] Adsorbent circulation rate Monitoring: This parameter is typically not measured directly by liquid flow rate, but rather by monitoring the output frequency of the VFD (Variable Frequency Drive) driving the adsorbent (or absorbent liquid) circulation pump or the actual speed of the motor. Since the pump flow rate and its speed exhibit a linear or known curvilinear relationship within a certain range, the system can accurately convert the VFD's operating parameters into the adsorbent circulation rate by consulting preset speed-flow characteristic curves in a database. (Unit: m3 / h)

[0044] 4. Waste heat sensor array: This sensor array is used to quantify the energy available for recycling.

[0045] Exhaust gas temperature Measurement: Insert armored K-type or S-type thermocouples at the position before the exhaust manifold of the main unit and generator set enters the waste heat boiler (if any) or is directly discharged into the chimney, to adapt to high temperature environments of up to 500-600°C and monitor the exhaust temperature in real time.

[0046] Exhaust gas flow Estimation: Directly measuring the exhaust gas flow rate under high temperature, high speed, and large pipe diameter conditions is technically challenging and costly. Therefore, this system employs a more engineering-oriented model estimation method. The system uses performance curves (MAPs) provided by the engine manufacturer, based on real-time engine load, speed, and fuel consumption. By combining this with a pre-defined air-fuel ratio model, the instantaneous exhaust gas mass flow rate or volumetric flow rate can be estimated with considerable accuracy. .

[0047] II. Data Preprocessing Unit The data preprocessing unit transforms raw data into optimized data that can be used by advanced models through the following sophisticated algorithmic process.

[0048] 1. Data cleaning steps: Outlier Removal: This embodiment preferably employs the 3σ criterion. In practice, the system maintains a dynamic sliding time window for each important time-series data point, such as airspeed V and fuel consumption F. At each time step, the system calculates the mean of the data within that window. and standard deviation For newly entered data points If it satisfies If the value is not found, the point is considered an outlier and is marked.

[0049] Data Correction: For marked outliers or missing data caused by communication interruptions, the system employs a tiered correction strategy: Strategy 1: Linear interpolation. Suitable for scenarios with very short data loss periods, such as 12 sampling points. Assume the valid data points before and after the missing point are... and Then missing points ( The value of ) was corrected to .

[0050] Strategy Two: Historical Similarity Data Prediction Method. This method is suitable for scenarios with long data gaps or requiring higher accuracy. The system takes a small segment of valid data preceding the currently missing data point, such as data containing multiple dimensions like airspeed, engine load, and wind speed, as a query vector. It then performs pattern matching in a database storing massive amounts of historical flight data, searching for the most similar historical segment. Once the most matching historical condition is found, the system uses the value at the corresponding time point within that historical condition, or the predicted value from a local prediction model (such as the ARIMA model) built based on that historical segment, to correct the currently missing data. This method fully leverages the advantages of large-scale flight route data, making data repair more intelligent and accurate.

[0051] Data standardization steps:

[0052] This embodiment uses Zscore standardization, and its calculation formula is as follows: in, For the original data points, and These are the global (or based on a large time window) mean and standard deviation of the data series, respectively.

[0053] The core purpose of standardization is to eliminate the asymmetry caused by different physical dimensions and numerical ranges. For example, in subsequent modeling, engine power... The value could be as high as 15,000 kW, while the wave height... The value might be as low as 3 meters. Without standardization, in any distance- or gradient-based optimization algorithm, the optimization direction would be entirely dominated by the enormous feature of engine power, while the influence of the equally crucial physical factor of wave height would be greatly weakened, leading to model distortion. After standardization, the values ​​of all features fluctuate around 0 and have similar scales, allowing the model to treat each input feature fairly, thereby uncovering the true and profound physical relationships between them.

[0054] In this embodiment, the feature-level fusion function It was used to construct a composite feature called the Comprehensive Flight Load Index (CSLI). .

[0055] Where: P The standardized regasified natural gas flow rate; W Standardized carbon capture efficiency; weighting coefficient to The determination of these weights: These weights are not arbitrarily set, but are derived through machine learning methods based on historical big data training. Specifically, the system uses the total energy consumption or total carbon emissions of historical voyages as the target variable, and the four standardized features mentioned above as input variables to train a multiple linear regression or a more complex gradient boosting tree (GBT) model. After training, the weights or feature importance assigned to each input feature by the model can be used as... to The value of is determined by . This ensures that the weighting coefficients can scientifically reflect the actual contribution of each factor to the total energy consumption.

[0056] To map the weighted sum to a more physically meaningful or easily processed interval, the Sigmoid function can be used to smoothly map values ​​of any real number range to the (0,1) interval. This results in the comprehensive navigation load index. It is a dimensionless value between 0 and 1, which can intuitively represent the current comprehensive load level of the ship: the closer it is to 1, the higher the comprehensive load.

[0057] III. Phased Collaborative Control Unit

[0058] Optimize the objective function: The design of this objective function reflects a comprehensive consideration of the sources of carbon emissions from FSRU vessels and a systematic integration of emission reduction measures, including:

[0059] Total carbon source term (F+G): It clearly breaks down emissions into two main categories: main engine / generator fuel oil and natural gas from regasification units. The coefficient is, for example, kgCO2 / kgfuel for typical marine light diesel (MGO).

[0060] Emission reduction effect items ( This item directly and dynamically couples the performance of the carbon capture system into the optimization objective. This means that when making decisions, the system will comprehensively consider the balance between the increase in emissions caused by adjusting the host load and the reduction in emissions caused by improving carbon capture efficiency.

[0061] Scene adjustment items The influencing factors for this operational phase are key to achieving phased control. It is not a fixed value, but rather a regulator automatically selected by the system based on the current operational phase. For example:

[0062] During the berthing and loading / unloading phase The internal structure may focus more on sub-functions related to regasification efficiency and port emission limits (if any), guiding the optimization direction towards reducing energy consumption related to G.

[0063] During the long-range voyage This may be related to the predicted remaining time of the voyage, the estimated time of arrival (ETA), and sea state factors. Closely coupled to achieve a balance between economical cruising speed and minimum total emissions per voyage.

[0064] The model's constraints firmly anchor the mathematical optimization problem within engineering realities and safety boundaries:

[0065] Speed ​​constraints : This is not only the minimum technical speed, but also a safe lower limit for speed under specific sea conditions to ensure ship efficiency and avoid stalling and excessive rolling. This value is dynamically adjusted by the system based on real-time wave height and wind speed. This corresponds to the design speed that the main engine's maximum continuous power (MCR) can achieve.

[0066] Flow constraints : This is the minimum load required for the regasification unit to maintain stable operation, such as preventing cavitation in the LNG pump and maintaining stable heat exchanger temperature. That is its rated capacity as indicated on the nameplate.

[0067] Cyclic rate constraints : This is the minimum cycle rate required to ensure that the adsorbent can be effectively regenerated. Below this value, desorption will be incomplete, which will affect the subsequent absorption efficiency. It is limited by the maximum power of the pump, the hydraulic characteristics of the pipeline, and the possible flooding phenomenon in the absorption tower.

[0068] When the above model is fed with real-time data from the data preprocessing unit, it constitutes a specific, nonlinear, constrained optimization problem. The phased collaborative control unit incorporates a highly efficient numerical optimization solver. The solver performs an iterative calculation in each decision cycle, searching for the objective function that satisfies the condition. Minimize the combination of decision variables This optimal solution combination This is then translated into specific instructions sent to each execution unit. For example, optimal speed. This is converted into a setpoint command for the main engine governor or CPP pitch; optimal natural gas flow rate. This is translated into setpoint commands for the LNG pump and heater control valves; optimal cycle rate. It is converted into a frequency setpoint command for the adsorbent circulation pump inverter.

[0069] Example 3:

[0070] The core of this embodiment lies in detailing the decision-making logic and algorithm implementation within the phased collaborative control unit. A major drawback of existing technologies is their reliance on a single, fixed control strategy, which cannot adapt to the varied operating conditions of FSRU vessels. This invention overcomes this deficiency by tailoring unique control models and parameter systems for different operating phases. This embodiment will analyze the innovative control strategies employed by this invention under three typical operating phases.

[0071] I. Cooperative Control Logic during the Berthing and Loading / Unloading Phase

[0072] Stage characteristics and control objective definition:

[0073] When the FSRU vessel is determined by the phased collaborative control unit to be in the berthing and loading / unloading phase through its AIS status, GPS location (long-term location in port or designated anchorage), speed (close to zero), and dock loading / unloading arm connection status signals, the system will automatically switch to the dedicated control mode for this phase.

[0074] During this stage, the ship's main propulsion system is either shut down or in hot standby mode, and the main energy consumption comes from:

[0075] Regasification unit: continuously regasifies LNG to meet the natural gas demand of downstream users. This process consumes a large amount of heat energy and may produce boil-off gas (BOG).

[0076] Auxiliary generator sets: provide electricity for regasification units, onboard living facilities, deck machinery, and carbon capture systems, and their fuel consumption is the main source of carbon emissions in this phase.

[0077] Shipboard carbon capture system: treats the exhaust gas from auxiliary generator sets.

[0078] Therefore, the core control objective at this stage is no longer speed or range efficiency, but rather to maximize the comprehensive utilization rate of shipboard energy, minimize fuel consumption and net carbon emissions per unit of electricity generated, and at the same time meet the more stringent environmental regulations that may exist in the port area.

[0079] Specific implementation of refined collaborative control strategy:

[0080] To achieve the above objectives, the phased collaborative control unit will generate and execute the following set of highly coordinated control instructions:

[0081] 1. Optimized allocation of waste heat utilization pathways:

[0082] This system treats the exhaust gas from the auxiliary generator set as a valuable thermal energy resource, rather than simply waste gas. Upon receiving a command, the waste heat utilization unit controls a precision three-way regulating valve on the exhaust gas pipeline to distribute the high-temperature exhaust gas (typically 350-500°C) to two key heat-using units according to a dynamically calculated preset ratio:

[0083] Path 1: Carbon Capture Desorption Tower Heat Exchanger. This is the primary heat flow path. As described in Example 2, CO2 desorption during the carbon capture process requires heating the CO2-rich adsorbent to approximately 80-130°C. The quality of the generator exhaust waste heat perfectly matches this requirement. By monitoring the desorption tower temperature in real time, the system precisely adjusts the exhaust gas flow rate to this path, ensuring the desorption process operates efficiently within the optimal temperature range. This completely replaces or significantly reduces the need to operate the additional fuel-fired boiler, achieving significant energy savings.

[0084] Path 2: LNG Tank Preheater. Under certain operating conditions, such as when the outside temperature is low or when pressure management of the tank is required, specific areas of the LNG tank need to be slightly heated to control the BOG (Boiled Air Gaseous) production rate. The system guides the waste heat from the desorption tower, or excess tail gas when the desorption tower load demand is low, into the tank's preheating loop, achieving cascaded energy utilization.

[0085] 2. Enhanced operation mode of carbon capture unit:

[0086] Considering the high environmental protection requirements of the port area and the sufficient supply of waste heat, the system will instruct the carbon capture unit to enter enhanced operation mode.

[0087] Increasing the adsorbent circulation rate θ: increasing the adsorbent circulation rate Adjust the rate to between 110% and 120% of its rated design value. This increased rate means more adsorbent flows through the absorption tower per unit time, increasing the total contact area and contact time with the flue gas, thus enabling the capture of a higher proportion of CO2 and improving carbon capture efficiency. Increase from the usual 90% to 95% or even higher.

[0088] Dynamic reduction in desorption time: Due to the stable and sufficient waste heat supply from the generator, the desorption tower can reach the target desorption temperature more quickly. The system dynamically shortens the desorption cycle time based on the real-time heating rate. For example, a standard cycle may be reduced from 20 minutes to 15 minutes. This not only increases the overall throughput of the carbon capture system but also matches the increased cycle rate, forming a highly efficient positive cycle.

[0089] 3. Economic and rapid control of power parameters:

[0090] The system sends commands to the power control unit to optimize the operation of the auxiliary generator set.

[0091] Shut down unnecessary auxiliary heating systems: For example, equipment such as preheaters for main engine fuel and lubricating oil and oil separators do not need to operate during main engine shutdown. The system will cut off their power through the power plant management system (PMS) to eliminate standby energy consumption.

[0092] Maintaining generators at economical load: The system intelligently starts and stops the number of generator sets and adjusts the load of operating units based on the real-time changing electrical load of the entire ship (mainly from the regasification unit) via the PMS, ensuring that they always operate within the optimal fuel consumption range of 75%-85%, avoiding low fuel efficiency and increased emissions (such as NOx and PM) caused by low load operation. This is the engineering embodiment of maintaining the engine at idle load as described in the claims, i.e., meeting the minimum economical operating load requirements.

[0093] Through the aforementioned three-pronged coordinated control, the FSRU forms a highly efficient internal energy ecosystem during the berthing phase. Waste heat generated by the generator is efficiently used to drive carbon capture, reducing additional energy consumption; enhanced carbon capture ensures ultra-low emissions within the port area; and refined management of the power system reduces basic energy consumption at the source.

[0094] II. Cooperative Control Logic During the Nearshore Cruise Phase

[0095] When an FSRU vessel leaves port and navigates in coastal waters, channels, or areas with high traffic volume, the system determines that it has entered the near-shore cruising phase.

[0096] The characteristics of this stage are: moderate speed, frequent changes in course (for avoidance, turning, and navigation along the channel), and complex traffic environment. The control objective shifts to: optimizing the ship's overall energy efficiency in real time while ensuring navigational safety and meeting route planning requirements, and quantifying and suppressing the additional energy losses caused by frequent turning operations.

[0097] Here we introduce the heading adjustment coefficient. Accurate energy consumption modeling: Traditional energy consumption models typically only consider speed, neglecting the significant impact of steering maneuvers. This invention innovatively introduces a heading adjustment coefficient. This is used to quantify the energy penalty incurred during steering in real time. Its calculation formula is:

[0098]

[0099] in: 1.05: A dimensionless energy penalty multiplier, always greater than 1; 1.05 (basic steering factor): Even when the ship is theoretically sailing in a straight line, due to minor wind and current influences, the autopilot will still make continuous, small-angle corrections. These small steering angles also generate drag. Statistical analysis of a large amount of historical data revealed that this micro-steering to maintain course results in an average additional energy consumption of about 5%. Therefore, a basic value of 1.05 is set to make the model more realistic under any sailing condition than an idealized pure straight-line sailing model. (Single course change angle): This refers to the angle by which a ship's course changes during a single complete turning maneuver, measured in degrees (°). For example, turning from 90° to 120°... The system automatically identifies and calculates this value by continuously monitoring the rate of change of the gyrocompass heading reading; 0.003 (steering penalty weight): This is an empirical coefficient calibrated for a specific ship type through tank tests on a ship model or CFD (Computational Fluid Dynamics) simulation. It quantifies the percentage increase in energy consumption per degree of steering angle. Numerical example: Suppose an FSRU vessel needs to perform a steering maneuver to avoid a fishing boat, changing its heading from 45° to 65° and then back to 45°.

[0100] For example: First turn: ;

[0101] Calculate the steering process : ;

[0102] This means that during this 20-degree turn, the ship's instantaneous energy consumption will be about 11% higher than when sailing straight at the same speed. This figure will be used to revise energy efficiency assessments and provide decision-making references for the navigator, such as the fact that small, gentle turns are more economical than large, sharp turns.

[0103] based on Optimize energy consumption efficiency Calculation: To provide crew members with an intuitive and accurate energy efficiency evaluation index, this invention proposes an optimized energy consumption utilization rate. Computational model. This model integrates the ship's transportation mission, navigation status, and regasification services, and creatively incorporates... The impact it brings.

[0104] Formula Correction and Explanation: To make the physical meaning clearer, we have provided an equivalent and more intuition-inspired expression for the formula in the claims:

[0105]

[0106] in: : Comprehensive energy consumption utilization rate (unit: ton nautical miles / ton oil equivalent or similar dimension). The deadweight tonnage of a ship (unit: tons) reflects the amount of cargo transported. : Ship's speed over water (unit: knots); The natural gas flow rate (unit: m³ / h) of the regasification unit reflects the amount of regasification service it provides. Fuel consumption of the main unit (unit: kg / h); Natural gas energy conversion factor, used to convert the energy consumption of natural gas to fuel oil equivalent (unit: kgfuel / m³gas). : Proportional coefficient, used to balance the weights of different contributing factors; denominator This is the key point of the invention. It means that the ship's total energy input includes not only the consumption of fuel oil and natural gas, but must also be multiplied by the course adjustment factor. This is equivalent to explicitly including the intangible energy loss caused by turning in the total energy cost.

[0107] For example, suppose a certain FSRU ship has the following specifications: DWT = 80,000 tons, V = 15 knots, G = 10,000 m³ / h, F = 2,500 kg / h. =0.6, =1, =50.

[0108] Case A: Straight-line navigation

[0109] , .

[0110]

[0111] Case B: Currently making a 20-degree turn.

[0112] , .

[0113]

[0114] The results show that steering operations improve overall energy efficiency. The energy efficiency index dropped from 190.48 to 180.18, quantifying a loss of approximately 5.4%. This index is displayed in real time on the bridge interface, providing clear feedback to the crew when they see a significant drop due to frequent or abrupt steering, prompting them to adopt a smoother and more predictable steering approach.

[0115] Dynamic adjustment of the carbon capture adsorbent circulation rate within a flexible range: During near-shore navigation, the main engine load fluctuates frequently due to speed adjustments and turns, causing changes in exhaust gas flow and CO2 concentration. In such cases, if a fixed adsorbent circulation rate is still used... This could lead to wasted pumping energy at low loads and insufficient capture efficiency at high loads. Therefore, the system dynamically adjusts the circulation rate within a preset flexible range (e.g., 80%-110% of the rated value) based on real-time changes in the host load. Its control logic is as follows: when the host load is detected to increase by more than 5% within 30 seconds, the system will proactively (feedforward control) adjust the load accordingly. Increase by a corresponding percentage to cope with the upcoming higher CO2 concentrations; conversely, when the load decreases, reduce appropriately. To save energy.

[0116] III. Cooperative Control Logic during the Long-Distance Voyage Phase

[0117] During long-distance ocean voyages far from land and along fixed routes, the system enters the open-sea voyage phase. This phase is characterized by long voyage times, a relatively constant course, but encounters complex and variable sea conditions (wind, waves, and currents) that significantly impact energy consumption. The control objective is to find the globally optimal speed-power-carbon capture strategy using intelligent algorithms, while meeting the ETA (Exit Time Assurance) requirements, to minimize total energy consumption and total carbon emissions for the entire voyage.

[0118] Here, the sea state influence factor is introduced. Achieving dynamic environmental modeling: To enable the control model to perceive the resistance of the marine environment, this invention introduces sea state influencing factors. This is a dimensionless multiplier calculated in real time to correct the performance curve of a ship in still water.

[0119] To make its physical meaning explicit as a penalty factor (i.e., a value ≥ 1), we express it as:

[0120]

[0121] in: : The comprehensive impact coefficient of sea state on energy consumption; 1.0 (base value): represents the ideal state of still water with no wind and no current; Relative wind speed (m / s). Wind resistance is proportional to the square of the wind speed. The reverse current component (m / s) in the bow direction; the current resistance is approximately linearly related to the current velocity. : Effective wave height (m), the additional resistance of the wave is approximately proportional to the square of the wave height; These are the drag coefficients for wind, current, and waves, respectively. These coefficients are related to the ship's hull type, the geometry of the part above / below the waterline, and the encounter angle. They have been calibrated in advance through model tests or numerical calculations and stored in the system database.

[0122] For example, suppose an FSRU encounters sea conditions: headwind m / s, countercurrent m / s, facing the waves m. The calibrated coefficient is , , .calculate :

[0123]

[0124]

[0125] Calculations show that the current severe sea conditions require ships to expend 23.35% more power than in calm water to maintain the same speed across the water. The value will become a key input to the optimization algorithm below, telling the algorithm: the current environmental resistance is high, please recalculate the optimal strategy.

[0126] Because ocean navigation is a long-term, dynamic optimization problem, decision variables (speed V, regasification flow rate G, carbon capture rate θ) and the external environment... There are highly nonlinear coupling relationships between them. To find the global optimum rather than getting trapped in local optima, this invention employs the Particle Swarm Optimization (PSO) algorithm.

[0127] PSO core iterative formula: The algorithm continuously updates the velocity of each particle. and location To explore the search space, the particle positions of the algorithm are defined as vectors. It iterative optimization is performed based on the particle velocity and position update formula to cope with changing sea conditions.

[0128] ,in, It is a particle The best position one has ever experienced, and It is the globally optimal position discovered for the entire population so far; These are the standard parameters of the algorithm.

[0129] Through a single iteration, the algorithm guides the particle toward a better solution (lower speed, matching carbon capture rate) and successfully finds a new global optimum. The system will repeat this process approximately 100-200 times, ultimately obtaining the gbest vector. This involves the phased collaborative control unit outputting the optimal control commands to each execution unit under the given sea conditions. This global optimization, compared to traditional simple feedback-based adjustments, can bring significant energy-saving and emission-reduction effects at the voyage level, thus achieving revolutionary and refined management of FSRU ship energy consumption and carbon emissions.

[0130] Example 4:

[0131] The core of this embodiment lies in revealing the dynamic collaborative mechanism and closed-loop feedback control logic within the system of the present invention, which is specifically reflected in two key collaborative closed loops: one is the deep coupling of the energy and environmental protection subsystem, and the other is the continuous optimization of the control and evaluation subsystem.

[0132] I. Deep Coupling of Energy and Environmental Protection Subsystems: Synergistic Linkage Mechanism between Carbon Capture Unit and Waste Heat Utilization Unit

[0133] As described in the aforementioned embodiments, one of the core components of shipborne carbon capture (especially chemical absorption) is CO2 desorption, which involves heating a CO2-rich absorbent (or adsorbent) to release CO2 for collection. This process is energy-intensive, and the economics and stability of its heat source directly determine the operating cost and efficiency of the entire carbon capture system. On the other hand, the exhaust pipes of the engines (main or auxiliary) of FSRU vessels (whether underway or at anchor) contain a large amount of waste heat resources of moderate grade (350-500℃). Directly releasing this waste heat into the atmosphere would constitute a huge waste of energy.

[0134] This invention recognizes the natural and perfect supply-demand matching relationship between the two. Therefore, a sophisticated collaborative linkage mechanism is designed to dynamically and in real-time intelligently match the heat demand of the carbon capture unit with the heating capacity of the waste heat utilization unit, thereby realizing a closed loop of advanced energy utilization.

[0135] The operation of this collaborative mechanism can be broken down into two levels: feedforward control and feedback regulation.

[0136] Feedforward Control: Initial Heat Allocation Based on Global Commands. After the phased collaborative control unit calculates the optimal strategy based on the global optimization model, it generates a waste heat utilization path adjustment command and sends it to the waste heat utilization unit. This command is not a simple on / off signal, but a quantified command containing specific heat allocation targets. For example, during the berthing phase, the command might be: send 85% of the total waste heat from the generator exhaust to the carbon capture and desorption tower, and reserve 15% for LNG storage tank preheating.

[0137] Upon receiving this command, the three-way valve control module (usually a PID controller) within the waste heat recovery unit precisely drives the electric or pneumatic three-way regulating valve installed on the exhaust gas main, adjusting its valve core position so that the exhaust gas flow ratio between the branch flowing to the desorption tower heat exchanger and the auxiliary branch flowing to the LNG storage tank preheater (or directly vented) reaches precisely 85:15. This is the initial control setting, i.e., the feedforward loop.

[0138] Feedback Regulation: Precise real-time correction based on desorption temperature cannot be achieved solely through feedforward control, as fluctuations in engine load and changes in ambient temperature can lead to real-time variations in exhaust gas temperature and flow rate, thereby affecting the actual heat gain of the desorption tower. To ensure that the desorption process remains within its most efficient temperature range, this invention designs a closed-loop feedback regulation system centered on the desorption temperature.

[0139] Key monitoring points: In the core area of ​​the absorbent reboiler within the desorption tower of the carbon capture unit, multiple high-precision platinum resistance temperature sensors, such as PT100, are installed. The data from these sensors, after averaging or weighting, yields a real-time value representing the current core desorption temperature. .

[0140] Setting the optimal temperature range: The system database has a preset optimal desorption temperature range, which is set to [80°C, 130°C] in this embodiment.

[0141] The hazards of temperatures below 80°C: The CO2 desorption reaction rate is too slow, resulting in incomplete desorption. This leads to a high concentration of CO2 remaining in the absorbent returned to the absorption tower (i.e., the lean solution is not lean enough), significantly reducing its ability to absorb CO2 from the next round of flue gas, thus impacting the overall carbon capture efficiency. Not up to standard.

[0142] The dangers of temperatures exceeding 130°C: While ensuring complete desorption, this presents two major problems. First, excessively high temperatures accelerate the thermal degradation of the absorbent (usually an amine solution), rendering it permanently ineffective and increasing operating costs. Second, heating beyond the necessary range is itself a waste of energy, reducing the overall energy efficiency of the system.

[0143] Implementation of feedback control logic: The three-way valve control module of the waste heat utilization unit, while executing feedforward commands, also continuously receives real-time temperature data from the desorption tower. And make fine adjustments based on the following logic:

[0144] When temperature Above 130°C (overheating state): Overheat suppression logic is triggered. The three-way valve control module will increase the opening of the auxiliary flow to the LNG storage tank preheater in small increments (e.g., adjusting the opening by 2% each time), while correspondingly decreasing the opening of the flow to the desorption tower. This is equivalent to gently removing some fuel from an overheated pot, reducing the heat entering the desorption tower heat exchanger and causing the temperature to slowly drop.

[0145] When temperature Below 80°C (underheating state): Underheating compensation logic is triggered. The three-way valve control module will close or reduce the opening of the auxiliary circuit, forcing almost all the waste heat from the exhaust gas to the desorption tower heat exchanger to ensure that it receives sufficient heat energy first and heats up to the effective operating range as soon as possible.

[0146] For example, suppose an auxiliary machine of an FSRU is in berthing operation with an exhaust gas temperature of 420°C. The initial command issued by the phased collaborative control unit requires that 80% of the waste heat be supplied to the desorption tower.

[0147] Initial state: The three-way valve opening is set to 80% to the desorption tower and 20% to the auxiliary circuit. After a period of time, the desorption tower temperature... The temperature stabilizes at 115°C, which is in the middle of the optimal range, ensuring efficient and stable system operation.

[0148] Changes in operating conditions: A large LNG transfer pump on board was started, which caused a sudden increase in the load on the auxiliary machinery, and the exhaust gas temperature rose to 460°C in a short period of time.

[0149] System response (overheat suppression): Due to a sudden increase in input heat, the temperature of the desorption tower began to rise continuously. When the temperature sensor reading reached 130.1°C, the feedback regulation mechanism was triggered.

[0150] First adjustment: The three-way valve control module automatically adjusts the opening to the desorption tower from 80% to 78%, and increases the opening of the auxiliary line to 22%.

[0151] Monitoring and Continuous Adjustment: The system continued to monitor and found that the temperature was still slowly rising to 130.5°C. Therefore, a second adjustment was made, setting the opening to 76%:24%.

[0152] A new equilibrium was reached: After several fine-tuning adjustments, the valve opening finally stabilized at 75%:25%, at which point the temperature of the desorption tower dropped and stabilized at around 128°C. The system successfully maintained key process parameters within the optimal range under the disturbance of drastic changes in external operating conditions through the coordinated feedback of internal subsystems, avoiding energy waste and absorbent degradation.

[0153] This collaborative mechanism integrates two previously independent systems (environmental protection equipment and energy equipment) into a highly efficient and adaptive energy-environment symbiotic system. It not only significantly reduces the operating cost (OPEX) of carbon capture and improves the overall energy efficiency of the FSRU, but more importantly, through precise closed-loop control, it ensures the stable and efficient operation of the carbon capture system under various operating conditions, providing a solid technical guarantee for the continuous low-carbon operation of ships.

[0154] II. Closed-Loop Feedback for Control Evaluation: Continuous Optimization Mechanism of Power Control Unit and Integrated Evaluation Unit

[0155] Any model-based optimization control relies on the accuracy of the model and the comprehensiveness of its perception of the external environment. However, in the real marine environment, there will always be nonlinear factors that the model fails to fully cover or unexpected situations that cannot be predicted. If the system is merely a one-way command issuer and cannot reflect on and correct its actions based on actual performance, its optimality cannot be consistently guaranteed. To address this, this invention designs a PDCA (Plan-Execute-Check-Act) closed-loop feedback mechanism. The power control unit is responsible for execution, while the comprehensive evaluation unit is responsible for checking and feeding back the check results to the decision-making brain (the phased collaborative control unit) to guide its action adjustments, thus forming a continuously self-optimizing intelligent cycle.

[0156] Collaborative control process and implementation details: (1) Refined execution of the power control unit: The power control unit is not only a transmitter of commands, but also responsible for converting strategic commands from the upper level (such as optimizing speed) into refined operations on the lower-level equipment. It will adjust the course according to the heading adjustment coefficient of the near-shore cruising phase calculated in Example 3, which includes real-time sea conditions and navigation status. Sea state influencing factors during long-range voyages , and implement specific control strategies.

[0157] Because when sailing at sea, When the speed spikes due to severe sea conditions, the power control unit may receive instructions that go beyond simply reducing speed. Instead, it might employ a combined strategy, such as reducing main engine power by 10% while simultaneously increasing the natural gas flow rate of the regasification unit by 5% (if external gas supply is required), to compensate for potential delays caused by the speed reduction (by providing more commercial services). This multi-variable, fine-grained control is the foundation for achieving global optimization.

[0158] (2) Quantitative Evaluation by the Integrated Evaluation Unit: While the power control unit executes commands, the integrated evaluation unit, acting as an independent supervisor, continuously conducts post-event evaluations. Calculation of Key Performance Indicators (KPIs): Cruise carbon intensity. This is a core indicator for assessing ship carbon emission efficiency, directly aligned with the IMO's CII regulations. Its calculation formula is:

[0159]

[0160] in, This is the total net CO2 emissions accumulated from the start of the voyage to the present (unit: tons). It refers to the ship's deadweight tonnage. This is the total number of nautical miles traveled since the start of the voyage. Physically, this indicator represents the amount of carbon dioxide emissions generated from transporting one ton of cargo one nautical mile.

[0161] Energy consumption utilization rate As described in Example 3, this indicator comprehensively evaluates the transportation efficiency and service efficiency of ships.

[0162] Rating Standards Establishment: The system incorporates a CII rating standards database. This database references official IMO standards and, based on ship type, tonnage, and other information, provides rating standards for... Five thresholds were set for the grades: A (excellent), B (good), C (average), D (mediocre), and E (poor).

[0163] For example: Grade A;

[0164] Grade B;

[0165] Grade C.

[0166] (3) Triggering a feedback loop for further optimization:

[0167] This is the core of this collaborative mechanism. The comprehensive evaluation unit compares the calculated KPI ratings with the preset targets at each evaluation cycle (e.g., hourly).

[0168] Triggering condition: When the system detects that the current voyage has accumulated [data / data / etc.] or instantaneous When the preset excellent or good (i.e., A or B grade) rating criteria are not met, for example, the calculated... If the system falls to level C, it will determine that the currently executing optimal control strategy is not performing well in actual applications.

[0169] Triggering action: Once the triggering conditions are met, the comprehensive evaluation unit will immediately send an internal signal requesting re-optimization to the phased collaborative control unit.

[0170] Re-optimization process: Upon receiving this signal, the phased collaborative control unit will immediately initiate a new round of optimization calculations (e.g., rerunning the PSO algorithm). Crucially, this optimization calculation will no longer be based solely on predicted data from the external environment; it will also incorporate feedback from the comprehensive evaluation unit regarding poor actual performance as a significant input. For example, the algorithm might add a penalty term to the model, assigning lower weights to parameter combinations that led to previous poor performance (such as excessively high speed); or, the algorithm might call a model correction module to adjust the speed-fuel consumption curve model based on the deviation between actual fuel consumption and model predictions. Or sea state influencing factors The coefficients are fine-tuned.

[0171] Issuance of new instructions: After further optimization calculations, the new and revised optimal control instructions will be issued to the power control unit and other actuators, thus completing a closed loop of problem discovery, analysis, and resolution.

[0172] This collaborative feedback mechanism endows the system of this invention with a valuable capacity for self-reflection and self-adaptation. It ensures that the system can continuously and dynamically approach its optimal operating goals not only under ideal conditions but also in the uncertain real world. This transforms ship energy and carbon management from a static, prediction-based open-loop control to a dynamic, effectiveness-based closed-loop intelligent management system, greatly enhancing the robustness and practical application value of the solution.

[0173] Example 5:

[0174] Please see Figure 2 It illustrates a flowchart of an intelligent management method for FSRU vessel energy consumption and carbon emissions based on route big data. This method embodies the logical operation of the system in Example 1 and specifically includes the following steps:

[0175] Step S1: Data Acquisition Step. This step corresponds to the continuous operation of the route big data acquisition unit. After the system starts, this step continuously acquires raw multi-source data from various sensors and subsystems of the ship, including ship operation data ( , , (etc.), route environmental data (wind, waves, currents, etc.), carbon capture data ( , , (etc.) and waste heat data ( , These data, etc., form the data foundation for all subsequent analysis and decision-making.

[0176] Step S2: Data Preprocessing. This step is performed by the data preprocessing unit. It involves real-time cleaning, standardization, and multi-source fusion of the massive, heterogeneous raw data stream collected in Step S1. Through this step, the system transforms the complex underlying data into clean, well-organized preprocessed data that can be directly used for mathematical modeling, ensuring the quality of decision input.

[0177] Step S3: Modeling and Solving Steps. This step is the core of the method and is executed by the phased collaborative control unit. First, the system automatically determines the operational phase (berthing and loading / unloading, near-shore cruising, or deep-sea navigation) based on the ship's real-time status and selects the corresponding operational phase influencing factors. Then, the preprocessed data output from step S2 is used as input to minimize net carbon emissions. In a phased carbon emission optimization model with the objective of [missing information], under multiple safety and operational constraints such as speed, natural gas flow rate, and carbon capture rate, the built-in optimization algorithm quickly solves the model, ultimately calculating the optimal set of coordinated control strategies under the current operating conditions, and converting them into specific carbon capture parameter adjustment commands, power parameter adjustment commands, and waste heat utilization path adjustment commands.

[0178] Step S4: Coordinated Control Execution. This step is the implementation of the decision, completed collaboratively by the carbon capture unit, power control unit, and waste heat utilization unit. These three units receive and precisely execute the corresponding commands generated in Step S3. This step emphasizes coordination; the regulation of carbon capture, power output, and waste heat distribution is not performed in isolation, but rather as a set of interrelated actions calculated based on a global optimization model to achieve overall optimization rather than local optimization. For example, when a command requires a reduction in speed, it may be accompanied by commands to reduce the heat required for carbon capture desorption and to redirect excess waste heat for other uses.

[0179] Step S5: Comprehensive Evaluation Step. This step is executed by the comprehensive evaluation unit, forming a closed-loop feedback loop in the method. After the control commands in Step S4 are executed, the system continuously monitors various performance parameters of the vessel and calculates and updates evaluation indicators such as energy efficiency and carbon intensity of the FSRU vessel in real time based on the latest preprocessed data and control execution results. The evaluation results are used to demonstrate the effectiveness of the current management strategy to operators and also serve as historical data for long-term performance evaluation of the system and self-optimization of the model, thereby achieving a continuously improving intelligent management cycle.

[0180] In summary, this embodiment, through the close integration of the aforementioned systems and methods, constructs a complete closed loop from data perception and intelligent decision-making to collaborative control and effect evaluation. It can deeply understand the complex operating conditions of FSRU vessels at different stages of operation and, from a forward-looking and holistic perspective, perform integrated and collaborative optimization scheduling of multiple key energy subsystems on board. This minimizes energy consumption and carbon emissions while ensuring the safe and reliable operation of the vessel, providing strong technical support for the green, economical, and intelligent operation of FSRU vessels.

[0181] Example 6:

[0182] Corresponding to the above embodiments, the present invention also proposes an electronic device.

[0183] like Figure 3 The diagram shows a structural schematic of an electronic device according to the present invention. The electronic device 200 includes a processor 201 and a memory 203. The processor 201 and the memory 203 are connected, for example, via a bus 202. Optionally, the electronic device 200 may further include a transceiver 204. It should be noted that in practical applications, the transceiver 204 is not limited to one unit, and the structure of this electronic device 200 does not constitute a limitation on the embodiments of the present invention.

[0184] Processor 201 may be a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA, or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in connection with this disclosure. Processor 201 may also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0185] Bus 202 may include a path for transmitting information between the aforementioned components. Bus 202 may be a PCI bus or an EISA bus, etc. Bus 202 may be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0186] The memory 203 stores a computer program corresponding to the intelligent management method for FSRU ship energy consumption and carbon emissions based on route big data in the above embodiments of the present invention. This computer program is controlled and executed by the processor 201. The processor 201 executes the computer program stored in the memory 203 to implement the content shown in the aforementioned method embodiments.

[0187] Among them, electronic devices 200 include, but are not limited to: mobile terminals such as laptops and tablets, as well as fixed terminals such as desktop computers. Figure 3 The electronic device 200 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0188] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, a computer-readable medium can be any means that can contain, store, transmit, or transfer programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, the computer-readable medium can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0189] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0190] In the description of this specification, references to the terms "an embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0191] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0192] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A smart management and control system for FSRU ship energy consumption and carbon emissions based on route big data, characterized in that, include: The route big data acquisition unit is used to acquire multi-source data of the FSRU vessel during the entire voyage. The multi-source data includes at least vessel operation data, route environment data, carbon capture data, and waste heat data. The FSRU vessel is a floating storage and regasification unit vessel. The data preprocessing unit is connected to the route big data acquisition unit and is used to clean, standardize and perform multi-source fusion processing on the multi-source data, and output the preprocessed data. The phased collaborative control unit is connected to the data preprocessing unit. Its core is to establish a phased carbon emission optimization model based on the operation phase of the FSRU vessel, and solve the model based on the preprocessed data to generate carbon capture parameter adjustment instructions, power parameter adjustment instructions, and waste heat utilization path adjustment instructions. The operation phase includes the berthing and loading / unloading phase, the near-shore cruising phase, and the open-sea navigation phase. A carbon capture unit is used to receive the carbon capture parameter adjustment command and regulate the adsorbent circulation rate and CO2 desorption process. The power control unit is used to receive the power parameter adjustment command and regulate the engine power and the natural gas flow of the regasification unit. The waste heat utilization unit is used to receive the waste heat utilization path adjustment command and coordinate the distribution of exhaust waste heat from the regasification device and the engine. The comprehensive evaluation unit is used to evaluate the energy efficiency and carbon intensity of FSRU vessels based on the preprocessed data and the control results of the phased collaborative control unit.

2. The system according to claim 1, characterized in that, The route big data collection unit includes: The ship's operating sensor array is used to collect the engine's fuel consumption. The natural gas flow rate of the regasification unit and the speed of the vessel ; The route environment sensor suite, including a GPS positioning module, anemometer, current meter, and wave height meter, is used to collect data on the ship's voyage. Wind speed Ocean current speed And the waves are high ; Carbon capture sensor array used to collect data at the inlet of the absorption tower. concentration ,exit concentration and the adsorbent circulation rate ; Waste heat sensor array, used to collect exhaust gas temperature and exhaust gas flow .

3. The system according to claim 1, characterized in that, The data preprocessing unit processes the multi-source data through the following steps: Data cleaning: Outlier data points exceeding the mean ± 3 standard deviations are removed using the 3σ criterion, and corrected using linear interpolation or historical similar working condition data prediction methods; Data standardization: using formulas The multi-source data is normalized, wherein... This is the original data. The mean of the data. The standard deviation of the data; Multi-source fusion: employing feature-level fusion functions Integrate multi-source data, among which For engine power, to For preset weighting coefficients, It is a non-linear transformation function.

4. The system according to claim 1, characterized in that, The control logic of the phased collaborative control unit during the berthing and loading / unloading phase is as follows: Output the waste heat utilization path adjustment command to control the waste heat utilization unit to distribute the tail gas waste heat of the regasification unit to the carbon capture adsorption tower heat exchanger and the LNG storage tank preheater according to a preset ratio. The carbon capture parameter adjustment command is output to adjust the adsorbent circulation rate under the condition that the regasification unit is operating at full load and the waste heat supply from the exhaust gas is sufficient. Adjust to 110%-120% of the rated value and shorten the desorption time; Output the power parameter adjustment command, turn off the engine auxiliary heating system, and maintain the engine at idle load.

5. The system according to claim 1, characterized in that, The control logic of the phased collaborative control unit during the near-shore cruise phase is as follows: Introducing heading adjustment coefficient Its calculation formula is ,in This refers to a single change of direction angle; Based on the heading adjustment coefficient Optimize energy consumption efficiency The calculation formula is: ,in For ship load capacity, This is the proportionality coefficient. This is the energy conversion factor for natural gas; The carbon capture parameter adjustment command adjusts the adsorbent circulation rate based on speed fluctuations. Dynamic adjustments are made within the elastic range.

6. The system according to claim 1, characterized in that, The control logic of the phased collaborative control unit during the open-sea navigation phase is as follows: Introducing sea state influence factors Its calculation formula is ,in For wind speed, The speed of the ocean current; The staged carbon emission optimization model is solved using a particle swarm optimization algorithm, where the particle positions are defined as vectors. It iterative optimization is performed based on the particle velocity and position update formula to cope with changing sea conditions.

7. The system according to claim 1, characterized in that, The carbon capture unit works in conjunction with the waste heat utilization unit, wherein: The desorption tower control module in the carbon capture unit controls the amount of waste heat input to the desorption tower heat exchanger according to the waste heat utilization path adjustment command, so as to maintain the desorption temperature in the optimal range of 80-130℃. The three-way valve control module in the waste heat utilization unit adjusts the temperature of the desorption tower based on feedback. When the temperature is higher than 130°C, the opening of the auxiliary line flowing to the LNG storage tank preheater is increased. When the temperature is lower than 80°C, the auxiliary line is closed to ensure the heating of the desorption tower.

8. The system according to claim 1, characterized in that, The power control unit works in conjunction with the integrated evaluation unit, wherein: The power control unit adjusts the course according to the heading adjustment coefficient during the near-shore cruising phase. and the sea state influencing factors of the aforementioned ocean voyage phase Based on real-time data, it executes refined control strategies such as reducing engine power, increasing natural gas flow, or reducing speed. The comprehensive evaluation unit calculates the carbon intensity of the voyage. Its formula is ,when or energy consumption utilization rate If the preset excellent or good rating criteria are not met, the phased collaborative control unit is triggered to re-optimize the parameters.

9. The system according to claim 1, characterized in that, The objective function of the phased carbon emission optimization model is: ； The constraints are: ； in, Carbon emissions per unit time for FSRU vessels This refers to engine fuel consumption. This refers to the natural gas flow rate of the regasification unit. This refers to the carbon emission coefficient of fuel. For natural gas carbon emission coefficient, For carbon capture efficiency. As an influencing factor during the operation phase, For ship speed, and These are the minimum safe speed and the maximum design speed, respectively. The circulation rate of the carbon capture adsorbent. and These represent the minimum and maximum circulation rates of the adsorbent, respectively.

10. A method for intelligent management and control of energy consumption and carbon emissions of FSRU vessels based on route big data, characterized in that, Includes the following steps: S1. Acquire multi-source data of the FSRU vessel during the entire voyage, wherein the multi-source data includes at least vessel operation data, route environment data, carbon capture data, and waste heat data; wherein the FSRU vessel is a floating storage and regasification unit vessel. S2. The multi-source data obtained in step S1 is cleaned, standardized, and fused to output the pre-processed data. S3. Establish a phased carbon emission optimization model based on the operational phase of the FSRU vessel, and solve the model based on the preprocessed data output in step S2 to generate carbon capture parameter adjustment instructions, power parameter adjustment instructions, and waste heat utilization path adjustment instructions; the operational phase includes the berthing and loading / unloading phase, the near-shore cruising phase, and the open-sea navigation phase. S4. Based on the carbon capture parameter adjustment command, power parameter adjustment command, and waste heat utilization path adjustment command generated in step S3, perform the following operations respectively: Adjusting the adsorbent circulation rate of the carbon capture unit and Desorption process; Regulate the engine power of the power control unit and the natural gas flow rate of the regasification unit; The waste heat from the regasification unit and the engine exhaust gas in the waste heat utilization unit is distributed collaboratively. S5. Based on the preprocessed data output from step S2 and the collaborative control execution results from step S4, evaluate the energy efficiency and carbon intensity of the FSRU vessel.

Images