Sailing-speed auxiliary decision making method for LNG dual-fuel trailing suction hopper dredger

Abstract

A sailing-speed auxiliary decision making method for an LNG dual-fuel trailing suction hopper dredger. The method comprises: step S1, collecting actual dredger operational data; step S2, collecting operating condition data, and establishing a trailing suction hopper dredger operating-condition identification database; step S3, establishing an LNG fuel main-engine energy consumption and sailing speed database; and step S4, by means of sailing speed optimization and corrective learning, providing a mobilization speed auxiliary decision-making suggestion. The present invention aims to provide a sailing-speed auxiliary decision making method for an LNG dual-fuel trailing suction hopper dredger to overcome existing defects, thereby providing scientific decision-making support for the mobilization and dredging speeds of dredgers, and improving the energy efficiency and environmental protection performance of dredgers.

Description

A speed-aided decision-making method for LNG dual-fuel trailing suction hopper dredgers Technical Field

[0001] This invention relates to a speed-assisted decision-making method for an LNG dual-fuel powered trailing suction hopper dredger. Background Technology

[0002] With increasing global awareness of environmental protection and the International Maritime Organization's (IMO) tightening of restrictions on greenhouse gas emissions from ships, the shipping industry is facing enormous pressure to reduce emissions. In the field of dredging engineering, LNG dual-fuel trailing suction hopper dredgers, as new energy-powered engineering vessels, have also received widespread attention regarding their energy consumption and emissions. Therefore, developing a speed-aided decision-making method for LNG dual-fuel powered trailing suction hopper dredgers is of great significance for improving ship navigation energy efficiency and reducing emissions.

[0003] Traditional trailing suction hopper dredgers typically use a single fuel oil as their power source, resulting in significant CO2 (carbon dioxide) emissions and other pollutants that negatively impact the environment. In contrast, LNG (liquefied natural gas) dual-fuel trailing suction hopper dredgers utilize both LNG and fuel oil for propulsion, achieving cleaner and more efficient energy utilization. During deployment and dredging operations, these vessels can be set to a reasonable, economically efficient speed based on actual working conditions and needs, thereby achieving energy conservation and emission reduction.

[0004] However, when LNG dual-fuel trailing suction hopper dredgers are navigating, multiple factors need to be considered, including the characteristics of the main engine, LNG fuel consumption, the aquatic environment, and various special construction conditions. Traditional speed decision-making methods often rely on human experience or fixed calculation models, which cannot reflect the actual condition and needs of the vessel in real time and accurately. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing methods and provide a speed-assisted decision-making method for LNG dual-fuel trailing suction hopper dredgers, which provides scientific decision support for the dispatch and dredging speed of the vessel, and improves the energy efficiency and environmental performance of the vessel.

[0006] The technical solution to achieve the above objective is: a speed auxiliary decision-making method for an LNG dual-fuel powered trailing suction hopper dredger, comprising:

[0007] Step S1: Collect actual ship data;

[0008] Step S2: Collect operating data and establish a database for identifying the operating conditions of trailing suction hopper dredgers;

[0009] Step S3: Establish a database of LNG fuel main engine energy consumption and speed;

[0010] Step S4: Through speed optimization and learning correction, provide auxiliary decision-making suggestions for dispatch speed.

[0011] Preferably, step S1, collecting actual ship data, includes: collecting the LNG fuel consumption of the trailing suction hopper dredger's main engine. LNG The speed of the trailing suction hopper dredger relative to the ground is v. d Collect wind speed v wind Wind direction D wind Collect propeller pitch ratio PD; collect propeller rotational speed n p ; Collect ship draft T d .

[0012] Preferably, step S2, collecting operating condition data and establishing a trailing suction hopper dredger operating condition identification database, includes:

[0013] Step S21: Based on the construction process and the actual condition of the vessel, the single trip of the trailing suction hopper dredger is divided into five working conditions: dredging, dumping, navigation, blowing, and other working conditions. Among them, the navigation condition is divided into heavy-load navigation and light-load navigation, and other working conditions include berthing, docking, and non-construction working conditions.

[0014] Step S22: Read the data from the equipment sensors in real time through the PLC of the dredger, including the limit signals, switch signals, and gate valve signals of the trailing suction dredger's construction equipment and devices;

[0015] Step S23: Based on the construction process and logical sequence of the trailing suction hopper dredger, identify the working conditions of the dredger. Then, based on the output results of the working condition identification, filter the data on energy efficiency, water environment, speed, and construction history, and select the heavy-load navigation data and light-load navigation data during the navigation process to provide a data foundation for subsequent model construction and optimization.

[0016] Preferably, step S3, establishing the LNG fuel main engine energy consumption and speed database, includes:

[0017] Step S31: During navigation, the main engine power is transmitted to the propeller through the propulsion bearing. The propeller overcomes the resistance caused by the environment during navigation, providing effective power to propel the ship. During this process, the drag coefficient caused by factors such as the water environment is C. d The ship's speed is V; therefore, according to the theoretical formula, the effective power of the dredger per unit time can be obtained as P. d =f(C d ,V);

[0018] Combined with the main engine fuel consumption rate g e The LNG fuel consumption per unit time and ship speed mechanism model can be obtained as FC LNG =g e ·Pd ;

[0019] Step S32, combining the energy consumption and speed mechanism model from step S31, under a single operating condition, the main engine fuel consumption rate g e Approaching a constant, the mechanism model and the total drag coefficient C d Related; slip ratio can reflect the influence of the aquatic environment on the resistance of ship navigation to a certain extent; the formula for calculating slip ratio is... Introducing an energy efficiency impact factor coefficient can reflect the external environment's stress on the ship, thus affecting its energy consumption. This coefficient can be expressed as a mathematical model f. Cd =f(Slip,T) d );

[0020] Step S33: Based on steps S31 and S32, simplify the LNG fuel consumption and ship speed mechanism model to FC. LNG =f(Slip,T) d )·V 3 .

[0021] Preferably, step S4, through the speed optimization module, corrects the learning and provides auxiliary decision-making suggestions for dispatch speed, including:

[0022] Step S41: Periodically collect a large amount of data on actual ship pitch, ship draft, speed, and LNG fuel consumption, and the data under navigation conditions filtered from the operating condition identification database in step S2. Use data-driven deep learning algorithms to correct the LNG energy consumption and speed model in step S3 to improve the model's generalization ability and accuracy.

[0023] Step S42: For the corrected mathematical model of LNG energy consumption and speed with higher accuracy, an optimization algorithm is used to optimize the mathematical model with the goal of minimizing LNG fuel consumption per unit time, and obtain the optimal speed V0 to provide speed auxiliary decision-making suggestions during ship dispatch.

[0024] Preferably, the LNG fuel consumption of the trailing suction hopper dredger's main engine is FC LNG Data is collected via mass flow meters installed on the outlet / inlet pipelines of the LNG storage tank; the trailing suction hopper dredger collects its ground speed (v) via a GPS system. d The trailing suction hopper dredger collects wind speed (v) using an anemometer. wind Wind direction D wind Environmental information; the trailing suction hopper dredger collects propeller pitch ratio (PD) and propeller speed (n) via a variable pitch system. p Trailing suction hopper dredgers calculate their draft (T) using draft sensors and cargo hold volume. d .

[0025] Preferably, step S1 further includes using the system to store the collected data in separate tables using MySQL data, and the database simultaneously stores the parameter data of the energy efficiency and speed mechanism models and mathematical models.

[0026] The beneficial effects of this invention are as follows: This LNG dual-fuel trailing suction hopper dredger speed auxiliary decision-making method combines the use of LNG fuel trailing suction hopper dredger sensing equipment to achieve automatic monitoring and collection of LNG fuel consumption, water environment parameters, and construction data; it introduces an automatic identification module for trailing suction hopper dredger operating conditions, labeling data under dredger navigation conditions; the LNG energy consumption and speed mechanism model is established based on ship main engine characteristics and ship resistance analysis theory; it simplifies the impact of external environment and ship draft on energy consumption, and improves the energy consumption and speed mechanism model by introducing energy efficiency influence factor coefficients; it periodically collects the above data, continuously performs data-driven correction learning on the model through deep learning algorithms, making the model more accurate, and then optimizes the model according to the optimization algorithm, providing auxiliary decision-making suggestions for dredger speed adjustment. This method for assisting dredger speed decision-making combines the use of sensing equipment on LNG-fueled trailing suction hopper dredgers to automatically monitor and collect LNG fuel consumption, aquatic environmental parameters, and construction data. It introduces an automatic operating condition identification module for trailing suction hopper dredgers, labeling data under different navigation conditions. The LNG energy consumption and speed mechanism model is established based on ship main engine characteristics and ship resistance analysis theory. The impact of external environment and ship draft on energy consumption is simplified, and the energy consumption and speed mechanism model is improved by introducing an energy efficiency influence factor coefficient. The above data is collected periodically, and the model is continuously improved through data-driven refinement using deep learning algorithms, making the model more accurate. An optimization algorithm is then used to optimize the model, providing auxiliary decision-making suggestions for dredger dispatch speed. This provides scientific decision support for ship dispatch and dredging speed, improving the ship's energy efficiency and environmental performance. Attached Figure Description

[0027] Figure 1 is a flowchart of the LNG dual-fuel powered trailing suction hopper dredger speed auxiliary decision-making method of the present invention;

[0028] Figure 2 is a detailed flowchart of step S2 of the LNG dual-fuel power trailing suction hopper dredger speed auxiliary decision-making method of the present invention.

[0029] Figure 3 is a detailed flowchart of step S3 of the LNG dual-fuel power trailing suction hopper dredger speed auxiliary decision-making method of the present invention.

[0030] Figure 4 is a detailed flowchart of step S4 of the LNG dual-fuel powered trailing suction hopper dredger speed auxiliary decision method of the present invention. Detailed Implementation

[0031] The technical solution of the present invention will now be clearly and completely described in conjunction with the accompanying drawings. In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0032] The invention will now be further described with reference to the accompanying drawings.

[0033] As shown in Figures 1-4, a speed auxiliary decision-making method for an LNG dual-fuel powered trailing suction hopper dredger includes:

[0034] Step S1: Collect actual ship data;

[0035] Step S2: Collect operating data and establish a database for identifying the operating conditions of trailing suction hopper dredgers;

[0036] Step S3: Establish a database of LNG fuel main engine energy consumption and speed;

[0037] Step S4: Through speed optimization and learning correction, provide auxiliary decision-making suggestions for dispatch speed.

[0038] This method for speed assistance decision-making for LNG dual-fuel trailing suction hopper dredgers establishes a working condition identification model based on the dredger's construction process and equipment status sensor data. Based on the mechanism model of the main engine's unit-time energy consumption and speed, it considers the influence factors of water environment, ship draft, and main engine operating status on the ship's energy efficiency and speed. The impact of energy efficiency factors on the ship is simplified into a mathematical model related to the ship's draft and slip rate. This model is then corrected using a data-driven deep learning algorithm. Finally, the optimal value of the model is calculated using an optimization algorithm, providing speed assistance decision-making suggestions for the dredger during navigation.

[0039] Step S1, collecting real-ship data, includes: collecting the LNG fuel consumption of the trailing suction hopper dredger's main engine. LNG The speed of the trailing suction hopper dredger relative to the ground is v. d Collect wind speed v wind Wind direction D wind Collect propeller pitch ratio PD; collect propeller rotational speed n p ; Collect ship draft T d .

[0040] Trailing suction hopper dredger main engine LNG fuel consumption FCLNG Data is collected via mass flow meters installed on the outlet / inlet pipelines of the LNG storage tank; the trailing suction hopper dredger collects its ground speed (v) via a GPS system. d The trailing suction hopper dredger collects wind speed (v) using an anemometer. wind Wind direction D wind Environmental information; the trailing suction hopper dredger collects propeller pitch ratio (PD) and propeller speed (n) via a variable pitch (CPP) system. p Trailing suction hopper dredgers calculate their draft (T) using draft sensors and cargo hold volume. d .

[0041] Step S1 also includes using the system to partition and store the collected data in MySQL database, with the database simultaneously storing parameter data from the energy efficiency and speed mechanism models and mathematical models.

[0042] Step S2, collecting operating condition data and establishing a trailing suction hopper dredger operating condition identification database, includes:

[0043] Step S21: Based on the construction process and the actual condition of the vessel, the single trip of the trailing suction hopper dredger is divided into five working conditions: dredging, dumping, navigation, blowing, and other working conditions. Among them, the navigation condition is divided into heavy-load navigation and light-load navigation, and other working conditions include berthing, docking, and non-construction working conditions.

[0044] Step S22: Read the data from the equipment sensors in real time through the PLC of the dredger, including the limit signals, switch signals, and gate valve signals of the trailing suction dredger's construction equipment and devices;

[0045] Step S23: Based on the construction process and logical sequence of the trailing suction hopper dredger, identify the working conditions of the dredger. Then, based on the output results of the working condition identification, filter the data on energy efficiency, water environment, speed, and construction history, and select the heavy-load navigation data and light-load navigation data during the navigation process to provide a data foundation for subsequent model construction and optimization.

[0046] The automatic operating condition identification module reads data from equipment sensors in real time through the dredger's self-control PLC, including limit signals, switch signals, and gate valve signals from the trailing suction hopper dredger's construction equipment or devices. Based on the construction process and the actual conditions of the vessel, it categorizes a single trip of the trailing suction hopper dredger into five operating conditions: dredging, dumping, navigation, blowing, and other. The navigation condition is further divided into heavy-load and light-load navigation, while other operating conditions include non-construction conditions such as berthing, docking, and shutdown. The logical judgment of the automatic operating condition identification model is as follows:

[0047] Step S3, establishing the LNG fuel main engine energy consumption and speed database, includes:

[0048] Step S31: During navigation, the main engine power is transmitted to the propeller through the propulsion bearing. The propeller overcomes the resistance caused by the environment during navigation, providing effective power to propel the ship. During this process, the drag coefficient caused by factors such as the water environment is C. d The ship's speed is V; therefore, according to the theoretical formula, the effective power of the dredger per unit time is P. d =f(C d ,V);

[0049] Combined with the main engine fuel consumption rate g e The LNG fuel consumption per unit time and ship speed mechanism model can be obtained as FC LNG =g e ·P d ;

[0050] During navigation, the main engine power is transmitted to the propeller through the propulsion bearing. The propeller then overcomes the resistance caused by the environment, providing effective power to propel the ship. In this process, the drag coefficient caused by factors such as the water environment is C. d Therefore, according to the theoretical formula, the total resistance of the dredger during navigation can be obtained as R. d =0.5ρSV 2 C d

[0051] Where: ρ—seawater density;

[0052] S—Wetted surface area of ​​the hull;

[0053] V – Ship speed.

[0054] The effective power of a ship per unit time is

[0055] In the formula: η s —Push shaft transmission efficiency;

[0056] η d —Improve efficiency.

[0057] Combined with the main engine fuel consumption rate g e The mechanism model for LNG fuel consumption per unit time and ship speed can be obtained as follows:

[0058] Step S32, combining the energy consumption and speed mechanism model from step S31, under a single operating condition, the main engine fuel consumption rate g e Approaching a constant, the mechanism model and the total drag coefficient C d Related; slip ratio can reflect the influence of the aquatic environment on the resistance of ship navigation to a certain extent; the formula for calculating slip ratio is... Introducing an energy efficiency impact factor coefficient can reflect the external environment's stress on the ship, thus affecting its energy consumption. This coefficient can be expressed as a mathematical model f. Cd =f(Slip,T) d );

[0059] Based on the energy consumption and speed mechanism model in step S31, under a single operating condition, Approaching a constant, the mechanism model and the total drag coefficient C d Strongly correlated, while the total damping coefficient is affected by environmental factors such as wind, waves, and currents, as well as the ship's draft. Currently, the wind, wave, and current coefficients are difficult to measure in real time using sensors, so the slip ratio can reflect the impact of the aquatic environment on ship navigation to a certain extent. The formula for calculating the slip ratio is... Theoretical speed = PD * n p *60 / 1852. Introducing the energy efficiency impact factor coefficient can be expressed as a mathematical model f. cd =f(Slip,T) d ).

[0060] Step S33: Based on steps S31 and S32, simplify the LNG fuel consumption and ship speed mechanism model to FC. LNG =f(Slip,T) d )·V 3 .

[0061] Step S4, through the speed optimization module, corrects the learning and provides auxiliary decision-making suggestions for dispatch speed, including:

[0062] Step S41: Periodically collect a large amount of data on actual ship pitch, ship draft, speed, and LNG fuel consumption, and the data under navigation conditions filtered from the operating condition identification database in step S2. Use data-driven deep learning algorithms to correct the LNG energy consumption and speed model in step S3 to improve the model's generalization ability and accuracy.

[0063] Step S42: For the corrected mathematical model of LNG energy consumption and speed with higher accuracy, an optimization algorithm is used to optimize the mathematical model with the goal of minimizing LNG fuel consumption per unit time, and obtain the optimal speed V0 to provide speed auxiliary decision-making suggestions during ship dispatch.

[0064] The model correction section includes periodically collecting data on actual ship pitch, draft, speed, and LNG fuel consumption. The automatic operating condition identification module filters light-load and heavy-load navigation data from the MySQL energy efficiency database. During deployment, the trailing suction hopper dredger mostly navigates empty (light-load), with only a few instances of heavy-load navigation. Using both light-load and heavy-load navigation data, a random forest algorithm is applied to optimize the FC (Fuel Consumption) data. LNG =f(Slip,T) d )·V 3 The model underwent data fitting and correction, and the energy consumption navigation model parameters for light-load and heavy-load navigation were stored in the MySQL energy efficiency database. Then, the particle swarm optimization (PSO) algorithm was used to optimize the mathematical model with the minimum LNG fuel consumption per unit time as the optimization objective, and the optimal speed V0 for light-load or heavy-load navigation was obtained.

[0065] This method for speed-assisted decision-making in LNG dual-fuel trailing suction hopper dredgers combines the use of sensors on the LNG-fueled dredger to automatically monitor and collect LNG fuel consumption, aquatic environmental parameters, and construction data. It introduces an automatic operating condition identification module to label data under different navigation conditions. The LNG energy consumption and speed mechanism model is established based on ship main engine characteristics and ship resistance analysis theory. The impact of external environment and ship draft on energy consumption is simplified, and the energy consumption and speed mechanism model is improved by introducing an energy efficiency influence factor coefficient. The method periodically collects the above data and continuously refines the model through data-driven learning using deep learning algorithms, making the model more accurate. Finally, an optimization algorithm optimizes the model to provide auxiliary decision-making suggestions for dredger dispatch speed, providing scientific decision support for ship dispatch and dredging speed, and improving the ship's energy efficiency and environmental performance.

[0066] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for LNG dual-fuel propulsion trailing suction dredger speed aided decision-making, characterized in that, Comprise; Step S1, collect real ship data; Step S2, collect working condition data, establish a database for identifying the working conditions of a drag suction dredger; Step S3, establish a database for the energy consumption of an LNG fuel main engine and the speed of the dredger; Step S4, through speed optimization, correction learning, and providing auxiliary decision-making suggestions for dispatching speed.

2. The LNG dual-fuel tractor dredger speed-assisted decision-making method according to claim 1, characterized in that, The step S1, collecting the real ship data, comprises: collecting the LNG fuel consumption FC of the main engine of the trailing suction dredger LNG ; collecting the ground speed v d of the trailing suction dredger; collecting the wind speed v wind , the wind direction D wind ; collecting the propeller pitch ratio PD; collecting the propeller rotating speed n p ; and collecting the ship draft T d .

3. The LNG dual-fuel dredger speed-assisted decision method according to claim 1, characterized in that, Said step S2, collecting working condition data, and establishing a database for identifying the working conditions of a drag suction dredger, comprises: Step S21, according to the construction process and the actual situation of the ship, the single trip of the drag suction dredger is divided into five working conditions, which are: dredging working condition, mud throwing working condition, sailing working condition, mud blowing working condition, and other working conditions; among them, the sailing working condition is divided into heavy load sailing and light load sailing, and the other working conditions include berthing, docking, and non-construction working conditions during stoppage; Step S22, real-time reading of equipment sensor data through the self-control PLC of the dredger, including the limit signal, switch signal, and gate valve signal of the construction equipment and device of the drag suction dredger; Step S23, according to the construction process and logical time sequence of the drag suction dredger, the working conditions of the dredger are identified, and then according to the output results of the working condition identification, the data of energy efficiency, water environment, speed, and construction history are filtered to select the heavy load sailing data and light load sailing data during sailing, providing a data basis for subsequent model construction and optimization.

4. The LNG dual-fuel dredger speed-assisted decision method of claim 1, wherein, Said step S3, establishing a database for the energy consumption of an LNG fuel main engine and the speed of the dredger, comprises: Step S31, during the sailing process, the main engine power is transmitted to the propeller through the propeller bearing, and the propeller provides effective power to push the ship sailing against the resistance caused by the environment during the sailing process; during this process, the ship is subjected to the resistance coefficient C d caused by the water environment and other factors; the ship speed is V; therefore, according to the theoretical formula, the effective power of the dredger per unit time can be obtained as P d =f(C d ,V). Combining the host fuel consumption rate g e The LNG fuel consumption per unit time can be obtained as FC LNG = g e · P d ; Step S32, combined with the energy consumption and speed mechanism model in step S31, in a single working condition, the main engine fuel consumption rate g e is close to a constant, the mechanism model and the total resistance coefficient C d are related; the slip rate Slip can reflect the influence of the water environment on the ship's sailing resistance to a certain extent; the calculation formula of the slip rate is The energy efficiency influence factor coefficient can reflect the influence of the external environment on the stress of the ship, thereby affecting the energy consumption of the ship. The coefficient can be expressed as a mathematical model Step S33, according to step S31 and step S32, simplifying the LNG fuel consumption and the ship speed mechanism model into FC LNG = f(Slip, T d ) · V 3 .

5. The LNG dual-fuel tractor dredger speed-assisted decision-making method according to claim 1, characterized in that, Said step S4, through the speed optimization module, correction learning, and providing auxiliary decision-making suggestions for dispatching speed, comprises: Step S41, periodically collecting a large amount of data of real ship pitch, ship draft, speed, and LNG fuel consumption, and filtering the data of sailing working condition from the working condition identification database in step S2, using a data-driven deep learning algorithm to correct the LNG energy consumption and speed model in step S3, and improving the generalization ability and accuracy of the model; Step S42, for the LNG energy consumption and speed mathematical model with higher accuracy after correction, using an optimization algorithm to optimize the mathematical model with the lowest LNG fuel consumption per unit time as the optimization target, to obtain the optimal speed V0, and realize the auxiliary decision-making suggestions for the speed of the ship during dispatching.

6. The LNG dual-fuel tractor dredger speed-assisted decision-making method according to claim 2, characterized in that, Trailing suction hopper dredger main engine LNG fuel consumption FC LNG Data is collected via mass flow meters installed on the outlet / inlet pipelines of the LNG storage tank; the trailing suction hopper dredger collects its ground speed (v) via a GPS system. d The trailing suction hopper dredger collects wind speed (v) using an anemometer. wind Wind direction D wind Environmental information; the trailing suction hopper dredger collects propeller pitch ratio (PD) and propeller speed (n) via a variable pitch system. p Trailing suction hopper dredgers calculate their draft (T) using draft sensors and cargo hold volume. d .

7. The LNG dual-fuel tractor dredger speed-assisted decision-making method according to claim 2, characterized in that, Said step S1 further comprises storing the collected data in tables through the system using MySQL data, and the database simultaneously stores the parameter data of the energy efficiency and speed mechanism model and the mathematical model.

Images