Method and device for optimizing navigation of vessel

Abstract

The present disclosure relates to a method and apparatus for optimizing the navigation of a vessel. The method according to one embodiment of the present disclosure can generate recommended navigation information on a navigation path of a ship on the basis of navigation plan information relating to a departure point and an arrival point of the ship, predict a BOG generation amount of the ship and a tank pressure value of the ship on the basis of the recommended navigation information, and predict a BOG generation amount of the ship on the basis of the predicted BOG generation amount. And acquires optimal navigation information relating to the operation control of the ship on the basis of the BOG generation amount and the tank pressure value.

Description

Technical Field

[0001] The present disclosure relates to a method and apparatus for optimizing the navigation of a ship. Background Art

[0002] Generally, during the transportation of liquefied gas by a ship, natural vaporized gas is generated in the liquefied gas storage tank, and this gas is called boil-off gas (BOG).

[0003] When BOG is generated, the pressure inside the storage tank rises, and the increase in the pressure inside the storage tank reduces the safety of the liquefied gas storage tank, thus there is a risk that the storage tank may explode. To prevent this danger, BOG is discharged, and environmental pollution may be caused and liquefied gas may be wasted during this process.

[0004] On the other hand, to maintain the pressure inside the storage tank, BOG is used as fuel for the propulsion engine or power generation engine of the ship. When there is still a surplus after being used as fuel, it can be liquefied by a reliquefaction device and stored in the cargo hold, or it can be removed by a gas combustion unit (GCU).

[0005] Therefore, the navigation cost of the ship varies greatly according to the amount of BOG generated during the transportation of liquefied gas, ship speed, power consumption, BOG treatment method, sea area location of different navigation routes, or climate change, etc. When formulating an economic navigation plan, there are problems that are difficult to predict. In particular, since the cargo handling system (CHS) of each ship is different, there is the above-mentioned complexity when analyzing the economic driving mode, and the amount of BOG generated also varies according to different navigation routes. Therefore, for ship drivers, there is a problem that it is difficult to perform the best driving to minimize the consumption of liquefied gas. Therefore, a method for effectively controlling a liquefied gas carrier in a driving mode that minimizes the consumption of liquefied gas is needed.

[0006] The foregoing background art is retained by the inventor for deriving the present invention, or technical information learned during the derivation process of the present invention, and should not be construed as well-known art known to the general public before the application of the present invention. Summary of the Invention

[0007] Technical Problems to be Solved by the Invention

[0008] The present invention aims to provide a method and apparatus for optimizing the navigation of a ship. In addition, it aims to provide a computer-readable recording medium recording a program for executing the method on a computer.

[0009] The problems to be solved by the present invention are not limited to those mentioned above. Other problems and advantages not mentioned in the present invention can be understood through the following description and can be more clearly understood through the embodiments of the present invention. In addition, it should be understood that the problems and advantages to be solved by the present invention can be achieved by the devices and their combinations pointed out in the claims of the patent.

[0010] Technical Solution

[0011] As a technical means for achieving the above technical problems, the first aspect of the present disclosure may provide a method for optimizing the navigation of a ship, which includes: a generation step of generating recommended navigation information about the navigation path of the ship based on navigation plan information related to the departure location and arrival location of the ship; a prediction step of predicting the BOG generation amount of the ship and the tank pressure value of the ship based on the recommended navigation information; and an acquisition step of acquiring the optimal navigation information related to the motion control of the ship based on the BOG generation amount and the tank pressure value.

[0012] The second aspect of the present disclosure may provide a computing device, which includes: at least one memory and at least one processor, wherein the processor generates recommended navigation information about the navigation path of the ship based on navigation plan information related to the departure location and arrival location of the ship, predicts the BOG generation amount of the ship and the tank pressure value of the ship based on the recommended navigation information, and acquires the optimal navigation information related to the motion control of the ship based on the BOG generation amount and the tank pressure value.

[0013] The third aspect of the present disclosure may provide a computer-readable recording medium that records a program for executing the method according to the first aspect on a computer.

[0014] In addition, a computer-readable recording medium may be provided, which stores another method, another system for implementing the present invention, and a computer program for executing the method.

[0015] Other aspects, features, and advantages other than the above will become clear through the following drawings, claims, and detailed description of the invention.

[0016] Beneficial Effects

[0017] According to the method for solving problems in the foregoing present disclosure, in the present disclosure, based on navigation plan information related to the departure location and arrival location of the ship, recommended navigation information about the navigation path of the ship is generated, the BOG generation amount of the ship and the tank pressure value of the ship are predicted based on the recommended navigation information, and the optimal navigation information related to the motion control of the ship is acquired based on the BOG generation amount and the tank pressure value, so that an economical navigation that minimizes the liquefied gas consumption of the ship can be achieved.

[0018] In addition, according to the problem-solving method of the present disclosure, the BOG generation amount and the storage tank pressure value are predicted based on one or more environmental information including meteorological and climate information, tidal current information, marine information, and ocean current information of each position on the navigation path of the ship, and the optimal navigation information is obtained based on the predicted BOG generation amount and the storage tank pressure value to calculate the entire navigation driving, so that direction suggestions for cargo management from the departure place to the arrival place of the ship can be provided, and safe cargo handling can be achieved based on the predicted storage tank pressure value.

[0019] In addition, according to the problem-solving method of the present disclosure, the optimal navigation information is obtained by updating the ship speed and the liquefied gas consumption amount on the navigation path to provide ship driving guidance to the driver, so that navigation can be assisted, and the carbon tax reduction effect can be provided by reducing the GCU incineration amount and the fuel gas amount of the engine.

[0020] The effects of the present invention are not limited to the above-mentioned effects, and those of ordinary skill in the art can clearly understand other effects not mentioned from the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is a diagram for illustrating an example of a system for optimizing the navigation of a ship according to an embodiment.

[0022] Figure 2 is a configuration diagram showing an example of a user terminal according to an embodiment.

[0023] Figure 3 is a configuration diagram showing an example of a server according to an embodiment.

[0024] Figure 4 is a flowchart for illustrating an example of a method for optimizing the navigation of a ship according to an embodiment.

[0025] Figure 5 is a flowchart for illustrating an example of a processor generating recommended navigation information based on navigation plan information according to an embodiment.

[0026] Figure 6 is a flowchart for illustrating an example of a processor predicting the BOG generation amount of a ship and the storage tank pressure value of the ship based on the recommended navigation information according to an embodiment.

[0027] Figure 7 is a flowchart for illustrating an example of a processor obtaining the optimal navigation information based on the BOG generation amount and the storage tank pressure value according to an embodiment.

[0028] Figure 8It is a flowchart for explaining another example of a processor according to an embodiment obtaining optimal navigation information based on BOG generation amount and storage tank pressure value.

[0029] Fig. 9 It is a flowchart for explaining another example of a method for optimizing the navigation of a ship according to an embodiment.

[0030] Fig.10 It is a diagram for explaining an example of a method for predicting BOG generation amount according to an embodiment.

[0031] Fig.11 It is a flowchart for explaining an example of a method for predicting BOG generation amount of a ship according to an embodiment.

[0032] Fig.12 It is a diagram for explaining an example of calculating gas consumption of a ship according to an embodiment.

[0033] Fig.13a It is a configuration diagram showing an example of a stacked model according to an embodiment.

[0034] Fig.13b It is a configuration diagram showing an example of a BOG generation amount prediction model of a ship according to an embodiment.

[0035] -----------------------Content deleted-----------------------

[0036] Fig.14 It is a diagram for explaining an example of calculating correct data for learning according to an embodiment.

[0037] Fig.15a It is a diagram for explaining a processor 110 according to an embodiment removing loss data from data stored in a memory 120.

[0038] Fig.15b It is a diagram for explaining an example of separating a part of pre-stored navigation data into learning data for an input data selection model and separating another part of the data into verification data for a BOG generation amount prediction model of a ship according to an embodiment.

[0039] Fig.16a It is a diagram for explaining an example of obtaining current navigation data of a ship from the outside of the ship according to an embodiment.

[0040] Fig.16b It is a diagram for explaining an example of obtaining current navigation data of a ship from the inside of the ship according to an embodiment.

[0041] Fig.17 It is a diagram for illustrating an example of applying weights to a predicted value of an initial BOG generation amount to calculate a predicted value of a final BOG generation amount according to an embodiment.

[0042] Fig.18 It is a diagram for illustrating an example of a method for predicting a storage tank pressure of a ship according to an embodiment.

[0043] Fig.19 It is a flowchart for illustrating an example of a method for predicting a storage tank pressure of a ship according to an embodiment.

[0044] Fig.20a It is a diagram for illustrating an example of separating a part of pre-stored actual voyage data into learning data and separating another part into verification data according to an embodiment.

[0045] Fig.20b It is a diagram for illustrating an example of a process of processing pre-stored actual voyage data according to an embodiment.

[0046] Fig.21 It is a diagram for illustrating an example of a process of learning a deep learning model for predicting a storage tank pressure of a ship according to an embodiment.

[0047] Fig. 22 It is a diagram for illustrating an example of determining a navigation mode according to whether the level of liquefied gas in a storage tank is above a specified height according to an embodiment.

[0048] Fig.23 It is a diagram for illustrating an example of a deep learning model corresponding to each of multiple navigation modes according to different levels of liquefied gas in a storage tank according to an embodiment.

[0049] Fig.24 It is a diagram for illustrating an example of applying weights to multiple intermediate values to obtain a predicted value of a storage tank pressure according to an embodiment.

[0050] Fig.25 It is a diagram for illustrating an example of a method for optimizing the navigation of a ship according to an embodiment.

[0051] Fig.26 It is a flowchart for illustrating an example of a method for optimizing the navigation of a ship according to an embodiment.

[0052] Fig. 27 It is a diagram for illustrating an example of obtaining optimal navigation information in different ways according to whether the speeds of each navigation section included in recommended navigation information are utilized during the navigation of a ship according to an embodiment.

[0053] Fig.28a It is a flowchart for illustrating an example of obtaining optimal navigation information when using the speeds of respective navigation sections included in recommended navigation information during the navigation of a ship according to an embodiment.

[0054] Fig.28b It is a flowchart for illustrating an example of obtaining optimal navigation information when not using the speeds of respective navigation sections included in recommended navigation information during the navigation of a ship according to an embodiment.

[0055] Fig.29 It is a diagram for illustrating an example of a system for controlling the navigation of a ship according to an embodiment.

[0056] Fig.30 It is a configuration diagram showing an example of a server according to an embodiment.

[0057] Fig.31 It is a flowchart for illustrating an example of a method for controlling the navigation of a ship according to an embodiment.

[0058] Fig.32 It is a diagram showing an example of a screen for displaying preset navigation information of a ship according to an embodiment.

[0059] Fig.33 It is a diagram showing an example of a screen that can obtain any one of a manually set route of a ship and a route automatically set through a route optimization function according to an embodiment.

[0060] Fig.34 It is a diagram for illustrating an example of a method for calculating a predicted value of the pressure of a liquefied gas cargo tank according to an embodiment.

[0061] Fig.35a It is a diagram showing an example of a comparison result between a predicted value and a measured value of the internal pressure of a liquefied gas cargo tank and a comparison result between an average speed and a measured value according to an embodiment.

[0062] Fig.35b It is a diagram showing an example of a comparison result between a predicted value and a measured value of the amount of liquefied gas evaporated from a liquefied gas cargo tank according to an embodiment.

[0063] Fig.35c It is a diagram showing an example of a comparison result between an energy efficiency operation index of a ship and a measured value according to an embodiment.

[0064] Fig.36 It is a diagram showing an example of a screen displayed by a processor according to an embodiment. Detailed implementation manners

[0065] The present disclosure relates to a method and apparatus for optimizing the navigation of a ship. According to a method of an embodiment of the present disclosure, recommended navigation information regarding the navigation path of a ship can be generated based on navigation plan information related to the departure location and arrival location of the ship, and the BOG generation amount and the tank pressure value of the ship can be predicted based on the recommended navigation information, and based on the BOG generation amount and the tank pressure value, optimal navigation information related to the action control of the ship can be obtained. Specific embodiments

[0067] Hereinafter, various embodiments of the present disclosure will be described with reference to the accompanying drawings. The various embodiments of the present disclosure can be variously changed and have various embodiments, and specific embodiments are illustrated in the drawings and related detailed descriptions are described. However, it should be understood that this is not intended to limit the various embodiments of the present disclosure to a specific implementation manner, but includes all changes and / or equivalents or substitutes included in the spirit and technical scope of the various embodiments of the present disclosure. In the description with reference to the accompanying drawings, similar components are given similar reference numerals.

[0068] Expressions such as "including" or "may include" that can be used in various embodiments of the present disclosure refer to the existence of corresponding functions, actions, or components of the disclosure, and do not limit the addition of one or more functions, actions, or components. In addition, it should be understood that terms such as "including" or "having" in various embodiments of the present disclosure are used to specify the existence of features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and are not used to preclude the existence or possibility of addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof in advance.

[0069] In various embodiments of the present disclosure, expressions such as "or" include any and all combinations of the words listed together. For example, "A or B" may include A, may include B, or may include both A and B.

[0070] Expressions such as "first", "second", "the first", or "the second" used in various embodiments of the present disclosure may modify various components of the various embodiments, but do not limit the corresponding components. For example, the expressions do not limit the order and / or importance of the corresponding components. The expressions can be used to distinguish one component from other components. For example, the first user equipment and the second user equipment are both user equipment and represent different user equipment from each other. For example, without departing from the scope of the rights of the various embodiments of the present disclosure, the first component may be named the second component, and similarly, the second component may also be named the first component.

[0071] In an embodiment of the present disclosure, terms such as "module", "unit", "part", etc. refer to elements that perform at least one function or action, and such elements can be implemented by hardware or software, or by a combination of hardware and software. Moreover, multiple "modules", "units", "parts", etc. are integrated as at least one module or chip, except in cases where each requires separate specific hardware implementation, so as to be implemented by at least one processor.

[0072] The terms used in various embodiments of the present disclosure are only used to illustrate specific embodiments and are not used to limit the various embodiments of the present disclosure. Unless otherwise clearly specified in the context, a singular expression includes a plural expression.

[0073] Unless otherwise defined, all terms used herein, including technical terms and scientific terms, have the same meaning as commonly understood by those of ordinary skill in the technical field to which the various embodiments of the present disclosure belong.

[0074] Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the related art, and should not be interpreted as ideal or overly formal meanings unless clearly defined in the various embodiments of the present disclosure.

[0075] In the present invention, liquefied gas can be used to mean all gaseous fuels that are usually stored in a liquid state. The gaseous fuels can be, for example, liquefied natural gas (LNG), liquefied petroleum gas (LPG), ethylene, ammonia, hydrogen, etc. In cases where they are no longer in a liquid state due to heating or pressurization, etc., they can also be conveniently referred to as liquefied gas. This also applies to boil-off gas.

[0076] Among them, for convenience, LNG can be used to mean natural gas (NG) in a liquid state and natural gas (NG) in a supercritical state, etc., and boil-off gas can be used to mean boil-off gas in a gaseous state and liquefied boil-off gas.

[0077] In addition, gas consumption can be used to mean including both the consumption of liquefied gas and the consumption of BOG, or can also be used to mean each of the consumption of liquefied gas or the consumption of BOG separately.

[0078] Among them, BOG (Boil-Off Gas) refers to the natural evaporation and gasification of natural gas in the storage tanks of ships. Usually, liquefied gas is transported in a cryogenic liquid state, and the storage tanks of ships used to store liquefied gas are composed of heat-insulating structures to maintain cryogenic temperatures. However, since the external temperature of the storage tank is about 40°C, the temperature difference between the inside and outside of the ship's storage tank is more than about 200°C, so it is impossible to completely block the heat inflow from the outside. The BOG generated by the heat flowing into the storage tank will cause economic problems.

[0079] Hereinafter, various embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0080] Figure 1 It is a diagram for explaining an example of a system for optimizing ship navigation according to an embodiment.

[0081] Refer to Figure 1 , the system 1 includes a user terminal 10 and a server 20. For example, the user terminal 10 and the server 20 can be connected by wired or wireless communication means to send and receive data to and from each other (for example, voyage plan information, recommended navigation information, BOG generation amount, storage tank pressure value, optimal navigation information, etc.).

[0082] For the sake of convenience of explanation, Figure 1 it is shown that the system 1 includes a user terminal 10 and a server 20, but it is not limited thereto. For example, the system 1 can include other external devices (not shown), and the operations of the user terminal 10 and the server 20 described below can be implemented by a single device (for example, the user terminal 10 or the server 20) or multiple devices.

[0083] The user terminal 10 can be a computing device including a display device and a device for receiving user input (for example, a keyboard, a mouse, etc.) and including a memory and a processor. For example, the display device can be implemented by a touch screen to receive user input. For example, the user terminal 10 can include a notebook computer, a desktop computer, a laptop computer, a tablet computer, a smart phone, etc., but it is not limited thereto.

[0084] The server 20 can be a device including the user terminal 10 and communicating with external devices (not shown). As an example, the server 20 can be a device for storing various data, including voyage plan information, recommended navigation information, BOG generation amount, storage tank pressure value, optimal navigation information, etc.

[0085] Alternatively, the server 20 can be a computing device including a memory and a processor and having its own computing power. As an example, the server 20 can execute the operations that will be described below with reference to Figures 1 to 36At least a part of the actions of the user terminal 10 described. For example, the server 20 can also be a cloud server, but is not limited thereto.

[0086] The user terminal 10 can obtain optimal navigation information related to the operation control of the ship. For example, the user terminal 10 can generate recommended navigation information about the navigation path of the ship based on the navigation plan information related to the departure location and arrival location of the ship. And, the user terminal 10 can predict the BOG generation amount of the ship and the tank pressure value of the ship based on the recommended navigation information. And, the user terminal 10 can obtain optimal navigation information related to the operation control of the ship based on the BOG generation amount and the tank pressure value.

[0087] On the other hand, the user terminal 10 can control the ship in a preset driving manner using the optimal navigation information. For example, the user terminal 10 can control the ship in a driving manner that minimizes the liquefied gas consumption of the ship using the learned optimal navigation information.

[0088] For example, the user terminal 10 can obtain optimal navigation information related to the operation control of the ship through an application program provided in the user terminal 10, and control the ship in a preset driving manner using the optimal navigation information. Among them, the application program can be a software program set for the navigation plan and control activities of the user 30. For example, the user 30 can perform various navigation plan and control activities such as the generation of recommended navigation information, the prediction of the BOG generation amount, the prediction of the tank pressure value, the acquisition of optimal navigation information, and the driving of the ship through the application program.

[0089] On the other hand, for the sake of convenience of explanation, throughout the specification, it is described that the user terminal 10 generates recommended navigation information about the navigation path of the ship based on the navigation plan information related to the departure location and arrival location of the ship, and based on the recommended navigation information, predicts the BOG generation amount of the ship and the tank pressure value of the ship, and based on the BOG generation amount and the tank pressure value, obtains optimal navigation information related to the operation control of the ship, but is not limited thereto. For example, at least a part of the actions performed by the user terminal 10 can be performed by the server 20.

[0090] In other words, hereinafter, with reference to Figures 1 to 36At least a part of the operations of the illustrated user terminal 10 can be executed by the server 20. For example, the server 20 can generate recommended navigation information regarding the navigation path of a ship based on voyage plan information related to the departure location and arrival location of the ship, and predict the BOG generation amount of the ship and the tank pressure value of the ship based on the recommended navigation information, and obtain optimal navigation information related to the operation control of the ship based on the BOG generation amount and the tank pressure value. Also, the server 20 can control the ship in a preset driving mode using the optimal navigation information.

[0091] Figure 2 is a configuration diagram showing an example of a user terminal according to an embodiment.

[0092] Referring to Figure 2 , the user terminal 100 includes a processor 110, a memory 120, an input / output interface 130, and a communication module 140. For ease of explanation, Figure 2 only the components related to the present invention are shown. Thus, in addition to Figure 2 the components shown, the user terminal 100 may further include other general components. In addition, Figure 2 it is obvious to those skilled in the technical field related to the present invention that the processor 110, the memory 120, the input / output interface 130, and the communication module 140 shown can be implemented as independent devices.

[0093] The processor 110 can process the instructions of a computer program by performing basic arithmetic, logical, and input / output operations. Among them, the instructions can be provided by the memory 120 or an external device (such as the server 20, etc.). Also, the processor 110 can comprehensively control the operations of other components included in the user terminal 100.

[0094] First, the processor 110 generates recommended navigation information regarding the navigation path of a ship based on voyage plan information related to the departure location and arrival location of the ship. For example, the processor 110 can generate recommended navigation information regarding the navigation path of a ship based on the departure time of the ship's departure location, the arrival time of the ship's arrival location, and the location information of the location.

[0095] The departure location and the arrival location can include any area or port in the sea area where the ship sails, and are not limited to the above examples.

[0096] The voyage plan information can refer to information related to the voyage plan of a ship. For example, the voyage plan information can include one or more of the departure time of the ship's departure location, the arrival time of the ship's arrival location, the latitude and longitude of the departure location, the latitude and longitude of the arrival location, and the tank requirement conditions of the ship at the arrival location.

[0097] On the other hand, the voyage plan information can be received through the user's input, but can refer to preset information. For example, if the user sets the departure location and arrival location of the ship, then corresponding to the set departure location and arrival location, the arrival time of the ship, the latitude and longitude of the departure location, the latitude and longitude of the arrival location, the requirements for the ship's storage tanks at the arrival location, etc. can be received from the preset information. On the other hand, the voyage plan information is not limited to the above examples.

[0098] The recommended navigation information is information on the navigation route generated based on the voyage plan information, and can include one or more of the position information of each navigation section of the ship on the navigation route, the speed information of each navigation section of the ship, and the environmental information of each navigation section of the ship. The position information can include the latitude and longitude of each navigation section of the ship, the speed information can include the speed of each navigation section of the ship, and the environmental information can include one or more of the meteorological and climate information, tidal current information, sea information, and ocean current information of each navigation of the ship.

[0099] On the other hand, the recommended navigation information can be the following information: the information on the navigation route generated by obtaining the meteorological and climate information and sea information of each position based on the position of the departure / arrival location and the departure / arrival time of the ship, and considering the propulsion resistance and BOG generation amount of the ship calculated based on the meteorological and climate information and sea information of each position. However, the recommended navigation information is not limited to the above examples.

[0100] The navigation route can be the route with the lowest fuel efficiency. For example, it can be the route that minimizes the propulsion resistance and BOG generation amount of the ship, but is not limited to this.

[0101] On the other hand, the processor 110 can input the voyage plan information into the recommended navigation information generation model as input data to obtain the recommended navigation information as output data. As an example, the processor 110 can input the departure / arrival time and the position information of the departure / arrival location of the ship into the recommended navigation information generation model to obtain the recommended navigation information. Among them, the recommended navigation information generation model can be a model including information such as the speed-fuel quantity performance function of the propulsion engine of the ship, the electric power-fuel quantity performance function of the power generation engine of the ship, the electric power-fuel quantity performance function of the compressor / pump / relinquefaction device / GCU / subcooler of the ship, and the speed-electric power generation performance function of the shaft generator. As another example, the recommended navigation information can be obtained by using the navigation information generation model described below, and is not limited to this.

[0102] On the other hand, the processor 110 may obtain environmental information regarding the navigation path of the ship based on the navigation plan information. Further, the processor 110 may generate recommended navigation information based on the navigation plan information and the environmental information, with the fuel consumption and BOG generation amount of the ship's navigation path as a reference. As an example, the processor 110 may obtain meteorological and marine information at each location based on the departure / arrival time of the ship, the latitude and longitude of the departure / arrival location, and the storage tank requirement conditions at the arrival location, and predict the propulsion resistance and BOG generation amount of the ship based on the departure / arrival time of the ship, the latitude and longitude of the departure / arrival location, the storage tank requirement conditions at the arrival location, and the meteorological and marine information at each location, so as to generate recommended navigation information regarding the navigation path that minimizes the generated propulsion resistance and BOG generation amount of the ship.

[0103] In addition, the processor 110 may predict the BOG generation amount of the ship and the storage tank pressure value of the ship based on the recommended navigation information. Specifically, the processor 110 may predict the BOG generation amount of the ship based on at least one of the position information of each navigation section, the speed information of each navigation section, and the environmental information of each navigation section. Further, the processor 110 may predict the storage tank pressure value of the ship based on at least one of the position information of each navigation section, the speed information of each navigation section, the environmental information of each navigation section, and the preset liquefied gas consumption.

[0104] On the other hand, the processor 110 may obtain the BOG generation amount of the ship by using a prediction model. As an example, the processor 110 may input the position information of each navigation section, the speed information of each navigation section, and the environmental information of each navigation section into the prediction model as input data to obtain the BOG generation amount of the ship as output data. As another example, the processor 110 may use the BOG generation amount prediction model described below to obtain the BOG generation amount prediction value.

[0105] On the other hand, the processor 110 may use a prediction model to obtain the storage tank pressure value of the ship. As an example, the processor 110 may input the position information of each navigation section, the speed information of each navigation section, the environmental information of each navigation section, and the preset liquefied gas consumption into the prediction model as input data to obtain the storage tank pressure value of the ship as output data. As another example, the processor 110 may use the storage tank pressure prediction model described below to obtain the storage tank pressure value.

[0106] The liquefied gas consumption can be derived based on the gas consumption of the propulsion engine, the gas consumption of the power generation engine, the gas consumption of the gas combustion device, and the gas consumption of the reliquefaction device. As an example, the liquefied gas consumption can be the sum of one or more of the gas consumption of the propulsion engine, the gas consumption of the power generation engine, the gas consumption of the combustion device (GCU), the gas consumption of the reliquefaction device, the gas consumption of the compressor, and the gas consumption of the pump. As another example, the liquefied gas consumption can be the sum of the gas consumption of the ship itself and the gas consumption of the equipment installed on the ship, but is not limited thereto.

[0107] Moreover, the processor 110 can obtain the optimal navigation information related to the operation control of the ship based on the BOG generation amount and the storage tank pressure value. For example, the processor 110 can predict the speed of each section of the ship and the usage amount of the equipment installed on the ship based on the minimum liquefied gas consumption during the voyage. Among them, the equipment can include the propulsion engine (MainEngine), power generation engine (Generator Engine), gas combustion device (Gas Combustion Unit), reliquefaction device (Reliquefaction), shaft generator, and subcooler installed on the ship, etc. Moreover, the processor 110 can calculate the fuel amount of the ship's propulsion engine based on the predicted speed of each section of the ship, and calculate the gas consumption of the equipment based on the predicted usage amount of the equipment. Moreover, the processor 110 can determine the liquefied gas consumption based on the calculated fuel amount of the propulsion engine and the gas consumption of the equipment. Finally, the processor can obtain the optimal navigation information including the BOG generation amount of the ship, the storage tank pressure value of the ship, the speed of each navigation section of the ship, the liquefied gas consumption of the ship, and the usage amount of the equipment installed on the ship.

[0108] On the other hand, the processor 110 can generate the nth intermediate navigation information related to the operation control of the ship based on the BOG generation amount and the storage tank pressure value. Moreover, the processor 110 can determine the (n + 1)th intermediate navigation information as the optimal navigation information based on the comparison between the nth intermediate navigation information and the (n + 1)th intermediate navigation information with a preset threshold value. Among them, n can be a natural number greater than or equal to 1.

[0109] The method of generating the nth intermediate navigation information may be the same as the method of generating the optimal navigation information described above. The intermediate navigation information may include the BOG generation amount of the ship, the storage tank pressure value of the ship, the speeds of each navigation section of the ship, the liquefied gas consumption of the ship, and the usage amount of the equipment installed on the ship. For example, the processor 110 may predict the speeds of each section of the ship and the usage amount of the equipment installed on the ship so that the liquefied gas consumption during the voyage becomes the minimum liquefied gas consumption. Among them, the equipment may include the main engine, generator engine, gas combustion unit, reliquefaction unit, shaft generator, and subcooler installed on the ship, etc. And, the processor 110 may calculate the fuel amount of the ship's main engine based on the predicted speeds of each section of the ship, and calculate the gas consumption of the equipment based on the predicted usage amount of the equipment. And, the processor 110 may determine the liquefied gas consumption based on the calculated fuel amount of the main engine and the gas consumption of the equipment. Finally, the processor may obtain the first intermediate navigation information including the BOG generation amount of the ship, the storage tank pressure value of the ship, the speeds of each navigation section of the ship, the liquefied gas consumption of the ship, and the usage amount of the equipment installed on the ship. However, the method of obtaining the intermediate navigation information is not limited to the above example.

[0110] The (n + 1)th intermediate navigation information may be generated based on one or more updated values among the speed information and the liquefied gas consumption of each navigation section included in the nth intermediate navigation information. As an example, the (n + 1)th intermediate navigation information related to the motion control of the ship may be based on the updated value of the speed information of each navigation section included in the nth intermediate navigation information. As described above, the BOG generation amount of the ship and the storage tank pressure value of the ship are predicted, and obtained based on the predicted BOG generation amount and storage tank pressure value. Among them, the updated value of the speed information of each navigation section may be the speed of each navigation section included in the (n + 1)th intermediate navigation information.

[0111] The processor 110 may use one or more of the speeds and the liquefied gas consumption of each navigation section included in the nth intermediate navigation information as updated values to predict the BOG generation amount of the ship and the storage tank pressure value of the ship, and obtain the (n + 1)th intermediate navigation information related to the motion control of the ship based on the predicted BOG generation amount and storage tank pressure value.

[0112] On the other hand, the processor 110 may determine the (n + 1)-th intermediate navigation information as the optimal navigation information based on the difference calculated from the n-th intermediate navigation information and the (n + 1)-th intermediate navigation information, and in response to the difference being below a preset threshold. Further, the processor 110 may update one or more of the speed information and the liquefied gas consumption of each navigation section included in the (n + 1)-th intermediate navigation information to generate the (n + 2)-th intermediate navigation information in response to the difference exceeding the preset threshold.

[0113] On the other hand, the processor 110 may control the ship in a preset driving manner using the optimal navigation information. The driving manner may include a driving manner that minimizes the liquefied gas consumption of the ship.

[0114] The above generation model and prediction model may be, respectively, learned machine learning models. For example, the prediction model may be a deep learning model using an artificial neural network.

[0115] A machine learning model refers to a statistical learning algorithm implemented based on the structure of a biological neural network in machine learning technology and cognitive science or the structure that executes its algorithm.

[0116] For example, the machine learning model may be a model described as follows: like in a biological neural network, nodes (Nodes) that are artificial neurons forming a network through the combination of synapses learn by repeatedly adjusting the weights of the synapses to reduce the error between the correct output corresponding to a specific input and the inferred output, thereby having the ability to solve problems. For example, the machine learning model may include any probability model, neural network model, etc. for artificial intelligence learning methods such as machine learning and deep learning.

[0117] For example, the machine learning model may be implemented as a multilayer perceptron (MLP) composed of multiple layers of nodes and the connections between them. The machine learning model according to an embodiment of the present invention may be implemented using one of various artificial neural network model structures including an MLP. For example, the machine learning model may be composed of an input layer that receives input signals or data from the outside, an output layer that outputs output signals or data corresponding to the input data, and one or more hidden layers located between the input layer and the output layer that receive signals from the input layer, extract features, and transfer them to the output layer. The output layer receives signals or data from the hidden layer and outputs them to the outside.

[0118] Reference will be made to Figures 4 to 36 Describe a specific example of the operation of the processor 110 according to an embodiment.

[0119] The processor 110 can be implemented as an array of multiple logic gates or as a combination of a general-purpose microprocessor and a memory storing a program executable in the microprocessor. For example, the processor 110 can include a general-purpose processor, a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a controller, a microcontroller, a state machine, etc. In some environments, the processor 110 can also include an application-specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), etc. For example, the processor 110 can also refer to a combination of a digital signal processor (DSP) and a microprocessor, a combination of multiple microprocessors, a combination of one or more microprocessors combined with a digital signal processor (DSP) core, or a combination of any other similarly configured processing devices, etc.

[0120] The memory 120 can include any non-transitory computer-readable recording medium. As an example, the memory 120 can include non-permanent mass storage devices such as random access memory (RAM), read only memory (ROM), disk drives, solid state drives (SSD), flash memory, etc. As another example, non-permanent mass storage devices such as ROM, SSD, flash memory, disk drives, etc. can be separate permanent storage devices different from the memory. In addition, the memory 120 can store an operating system (OS) and at least one program code (e.g., code for the processor 110 to execute the actions to be described below with reference to Figures 4 to 36 the description).

[0121] These software components can be loaded from a computer-readable recording medium separately provided from the memory 120. Such a separately provided computer-readable recording medium can be a recording medium that can be directly connected to the user terminal 100. For example, it can include computer-readable recording media such as a floppy disk drive, a magnetic disk, a magnetic tape, a DVD / CD-ROM drive, a memory card, etc. Alternatively, the software components can also be loaded into the memory 120 through the communication module 140 instead of the computer-readable recording medium. For example, at least one program can be loaded into the memory 120 based on a computer program (e.g., a computer program for the processor 110 to execute the actions to be described below with reference to Figures 4 to 9 the computer program described, etc.), and the computer program is set by a file provided by a developer or a file distribution system for distributing installation files of application programs through the communication module 140.

[0122] The input / output interface 130 can be a device for interfacing with an input or output device (e.g., a keyboard, a mouse, etc.), and the input or output device can be connected to the user terminal 100 or can be included in the user terminal 100. The input / output interface 130 can be configured to be separate from the processor 110, but is not limited thereto, and can also be configured such that the input / output interface 130 is included in the processor 110.

[0123] The communication module 140 can provide a configuration or function for the server 20 and the user terminal 100 to communicate with each other through a network. Also, the communication module 140 can provide a configuration or function for the user terminal 100 to communicate with other external devices. For example, control signals, instructions, data, etc. provided under the control of the processor 110 can be sent to the server 20 and / or external devices through the communication module 140 and the network.

[0124] On the other hand, although not shown in Figure 2 the user terminal 100 may also include a display device. For example, the display device can also be implemented by a touch screen. Alternatively, the user terminal 100 can be connected to an independent display device through a wired or wireless communication method to enable data transmission and reception therebetween. For example, recommended navigation information or optimal navigation information, etc. can be provided through the display device.

[0125] Figure 3 is a configuration diagram showing an example of a server according to an embodiment.

[0126] Referring to Figure 3 , the server 200 includes a processor 210, a memory 220, and a communication module 230. For ease of explanation, Figure 3 only the components related to the present invention are shown in Figure 3In addition to the components shown, the server 200 may further include other general components. Furthermore, Figure 3 It will be apparent to those skilled in the art related to the technical field of the present invention that the processor 210, the memory 220, and the communication module 230 shown may be implemented as separate devices.

[0127] The processor 210 may generate recommended navigation information regarding the navigation path of the ship based on navigation plan information related to the departure location and arrival location of the ship. In addition, the processor 210 may predict the BOG generation amount of the ship and the tank pressure value of the ship based on the recommended navigation information. In addition, the processor 210 may obtain optimal navigation information related to the operation control of the ship based on the BOG generation amount and the tank pressure value. In addition, the processor 210 may control the ship in a preset driving manner using the optimal navigation information.

[0128] In other words, with reference to Figure 2 , at least one of the operations of the above-described processor 110 may be performed by the processor 210. In this case, the user terminal 100 may output the information transmitted from the server 200 through the display device.

[0129] On the other hand, the implementation example of the processor 210 is the same as the implementation example of the processor 110 described above with reference to Figure 2 , and thus, the detailed description is omitted.

[0130] The memory 220 may store various data such as data required for the operation of the processor 210 and data generated according to the operation of the processor 210. And, an operating system (OS) and at least one program (for example, a program required for the operation of the processor 210, etc.) may be stored in the memory 220.

[0131] On the other hand, the implementation example of the memory 220 is the same as the implementation example of the memory 120 described above with reference to Figure 2 , and thus, the detailed description is omitted.

[0132] The communication module 230 may provide a configuration or function for the server 200 and the user terminal 100 to communicate with each other through a network. And, the communication module 140 may provide a configuration or function for the server 200 to communicate with other external devices. For example, control signals, instructions, data, etc. provided according to the control of the processor 210 may be sent to the user terminal 100 and / or external devices through the communication module 230 and the network.

[0133] Figure 4 is a flowchart for explaining an example of a method for optimizing ship navigation according to an embodiment.

[0134] With reference to Figure 4, the method for optimizing ship navigation includes Figure 1 and Figure 2 the steps processed in the user terminals 10, 100 or the processor 110 shown in a time series. Therefore, even if content is omitted hereinafter, the above description regarding Figure 1 and Figure 2 the user terminals 10, 100 or the processor 110 shown can also be applied to Figure 4 the method for optimizing ship navigation.

[0135] In addition, as described above with reference to Figure 1 and Figure 3 , Figure 4 at least one of the steps of the method for optimizing ship navigation can be processed in the server 20, 200 or the processor 210.

[0136] In step 310, the processor 110 generates recommended navigation information regarding the navigation path of the ship based on the navigation plan information related to the departure location and arrival location of the ship.

[0137] As an example, the processor 110 can input the departure time of the ship's departure location, the arrival time of the ship's arrival location, the latitude and longitude of the departure location, and the latitude and longitude of the arrival location into the recommended navigation information generation model as input data to generate recommended navigation information as output data. The recommended navigation information generation model including information such as the speed - fuel quantity performance function of the ship's propulsion engine, the electric power - fuel quantity performance function of the ship's power generation engine, the electric power - fuel quantity performance function of the ship's compressor / pump / reliquefaction device / GCU / subcooler, and the speed - power generation performance function of the shaft generator can derive the route with the lowest fuel efficiency by analyzing the resistance performance of the ship according to the propulsion resistance of the ship. Herein, the fuel efficiency can refer to the fuel quantity consumed per unit travel distance or per unit time of the ship.

[0138] As another example, the processor 110 can obtain the meteorological and marine information of each location based on the departure time of the ship's departure location, the arrival time of the ship's arrival location, the latitude and longitude of the departure location, the latitude and longitude of the arrival location, and the storage tank requirement conditions of the arrival location, and predict the propulsion resistance and BOG generation amount of the ship based on the ship's departure / arrival time, the latitude and longitude of the departure / arrival location, the storage tank requirement conditions of the arrival location, the meteorological and marine information of each location, so as to generate recommended navigation information regarding the navigation path that minimizes the generated propulsion resistance and BOG generation amount of the ship.

[0139] Hereinafter, reference will be made to Figure 5Illustrate an example in which a processor generates recommended navigation information based on voyage plan information.

[0140] Figure 5 It is a flowchart for illustrating an example in which a processor generates recommended navigation information based on voyage plan information according to an embodiment.

[0141] Refer to Figure 5 In step 410, the processor 110 obtains environmental information about the navigation path of the ship based on the voyage plan information. For example, the processor 110 can obtain environmental information about the navigation path of the ship based on one or more of the departure time of the departure location of the ship, the arrival time of the arrival location of the ship, the latitude and longitude of the departure location, the latitude and longitude of the arrival location, and the tank requirement conditions of the ship at the arrival location.

[0142] Among them, the environmental information may include one or more of the meteorological and climatic information, tidal current information, maritime information, and ocean current information of each position included in the navigation path of the ship. On the other hand, the environmental information may refer to the information about the environment in the navigation path of the ship and is not limited to the above examples.

[0143] In step 420, the processor 110 generates recommended navigation information based on the voyage plan information and the environmental information, with the fuel consumption and BOG generation amount of the navigation path of the ship as the benchmark. For example, the processor 110 can predict the propulsion resistance and BOG generation amount of the ship based on the departure / arrival time of the ship, the latitude and longitude of the departure / arrival location, the tank requirement conditions at the arrival location, the meteorological and climatic information and maritime information of each position, thereby generating recommended navigation information about the navigation path that minimizes the generated propulsion resistance and BOG generation amount of the ship. Among them, when predicting the BOG generation amount, the processor 110 can predict the BOG generation amount of the ship considering the change in the external air temperature.

[0144] Refer to again Figure 4 In step 320, the processor 110 predicts the BOG generation amount of the ship and the tank pressure value of the ship based on the recommended navigation information. The obtained BOG generation amount and tank pressure value may be time-series data for each navigation section, but are not limited thereto.

[0145] As an example, the processor 110 can predict the BOG generation amount of the ship based on the position information of each navigation section included in the recommended navigation information and the speed information of each navigation section, and predict the tank pressure value of the ship based on the preset liquefied gas consumption.

[0146] As another example, the processor 110 can use a prediction model to obtain the BOG generation amount of the ship and the tank pressure value of the ship.

[0147] However, the method for obtaining the BOG generation amount of a ship and the tank pressure value of the ship is not limited to the above examples.

[0148] In the following, reference will be made to Figure 6 to illustrate an example in which a processor predicts the BOG generation amount of a ship and the tank pressure value of the ship based on recommended navigation information.

[0149] Figure 6 is a flowchart for illustrating an example in which a processor based on a recommended navigation information predicts the BOG generation amount of a ship and the tank pressure value of the ship according to an embodiment.

[0150] Referring to Figure 6 , in step 510, the processor 110 predicts the BOG generation amount of the ship based on the position information of each navigation section, the speed information of each navigation section, and the environmental information of each navigation section.

[0151] As an example, the processor 110 may input the position information of each navigation section, the speed information of each navigation section, and the environmental information of each navigation section into a prediction model as input data to obtain the BOG generation amount of the ship as output data. As another example, the processor 110 may use the BOG generation amount prediction model described below to obtain the BOG generation amount. Among them, the BOG generation amount prediction model includes a plurality of deep learning models, which use the navigation data of the ship to predict the BOG generation amount at different times. In addition, the BOG generation amount prediction model may include a plurality of deep learning models corresponding to each of a plurality of navigation modes according to different liquid gas levels in the tank. However, the method for obtaining the BOG generation amount is not limited to the above examples.

[0152] In step 520, the processor 110 predicts the tank pressure value of the ship based on the position information of each navigation section, the speed information of each navigation section, the environmental information of each navigation section, and a preset liquid gas consumption amount.

[0153] As an example, the processor 110 may input the position information of each navigation section, the speed information of each navigation section, the environmental information of each navigation section, and a preset liquid gas consumption amount into a prediction model as input data to obtain the tank pressure value of the ship as output data. As another example, the processor 110 may use the tank pressure prediction model described below to obtain the tank pressure value. Among them, the tank pressure prediction model outputs the predicted tank pressure value of the ship at different times. In addition, the tank pressure prediction model may include a plurality of deep learning models corresponding to each of a plurality of navigation modes according to different liquid gas levels in the tank. However, the method for obtaining the tank pressure value is not limited to the above examples.

[0154] Referring again to Figure 4 In step 330, the processor 110 obtains the optimal navigation information related to the operation control of the ship based on the BOG generation amount and the storage tank pressure value.

[0155] As an example, the processor 110 can predict the speed of each section of the ship and the usage amount of the equipment provided on the ship based on the minimum liquefied gas consumption during the voyage. And the processor 110 can calculate the fuel amount of the propulsion engine of the ship based on the predicted speed of each section of the ship, and calculate the gas consumption amount of the equipment based on the predicted usage amount of the equipment. And the processor 110 can determine the liquefied gas consumption amount based on the calculated fuel amount of the propulsion engine and the gas consumption amount of the equipment. Finally, the processor can obtain the optimal navigation information including the BOG generation amount of the ship, the storage tank pressure value of the ship, the speed of each navigation section of the ship, the liquefied gas consumption amount of the ship, and the usage amount of the equipment provided on the ship.

[0156] As another example, the processor 110 can use the driving optimization model to be described below to generate the optimal navigation information considering the constraints.

[0157] However, the method for generating the optimal navigation information is not limited to the above examples.

[0158] Hereinafter, reference will be made to Figure 7 to illustrate an example in which the processor obtains the optimal navigation information based on the BOG generation amount and the storage tank pressure value.

[0159] Figure 7 is a flowchart for illustrating an example in which a processor obtains the optimal navigation information based on the BOG generation amount and the storage tank pressure value according to an embodiment.

[0160] Referring to Figure 7 in step 610, the processor 110 generates the nth intermediate navigation information related to the operation control of the ship based on the BOG generation amount and the storage tank pressure value.

[0161] As an example, the processor 110 can predict the speeds of various sections of the ship and the usage amounts of the equipment installed on the ship, so that the liquefied gas consumption during the voyage becomes the minimum liquefied gas consumption. Among them, the equipment can include the main engine, generator engine, gas combustion unit, reliquefaction unit, shaft generator, subcooler, etc. installed on the ship. And, the processor 110 can calculate the fuel amount of the ship's main engine based on the predicted speeds of various sections of the ship, and calculate the gas consumption of the equipment based on the predicted usage amounts of the equipment. And, the processor 110 can determine the liquefied gas consumption based on the calculated fuel amount of the main engine and the gas consumption of the equipment. Finally, the processor can obtain the nth intermediate voyage information including the BOG generation amount of the ship, the tank pressure value of the ship, the speeds of various navigation sections of the ship, the liquefied gas consumption of the ship, and the usage amounts of the equipment installed on the ship.

[0162] As another example, the processor 110 can use the voyage optimization model described below to generate the nth intermediate voyage information considering the constraints.

[0163] However, the method for generating the nth intermediate voyage information is not limited to the above examples.

[0164] In step 620, the processor 110 determines the (n + 1)th intermediate voyage information as the optimal voyage information based on the comparison between the nth intermediate voyage information and the (n + 1)th intermediate voyage information, with a preset threshold as the benchmark.

[0165] As an example, the processor 110 can determine the (n + 1)th weekly voyage information as the optimal voyage information based on the comparison between the speeds of various sections included in the nth intermediate voyage information and the speeds of various sections included in the (n + 1)th intermediate voyage information, with a preset threshold as the benchmark.

[0166] As another example, the processor 110 can determine the (n + 1)th weekly voyage information as the optimal voyage information based on the comparison between the liquefied gas consumption included in the nth intermediate voyage information and the liquefied gas consumption included in the (n + 1)th intermediate voyage information, with a preset threshold as the benchmark.

[0167] However, the method for determining the optimal voyage information is not limited to the above examples.

[0168] Hereinafter, reference will be made to Figure 8 Describe an example in which the processor obtains the optimal voyage information based on the BOG generation amount and the tank pressure value.

[0169] Figure 8It is a flowchart for explaining another example in which a processor according to an embodiment obtains optimal navigation information based on the BOG generation amount and the storage tank pressure value.

[0170] Referring to Figure 8 , in step 710, the processor 110 can calculate the difference based on the nth intermediate navigation information and the (n + 1)th intermediate navigation information, and in response to the difference being below a preset threshold, determine the (n + 1)th intermediate navigation information as the optimal navigation information.

[0171] As an example, the processor 110 can calculate the difference based on the speeds of each section included in the nth intermediate navigation information and the speeds of each section included in the (n + 1)th intermediate navigation information. And the processor 110 can, in response to the calculated difference being 0.01 or less, determine the (n + 1)th intermediate navigation information as the optimal navigation information.

[0172] As another example, the processor 110 can calculate the difference based on the liquefied gas consumption included in the nth intermediate navigation information and the liquefied gas consumption included in the (n + 1)th intermediate navigation information. And the processor 110 can, in response to the calculated difference being 0.01 or less, determine the (n + 1)th intermediate navigation information as the optimal navigation information.

[0173] However, the method for determining the optimal navigation information is not limited to the above examples.

[0174] In step 720, in response to the difference exceeding the preset threshold, the processor 110 updates at least one of the speed information and the liquefied gas consumption of each navigation section included in the (n + 1)th intermediate navigation information to generate the (n + 2)th intermediate navigation information.

[0175] As an example, when the difference between the speeds of each section included in the nth intermediate navigation information and the speeds of each section included in the (n + 1)th intermediate navigation information exceeds 0.01, the processor 110 can update the speeds of each navigation section included in the (n + 1)th intermediate navigation information to generate the (n + 2)th intermediate navigation information. The processor 110 can, based on the speeds of each navigation section included in the (n + 1)th intermediate navigation information, as described above, predict the BOG generation amount of the ship and predict the storage tank pressure value of the ship, and based on the predicted BOG generation amount and the storage tank pressure value, obtain the (n + 2)th intermediate navigation information related to the motion control of the ship. Among them, as the speeds of each navigation section are updated, the gas consumption of the propulsion engine and the gas consumption of the power generation engine at different speeds of the ship will also be updated, so the liquefied gas consumption will also be updated. That is, the (n + 2)th intermediate navigation information can be information generated based on the updated values of the speeds of each section and the liquefied gas consumption.

[0176] As another example, when the difference between the liquefied gas consumption included in the nth intermediate navigation information and the liquefied gas consumption included in the (n + 1)th intermediate navigation information exceeds 0.01, the processor 110 may update the navigation liquefied gas consumption included in the (n + 1)th intermediate navigation information to generate the (n + 2)th intermediate navigation information. The processor 110 may predict the tank pressure value of the ship based on the liquefied gas consumption included in the (n + 1)th intermediate navigation information, and obtain the (n + 2)th intermediate navigation information related to the motion control of the ship based on the predicted BOG generation amount and the tank pressure value. That is, the (n + 2)th intermediate navigation information may be information generated based on the updated value of the liquefied gas consumption.

[0177] The above preset value may be a value set by the user or developer, or a value obtained by the processor 110 through repeatedly generating the nth intermediate navigation information. As an example, the processor 110 may obtain the optimal navigation information, set the correct value corresponding to the optimal navigation information, and obtain the preset value by matching the optimal navigation information and the correct value. As another example, the processor 110 may obtain the optimal navigation information, calculate the error between the optimal navigation information and the correct value using a loss function, and obtain the preset value based on the calculated error.

[0178] Hereinafter, reference will be made to Fig. 9 Another example of a method for optimizing the navigation of a ship will be described.

[0179] Fig. 9 is a flowchart for explaining another example of a method for optimizing the navigation of a ship according to an embodiment.

[0180] Fig. 9 Steps 810 to 830 of Figure 4 correspond to steps 310 to 330 of

[0181] In step 840, the processor 110 may control the ship in a preset driving manner using the optimal navigation information. Among them, the driving manner may include a driving manner that minimizes the liquefied gas consumption of the ship.

[0182] When obtaining the optimal navigation information, the processor 110 can, based on the minimum liquefied gas consumption during a voyage, predict the speed of each section of the ship and the usage amount of the equipment installed on the ship, calculate the fuel amount of the ship's propulsion engine based on the predicted speed of each section of the ship, and calculate the gas consumption amount of the equipment based on the predicted usage amount of the equipment. Moreover, the processor 110 can determine the liquefied gas consumption based on the calculated fuel amount of the propulsion engine and the gas consumption amount of the equipment. Therefore, the BOG generation amount of the ship, the tank pressure value of the ship, the speed of each navigation section of the ship, the liquefied gas consumption of the ship, and the usage amount of the equipment installed on the ship included in the optimal navigation information can be values generated based on the minimum liquefied gas consumption during a voyage. That is, when the processor 110 controls the ship using the optimal navigation information obtained by the above method, it can control the ship in a driving mode that minimizes the liquefied gas consumption of the ship.

[0183] Fig.10 FIG. is an example for explaining a method of predicting BOG generation amount according to an embodiment.

[0184] Refer to Fig.10 , which shows an example of a ship 1010 including at least one storage tank 1020. During the navigation of the ship 1010, BOG (refer to 1030) may be generated in the storage tank 1020.

[0185] As methods for processing BOG, there are methods such as using it as fuel for a main engine or a generator engine, reliquefaction, incineration in a GCU (Gas Combustion Unit), etc. To effectively process BOG by the above methods, it is necessary to predict the BOG generation amount.

[0186] In the past, the BOG generation amount would change at any time according to the meteorological conditions, temperature, sloshing, etc. of the navigation route, so there were limitations in accurately predicting the BOG generation amount.

[0187] According to an embodiment of a method for predicting the BOG generation amount of a ship, input data for a BOG generation amount prediction model is selected from the navigation data of the ship 1010. And the BOG generation amount prediction model is learned through the input data, and the BOG generation amount is predicted through the learned prediction model.

[0188] Therefore, the navigation of a liquefied gas carrier can be achieved according to the BOG generation amount guaranteed in the cargo transportation contract. In addition, during the navigation of the ship, the meteorological conditions change, so the correlation between the BOG generation amount of the ship and the meteorological conditions can be derived.

[0189] In the following, reference will be made to Figure 2 and Figures 11 to 17 to describe in detail a method and an apparatus for predicting the BOG generation amount of a ship according to an embodiment of the present disclosure.

[0190] Referring to Figure 2 , the communication module 140 may receive information on existing navigation data, information on current navigation data, weather information, etc. from an external server or an external device. In addition, various data such as data generated based on existing navigation data, current navigation data, weather information, and the actions of the processor 110 may be stored in the memory 120.

[0191] The processor 110 may control the operation of the apparatus 100 by executing a program stored in the memory 120. As an example, the processor 110 may execute at least a part of the method for predicting the BOG generation amount of a ship described with reference to Figures 11 to 17 .

[0192] In other words, the processor 110 may select input data for the BOG generation amount prediction model from existing navigation data using an input data selection model, learn the BOG generation amount prediction model including a plurality of deep learning models using the input data, and predict the BOG generation amount based on the BOG generation amount prediction model learned using the current navigation data of the ship.

[0193] The processor 110 may select input data for the BOG generation amount prediction model from existing navigation data using an input data selection model.

[0194] For example, the processor 110 may calculate the correlation coefficient between a part of the pre-stored navigation data and the BOG generation amount, learn the input data selection model using the calculated correlation coefficient, and select, as input data, data with a correlation coefficient equal to or greater than a specified value using the learned input data selection model.

[0195] In addition, at least one of the plurality of deep learning models includes a stacking model, and the stacking model may include a plurality of deep learning sub-models.

[0196] The processor 110 may learn the BOG generation amount prediction model including a plurality of deep learning models using the input data. For example, the processor 110 may calculate correct data for learning, perform learning using the input data and the calculated correct data, and verify the BOG generation amount prediction model using another part of the pre-stored navigation data.

[0197] Among them, the correct data may be calculated using at least any one of the gas consumption amount, the gas temperature change value, and the heat insulation material temperature change value.

[0198] The processor 110 can predict the BOG generation amount through a BOG generation amount prediction model that learns using the current navigation data of the ship. For example, the processor 110 can output the initial BOG generation amount prediction values of multiple deep learning models, and apply different weights to the initial BOG generation amount prediction values respectively to calculate the final BOG generation amount prediction value.

[0199] Among them, the processor 110 can apply the highest weight to the initial BOG generation amount prediction value output from the stacked model among the initial BOG generation amount prediction values.

[0200] Hereinafter, with reference to Figures 11 to 17 a method for predicting the BOG generation amount of a ship according to an embodiment of the present disclosure will be described in detail.

[0201] Fig.11 A flowchart for illustrating an example of a method for predicting the BOG generation amount of a ship according to an embodiment.

[0202] With reference to Fig.11 , the method for predicting the BOG generation amount of a ship may include step 1110 to step 1130. However, it is not limited thereto. In addition to Fig.11 the steps shown, the method for predicting the BOG generation amount of a ship may further include other general steps. In addition, as referred to above with reference to Figure 2 and Fig.10 described, Fig.11 at least one of the steps in the flowchart shown can be processed by the processor 110.

[0203] In step 1110, the processor 110 can select the input data of the BOG generation amount prediction model from the existing navigation data by using the input data selection model.

[0204] For example, the processor 110 can calculate the correlation coefficient between the existing navigation data and the BOG generation amount, learn the input data selection model by using the calculated correlation coefficient, and use the learned input data selection model to select the data with a correlation coefficient above a specified value as the input data.

[0205] First, the processor 110 calculates the correlation coefficient. For example, the processor 110 can calculate the linear correlation coefficient between the existing navigation data and the BOG generation amount. And, the processor 110 can use the data with a linear correlation coefficient of 0.1 or more in the existing navigation data as the learning data for the input data selection model. Among them, the linear correlation coefficient can refer to the Pearson correlation coefficient. The Pearson correlation coefficient refers to the covariance of two variables divided by the product of the standard deviations. However, the example of the linear correlation coefficient calculated by the processor 110 is not limited to the above-mentioned Pearson correlation coefficient.

[0206] The processor 110 learns the input data selection model. For example, the processor 110 can use the learned input data selection model to select input data from the existing navigation data.

[0207] Among them, the deep learning model refers to a set of machine learning algorithms that use a hierarchical algorithm structure based on a deep neural network in machine learning technology and cognitive science.

[0208] For example, the deep learning model can be composed of the following layers: an input layer that receives input signals or data from the outside; an output layer that outputs output signals or data corresponding to the input data; and at least one hidden layer that is located between the input layer and the output layer, receives signals from the input layer, extracts features, and passes them to the output layer. The output layer receives signals or data from the hidden layer and outputs them to the outside.

[0209] Therefore, the input data selection model is learned to receive a part of the pre-stored navigation data and extract the data with a linear correlation coefficient of 0.1 or more (such as gas consumption, etc.).

[0210] In addition, the processor 110 selects input data. For example, the processor 110 can select input data including gas consumption, cargo loading amount (such as the liquid gas level in the storage tank), etc. Among them, the gas consumption can be calculated using the gas consumption in the main engine, generator engine, gas combustion unit, and reliquefaction unit. In addition, the processor 110 can select input data including gas consumption, cargo loading amount (such as the liquid gas level in the storage tank), water temperature, air temperature, air pressure, ship speed, wave height, and swell height, etc.

[0211] In the following, reference will be made to Fig.12 to illustrate an example in which the processor 110 calculates the gas consumption.

[0212] Fig.12 is a diagram for illustrating an example of calculating the gas consumption of a ship according to an embodiment.

[0213] Referring to Fig.12 , the processor 110 calculates the gas consumption 1210 by using the gas consumption 1220 of the propulsion engine, the gas consumption 1230 of the power generation engine, the gas consumption 1240 of the gas combustion device, and the gas consumption 1250 of the reliquefaction device. As an example, the difference between the sum of the gas consumption 1220 of the propulsion engine, the gas consumption 1230 of the power generation engine, and the gas consumption 1240 of the gas combustion device and the gas consumption 1250 of the reliquefaction device can be calculated.

[0214] In the past, when using the gas vaporization amount as input data, since there was no information on whether the vaporized gas was used, discharged, reliquefied, etc., it was impossible to accurately predict the BOG generation amount.

[0215] Therefore, by calculating the gas consumption 1210 instead of the gas vaporization amount as input data, the BOG generation amount per unit time can be predicted, and efficient navigation of the ship can be achieved. In addition, it is possible to confirm in real time whether the BOG generation amount benchmark specified in the cargo transportation contract is reached.

[0216] Referring again to Fig.11 , in step 1120, the processor 110 can use the input data to learn a BOG generation amount prediction model including multiple deep learning models.

[0217] For example, at least one of the multiple deep learning models can include a Stacking Model. In addition, the Stacking Model can include deep learning sub-models.

[0218] Among them, the Stacking Model refers to an algorithm that uses the output data of multiple deep learning sub-models as the learning data of a deep learning model.

[0219] In the following, reference will be made to Figure 13a to Figure 13b to illustrate an example of the BOG generation amount prediction model.

[0220] Fig.13a is a configuration diagram showing an example of a Stacking Model according to an embodiment.

[0221] Referring to Fig.13a, the stacked model 1310 may include a first deep learning sub-model 1311 to an nth deep learning sub-model 1312 and an (n + 1)th deep learning sub-model 1313. Here, n is a natural number greater than 3. As an example, the first deep learning sub-model 1311 to the (n + 1)th deep learning sub-model 1313 may be the same deep learning model respectively. In addition, the first deep learning sub-model 1311 to the (n + 1)th deep learning sub-model 1313 may be different deep learning models respectively. As another example, at least one of the first deep learning sub-model 1311 to the nth deep learning sub-model 1312 may include multiple deep learning models.

[0222] For example, the processor 110 uses the same learning data to learn the first deep learning sub-model 1311 to the nth deep learning sub-model 1312. The first predicted value 1314 to the nth predicted value 1315 are output from the learned deep learning sub-models (deep learning sub-model 1311, deep learning sub-model 1312). The output first predicted value 1314 to the nth predicted value 1315 are used as the learning data of the (n + 1)th deep learning sub-model 1313. And, the output data of the (n + 1)th deep learning sub-model 1313 is used as the mth initial output value 1316 of the BOG generation amount prediction model of the ship 1010.

[0223] Fig.13b is a configuration diagram showing an example of a BOG generation amount prediction model of a ship according to an embodiment.

[0224] Refer to Fig.13b , the BOG generation amount prediction model 1320 of the ship 1010 may include a first deep learning model 1321 to an mth deep learning model 1322. Here, m is a natural number greater than 4. For example, at least one of the first deep learning model 1321 to the mth deep learning model 1322 may be the stacked model 1310.

[0225] Since the BOG generation amount prediction model of the ship includes multiple deep learning models, the prediction accuracy of the BOG generation amount of the ship can be improved.

[0226] For example, by using the prediction results of multiple deep learning models, diversity can be ensured. Therefore, by using diverse prediction results, the generalization performance of the BOG generation amount prediction model of the ship including multiple deep learning models can be improved.

[0227] Among them, generalization means the ability of a deep learning model to perform accurate predictions on new data in addition to learning the data. In other words, it means not overfitting or underfitting, but maintaining accuracy for new data. Among them, overfitting means that the deep learning model shows high accuracy only for the learning data, but low accuracy for data other than the learning data. Underfitting means that due to the deep learning model not fully learning the learning data, low accuracy is shown for both the learning data and data other than the learning data.

[0228] In addition, since each prediction result is independent of each other, even if the accuracy of one prediction value is low, the accuracy can be improved by using multiple other prediction values with high accuracy.

[0229] -------------------Content deleted--------------------------

[0230] -------------------Content deleted--------------------------

[0231] For example, the processor 110 can calculate the correct data for learning, and use the input data and the calculated correct data to learn the BOG generation amount prediction model, and use another part of the pre-stored navigation data to verify the BOG generation amount prediction model.

[0232] For example, the processor 110 can calculate the correct data by using at least any one of the gas consumption, the gas temperature change value, and the insulation material temperature change value.

[0233] First, the processor 110 calculates the correct data, and uses the calculated correct data and the input data to learn the BOG generation amount prediction model. For example, the processor 110 can calculate the correct data for supervised learning. The processor 110 can perform supervised learning on the BOG generation amount prediction model using the correct data to improve the accuracy of the model.

[0234] Among them, supervised learning is a machine learning method that learns using training data so that the output data can output values close to the correct data. In addition, the performance of the model that has undergone supervised learning is evaluated using test data.

[0235] In the following, reference will be made to Fig.14 Describe an example in which the processor 110 calculates the correct data.

[0236] Fig.14 This is a diagram for illustrating an example of calculating correct data for learning according to an embodiment.

[0237] Referring to Fig.14 , the processor 110 can calculate correct data by using the gas consumption 1420, the gas temperature change value 1430, and the insulation material temperature change value 1440. As an example, the processor 110 can calculate the difference between the sum of the gas consumption 1420 and the gas temperature change value 1430 and the insulation material temperature change value 1440 as the correct data 1410. As another example, the processor 110 can calculate correct data by using the gas consumption 1420, the gas temperature change value 1430, the insulation material temperature change value 1440, and the liquefied gas consumption.

[0238] Among them, the gas temperature inside the storage tank is affected by the temperature outside the storage tank. Therefore, the gas temperature change value 1430 can be the gas temperature change value 1430 considering the gas temperature inside the storage tank and the temperature outside the storage tank.

[0239] Moreover, the processor 110 can use another part of the pre-stored voyage data to verify the BOG generation prediction model. For example, the pre-stored voyage data can be separated into learning data for the input data selection model and verification data for the BOG generation prediction model of the ship. In addition, the performance of the model can be evaluated by verifying the BOG generation prediction model of the ship, and further learning can be carried out.

[0240] Hereinafter, an example of the processor 110 separating the pre-stored voyage data into learning data and verification data will be described with reference to Figure 15a to Figure 15b .

[0241] Fig.15a This is a diagram for illustrating that the processor 110 removes loss data in the data stored in the memory 120 according to an embodiment.

[0242] Referring to Fig.15a , the processor 110 removes the loss data 1512 in the voyage data 1511 pre-stored in the memory 120. The loss data 1512 refers to the part of the pre-stored voyage data 1511 where data is not stored due to measurement errors. The loss data 1512 may affect the accuracy of the model, so the processor 110 can remove the loss data 1512.

[0243] Fig.15bThis is a diagram for illustrating an example in which a part of the pre-stored navigation data according to an embodiment is separated as learning data for an input data selection model and another part of the data is separated as verification data for a BOG generation amount prediction model of a ship.

[0244] Moreover, the processor 110 separates the pre-stored navigation data 1520 from which the loss data 1512 has been removed into learning data 1521 for the input data selection model and verification data 1522 for the BOG generation amount prediction model of the ship.

[0245] Herein, the purpose of separating the pre-stored navigation data 1520 into learning data 1521 and verification data 1522 is to prevent a state where the model is not sufficiently learned or a state of overfitting of the model. Herein, overfitting means that when the model over-learns the training data, although the accuracy is high when the training data is input, the accuracy of the model becomes very low if other data is input.

[0246] Refer again to Fig.11 , in step 1130, the processor 110 may predict the BOG generation amount according to the BOG generation amount prediction model learned using the current navigation data of the ship.

[0247] First of all, the processor 110 acquires the current navigation data of the ship. For example, the current navigation data of the ship may include the gas consumption of the propulsion engine, the gas consumption of the power generation engine, the gas consumption of the gas combustion device, the gas consumption of the reliquefaction device, the temperature in the storage tank, the pressure in the storage tank, the cargo loading amount (for example, the liquid gas level in the storage tank), the water temperature, the air temperature, the air pressure, the wave height, and the gas consumption of the ship, etc. However, this is only an example, and the current navigation data of the ship is not limited thereto. In addition, the communication module 140 may acquire data on the air temperature, air pressure, wave height, etc. from the meteorological information center.

[0248] Hereinafter, an example in which the processor 110 acquires the current navigation data of the ship will be described with reference to Figures 16a to 16b This is a diagram for illustrating an example of acquiring the current navigation data of the ship from the outside of the ship according to an embodiment.

[0249] Fig.16a This is a diagram for illustrating an example of acquiring the current navigation data of the ship from the outside of the ship according to an embodiment.

[0250] Refer to Fig.16a , the processor 110 may acquire the current navigation data of the ship from the outside 1610 of the ship. As an example, the processor 110 may acquire data such as the water temperature and wave height from the outside 1610 of the ship.

[0251] Fig.16bIt is a diagram for explaining an example of obtaining the current navigation data of a ship from the interior of the ship according to an embodiment.

[0252] Referring to Fig.16b , the processor 110 can obtain the current navigation data of the ship from the interior 1620 of the ship. Specifically, data such as the temperature in the storage tank, the pressure in the storage tank, and the cargo loading amount can be obtained from the storage tank 1621 located in the interior 1620 of the ship. In addition, data such as the gas consumption of the propulsion engine can be obtained from the propulsion engine 1622, data such as the gas consumption of the power generation engine can be obtained from the power generation engine 1623, data such as the gas consumption of the gas combustion device can be obtained from the gas combustion device 1624, and data such as the gas consumption of the reliquefaction device can be obtained from the reliquefaction device 1625. However, this is only an example, and the locations for obtaining the current navigation data of the ship are not limited to this.

[0253] For example, the processor 110 can output the respective initial BOG generation amount prediction values of multiple deep learning models, and apply different weights to the initial BOG generation amount prediction values respectively to calculate the final BOG generation amount prediction value.

[0254] For example, the processor 110 can apply the highest weight to the initial BOG generation amount prediction value output from the stacked model among the initial BOG generation amount prediction values.

[0255] First, the processor 110 can output the respective initial BOG generation amount prediction values of multiple deep learning models. For example, the processor 110 can output the first initial output value to the m-th initial output value as the output values of the first deep learning model to the m-th deep learning model included in the BOG generation amount prediction model of the ship. In addition, the m-th deep learning model can be a stacked model.

[0256] And, the processor 110 can apply different weights to the initial BOG generation amount prediction values respectively to calculate the final BOG generation amount prediction value. In addition, the processor 110 can apply the highest weight to the initial BOG generation amount prediction value output from the stacked model.

[0257] Among them, the weight represents the importance of each data, and weights can be applied to each data to improve the learning accuracy of the model. Therefore, the higher the importance of the data, the higher the applicable weight.

[0258] As an example, the processor 110 may apply the same weights to the initial BOG generation amount prediction values respectively to calculate the final BOG generation amount prediction value. As another example, the processor 110 may apply different weights to the initial BOG generation amount prediction values respectively to calculate the final BOG generation amount prediction value. As yet another example, the processor 110 may apply the highest weight to the initial BOG generation amount prediction value output from the stacked model among the initial BOG generation amount prediction values. The stacked model includes a deep learning sub-model, so its importance is high. Therefore, a relatively high weight may be applied to the initial BOG generation amount prediction model output from the stacked model.

[0259] In the following, reference will be made to Fig.17 to illustrate an example of predicting the BOG generation amount according to the BOG generation amount prediction model of the ship.

[0260] Fig.17 FIG. is a diagram for illustrating an example of applying weights to the initial BOG generation amount prediction value to calculate the final BOG generation amount prediction value according to an embodiment.

[0261] Referring to Fig.17 the processor 110 may output the initial output values of the first deep learning model 1720 to the m-th deep learning model 1730 included in the BOG generation amount prediction model 1710 of the ship. Among them, the m-th deep learning model 1730 may be a stacked model. In addition, the m-th initial output value 1750 may be the initial output value output from the stacked model.

[0262] Among the initial output values of the first deep learning model 1720 to the m-th deep learning model 1730 included in the BOG generation amount prediction model 1710 of the ship, the stacked model, that is, the m-th deep learning model 1730, may have the highest accuracy.

[0263] Weights W11770 to weight W m 1780 may be applied to the first initial output value 1740 to the m-th initial output value 1750. Weights W11770 to weight W m 1780 may be the same value respectively. In addition, weights W11770 to weight W m 1780 may be different values respectively. Among weights W11770 to weight W m 1780, the weight W m 1780 of the m-th initial output value output from the stacked model may be the largest value.

[0264] Therefore, the processor 110 may obtain the final output value 1790 close to the actual BOG generation amount, that is, the BOG generation amount prediction value, from the BOG generation amount prediction model of the ship.

[0265] Fig.18 This is a diagram showing an example of a method for predicting the pressure of a storage tank on a ship according to an embodiment.

[0266] Refer to Fig.18 , an example of a ship 1810 including at least one storage tank 1820 is shown. During the voyage of the ship 1810, BOG may be generated in the storage tank 1820, which may increase the pressure inside the storage tank 1820 (refer to 1830).

[0267] As described above, the generation of BOG increases the volume of liquefied gas loaded in the storage tank 1820, ultimately increasing the pressure inside the storage tank 1820. When the pressure inside the storage tank 1820 increases, the safety of the storage tank 1820 decreases, and there is a possibility of explosion of the storage tank 1820. To prevent such a danger, BOG is discharged, and environmental pollution may be caused during this process.

[0268] In the past, the pressure of the storage tank 1820 changed at any time according to the meteorological conditions, temperature, sloshing, etc. of the voyage path, so it was limited to accurately predict the pressure of the storage tank 1820.

[0269] According to a method for predicting the pressure of a storage tank on a ship according to an embodiment, multiple deep learning models are learned using pre-stored actual voyage data. And, one of multiple navigation modes is selected according to the water level of the liquefied gas in the storage tank, and the pressure of the storage tank 1820 of the ship 1810 is predicted using the deep learning model corresponding to the selected navigation mode.

[0270] Therefore, the real-time pressure inside the storage tank 1820 can be predicted to achieve response to future situations. In addition, according to the means for solving problems of the present invention, the usage amount of equipment required for the voyage of the ship 1810 can be effectively controlled.

[0271] Hereinafter, with reference to Figure 2 and Figures 19 to 24 a method and apparatus for predicting the pressure of a ship storage tank according to an embodiment of the present disclosure will be described in detail.

[0272] Refer to Figure 2 , the communication module 140 can receive information on existing voyage data, current voyage data, recommended navigation information, weather information, etc. from an external server or an external device. In addition, various data such as data generated according to existing voyage data, current voyage data, recommended navigation information, weather information, and the actions of the processor 110 can be stored in the memory 120.

[0273] The processor 110 can control the operation of the device 100 by executing a program stored in the memory 120. As an example, the processor 110 can execute with reference to Figures 19 to 24 At least a part of the method for predicting the storage tank pressure of a ship described.

[0274] In other words, the processor 110 can learn deep learning models corresponding to multiple navigation modes of the ship's navigation using pre-stored actual navigation data, select one of the multiple navigation modes according to the level of liquefied gas in the storage tank, and use the deep learning model corresponding to the selected navigation mode to predict the pressure of the storage tank from the recommended navigation information.

[0275] First, the processor 110 can learn deep learning models corresponding to multiple navigation modes of the ship's navigation using pre-stored actual navigation data.

[0276] For example, the processor 110 can obtain correct data for learning, learn deep learning models corresponding to multiple navigation modes using a part of the pre-stored actual navigation data and the correct data, and verify the learned deep learning models using another part of the pre-stored actual navigation data.

[0277] Among them, the learning can be performed using the error between the correct data and the output data of the deep learning model and the backpropagation algorithm.

[0278] In addition, the processor 110 can select one of the multiple navigation modes according to the level of liquefied gas in the storage tank.

[0279] For example, the processor 110 measures the level of liquefied gas in the storage tank, selects the first mode among the multiple navigation modes when the level is above a specified height, and selects the second mode among the multiple navigation modes when the level is below the specified height.

[0280] The processor 110 can predict the pressure of the storage tank from the recommended navigation information using the deep learning model corresponding to the selected navigation mode.

[0281] For example, the processor 110 can obtain the recommended navigation information of the ship, use the recommended navigation information as input data to obtain multiple intermediate values, and apply weights to the multiple intermediate values to obtain a predicted value of the storage tank pressure.

[0282] Fig.19 Is a flowchart for illustrating an example of the method for predicting the storage tank pressure of a ship according to an embodiment.

[0283] Refer to Fig.19 , the method for predicting the storage tank pressure of a ship may include steps 1910 to 1930. However, it is not limited thereto. In addition to Fig.19In addition to the steps shown, the method for predicting the storage tank pressure of a ship may also include other general steps. Further, as referred to above with reference to Figure 2 and Fig.18 described, Fig.19 at least one of the steps in the flowchart shown can be processed by the processor 110.

[0284] In step 1910, the processor 110 may utilize pre-stored actual navigation data to learn deep learning models respectively corresponding to multiple navigation modes of the ship's navigation.

[0285] For example, the processor 110 may obtain correct data for learning, and utilize a part of the pre-stored actual navigation data and the correct data to learn deep learning models respectively corresponding to multiple navigation modes, and utilize another part of the pre-stored actual navigation data to verify the learned deep learning models.

[0286] Among them, the correct data is the data required for supervised learning of the deep learning model, and refers to the object that the deep learning model is to predict. The correct data is used to measure the performance of the deep learning model during the learning process of the deep learning model and evaluate the prediction results of the deep learning model.

[0287] In addition, supervised learning is one of the machine learning methods, and its goal is to learn the relationship between the input data and the correct data, and predict the result of the new input data when new input data is input.

[0288] First, the processor 110 obtains the correct data for learning.

[0289] For example, the processor 110 may obtain the actual storage tank pressure value under navigation conditions similar to the current navigation from the pre-stored actual navigation data as the correct data. In addition, the navigation conditions may include weather information, navigation speed in each section, total average speed, and the amount of liquefied gas in the storage tank 1820 when entering / leaving the port, etc.

[0290] For example, the pre-stored actual navigation data may include the latitude, longitude, liquefied gas discharge amount, speed, wave height, wave period, wave direction, swell height, swell period, swell direction, wind speed, air temperature, air pressure, and water temperature of the ship 1810.

[0291] As an example, the actual storage tank pressure value may be the storage tank pressure value in each navigation section. As another example, the actual storage tank pressure value may be the average storage tank pressure value during navigation.

[0292] For example, the processor 110 uses a part of the pre-stored actual navigation data and correct data to learn deep learning models corresponding to multiple navigation modes respectively.

[0293] Therefore, deep learning models corresponding to multiple navigation modes can be learned to predict the pressure of the storage tank 1820 from the recommended navigation information.

[0294] For example, the processor 110 can separate the pre-stored actual navigation data and use it as learning data and verification data.

[0295] In the following, reference will be made to Fig.20a to illustrate an example in which the processor 110 separates a part of the pre-stored actual navigation data into learning data and another part into verification data.

[0296] Fig.20a FIG. is a diagram for illustrating an example in which a part of the pre-stored actual navigation data according to an embodiment is separated into learning data and another part into verification data.

[0297] Referring to Fig.20a , the processor 110 separates the pre-stored actual navigation data 2011 into a part 2012 of the pre-stored actual navigation data and another part 2013 of the pre-stored actual navigation data. The separated part 2012 of the pre-stored actual navigation data is used as learning data for the deep learning model, and the other part 2013 is used as verification data for the deep learning model.

[0298] In the following, reference will be made to Fig.20b to detail an example of the process by which the processor 110 processes the pre-stored actual navigation data 2011.

[0299] Fig.20b FIG. is a diagram for illustrating an example of the process of processing the pre-stored actual navigation data according to an embodiment.

[0300] Referring to Fig.20b , the processor 110 filters the noise of the pre-stored actual navigation data 2021 using a noise filter. Among them, the noise filter may refer to a Savitzky-Golay filter. However, the example of the noise filter used by the processor 110 is not limited to the above Savitzky-Golay filter.

[0301] The processor 110 normalizes the data with filtered noise (refer to 2023). Among them, data normalization (Normalization) (refer to 2023) is a preprocessing process that adjusts the scale of the input data when learning a deep learning model to improve the learning speed and the performance of the deep learning model.

[0302] As an example, data normalization (refer to 2023) can utilize the Min - Max normalization technique. The Min - Max normalization technique is a technique that converts the values of the input data into a range between 0 and 1. As another example, data normalization (refer to 2023) can utilize the Standardization technique. The Standardization technique is a technique that converts the input data into a distribution with a mean of 0 and a variance of 1. However, the examples of the normalization techniques utilized by the processor 110 are not limited to the above - mentioned Min - Max normalization technique or Standardization technique.

[0303] The processor 110 divides the normalized data of 2023 according to voyages. Among them, a voyage refers to the number of times of navigation.

[0304] In addition, the processor 110 converts the divided data of different voyages in 2024 into the format of a tensor 2025. Among them, a tensor 2025 is a mathematical concept representing a multi - dimensional array. A vector represents a one - dimensional array, a matrix represents a two - dimensional array, and a tensor 2025 represents an array with three or more dimensions. Therefore, a deep learning model can utilize the tensor 2025 to represent the input data and the parameters of the deep learning model.

[0305] The processor 110 can form a batch 2026 from ten tensors 2025. Among them, a batch 2026 refers to a set of input data that can process the input data of a deep learning model at one time. Usually, a batch 2026 includes multiple input data, and each input data has the same size. By using a batch 2026, the generalization performance of the deep learning model can be improved and efficient computation can be achieved. Therefore, the processor 110 can improve the learning efficiency when repeatedly learning the deep learning model by forming a batch 2026.

[0306] The processor 110 can improve the learning efficiency of the deep learning model and the prediction accuracy of the deep learning model by utilizing the processed actual navigation data 2027.

[0307] In addition, the processor 110 can use the error between the correct data and the output data of the deep learning model and the backpropagation algorithm to learn the deep learning model.

[0308] Among them, the backpropagation algorithm is an algorithm used in the field of supervised learning to enable the deep learning model to learn. The backpropagation algorithm can calculate the error between the output data and the correct data, and use the calculated error to calculate the weights and biases. And, the calculated weights and biases are updated to minimize the error between the output data and the correct data.

[0309] Hereinafter, with reference to Fig.21 , an example of the processor 110 learning the deep learning model using the backpropagation algorithm will be described.

[0310] Fig.21 is a diagram for explaining an example of the process of learning a deep learning model for predicting the pressure of a ship storage tank according to an embodiment.

[0311] With reference to Fig.21 , the processor 110 obtains the output data 2120 and the correct data 2130 of the deep learning model 2110. And, the processor 110 calculates the error 2140 between the output data 2120 and the correct data 2130 by using a loss function. The processor 110 calculates the weights and biases of the error 2140, and repeatedly uses the process of modifying the weights by the backpropagation algorithm 2150 to learn the deep learning model 2110.

[0312] In order to prevent the problem of weight loss during the process of using the backpropagation algorithm 2150, the processor 110 initializes the weights using the Xavier Initialization method. Among them, Xavier Initialization is one of the methods for initializing weights, and uses the normal distribution to initialize the weights. However, the example of the method for initializing the weights used by the processor 110 is not limited to the above Xavier Initialization method.

[0313] In addition, when using the backpropagation algorithm 2150, the processor 110 uses the Root Mean Square Propagation (RMSprop) technique to find the optimal weight value. Among them, RMSprop is an algorithm that helps the deep learning model to learn quickly and stably, and can provide the optimal weights for each parameter for effective learning. However, the example of the method for finding the optimal weight value used by the processor 110 is not limited to the above RMSprop technique.

[0314] The processor 110 may verify the learned deep learning model by using another part 2013 of the pre-stored actual navigation data 2011.

[0315] Among them, verification is a process described below, which evaluates the performance of the deep learning model and confirms whether the deep learning model has achieved generalization. In other words, it is a process for preventing overfitting or underfitting.

[0316] The steps for the above-mentioned processor 110 to learn the deep learning model can be similarly applied to the deep learning models corresponding to multiple navigation modes of the navigation of the ship 1810.

[0317] Refer again to Fig.19 In step 1920, the processor 110 may select one of multiple navigation modes according to the water level of the liquefied gas in the storage tank.

[0318] For example, the processor 110 may measure the water level of the liquefied gas in the storage tank. When the water level is above a specified height, it selects the first mode among the multiple navigation modes. When the water level is below the specified height, it selects the second mode among the multiple navigation modes.

[0319] Hereinafter, an example in which the processor 110 selects the first mode or the second mode among multiple navigation modes according to the water level of the liquefied gas will be described with reference to Figure 22 to Figure 23 FIG.

[0320] Fig. 22 FIG. is an example for explaining an example of determining a navigation mode according to whether the water level of the liquefied gas in the storage tank is above a specified height according to an embodiment.

[0321] Refer to Fig. 22 FIG., the processor 110 measures the water level of the liquefied gas in the storage tank 2140 and determines whether it is a case 2220 where the water level of the liquefied gas is above the specified height or a case 2120 where the water level of the liquefied gas is below the specified height. For example, the specified height may be half of the height of the storage tank 2140. Therefore, when the water level of the liquefied gas is above half of the height of the storage tank 2140 (refer to 2220), the processor 110 may determine it as a laden voyage. When the water level of the liquefied gas is below half of the height of the storage tank 2140 (refer to 2120), it may be determined as a ballast voyage.

[0322] Fig.23 FIG. is an example for explaining an example of the deep learning model corresponding to multiple navigation modes according to different water levels of the liquefied gas in the storage tank according to an embodiment.

[0323] Reference Fig.23 , when the water level of the liquefied gas is above half of the height of the storage tank (refer to 2310), the processor 110 selects the first mode 2330, and when the water level of the liquefied gas is below half of the height of the storage tank (refer to 2320), it selects the second mode 2340. For example, the first mode 2330 can be a full-load navigation mode, and the second mode 2340 can be a ballast navigation mode. In addition, the deep learning model 2350 of the first mode 2330 can use the Long Short-Term Memory (LSTM) algorithm, and the deep learning model 2360 of the second mode 2340 can use the Gate Recurrent Unit (GRU) algorithm. However, the algorithms used by the deep learning models 2350 and 2360 are not limited to the above-mentioned LSTM algorithm and GRU algorithm.

[0324] Refer again to Fig.19 , in step 1930, the processor 110 can use the deep learning model corresponding to the selected navigation mode to predict the pressure of the storage tank according to the recommended navigation information.

[0325] For example, the processor 110 can obtain the recommended navigation information of the ship, and use the recommended navigation information as input data to obtain multiple intermediate values, and apply weights to the multiple intermediate values to obtain the pressure prediction value of the storage tank.

[0326] First, the processor 110 obtains the recommended navigation information of the ship. The processor 110 can obtain the recommended navigation information by the method as referred to above Figures 4 to 5 described.

[0327] The processor 110 can use the recommended navigation information as input data to obtain multiple intermediate values, and can apply weights to the multiple intermediate values to obtain the pressure prediction value of the storage tank.

[0328] Hereinafter, an example of the processor 110 applying weights to multiple intermediate values to obtain the pressure prediction value of the storage tank will be described with reference to Fig.24 .

[0329] Fig.24 FIG. is an example diagram for explaining applying weights to multiple intermediate values to obtain the pressure prediction value of the storage tank according to an embodiment.

[0330] Refer to Fig.24, the processor 110 can use the recommended navigation information 2410 as the input data of the deep learning model 2420 to obtain an intermediate value 2430. As an example, in the first mode, i.e., the fully loaded navigation mode, the deep learning model 2420 can use the LSTM algorithm. As another example, in the second mode, i.e., the ballast navigation mode, the deep learning model 2420 can use the GRU algorithm. However, the algorithms used by the deep learning model 2420 are not limited to the above-mentioned LSTM algorithm and GRU algorithm.

[0331] In addition, the processor 110 can obtain the pressure prediction value 2450 of the storage tank by applying a weight 2440 to the intermediate value 2430. For example, the processor 110 can use a linear layer to apply the weight 2440 to the intermediate value 2430 to obtain the pressure prediction value 2450 of the storage tank. However, the method by which the processor 110 applies the weight 2440 to the intermediate value 2430 is not limited to the method of using a linear layer.

[0332] Therefore, the processor 110 can use different deep learning models according to the level of liquefied gas in the storage tank 1820 of the ship 1810 to predict the storage tank pressure value of the ship 1810. That is, the processor 110 can use different deep learning models for each navigation mode to predict the storage tank pressure of the ship, thereby improving the accuracy of predicting the storage tank pressure of the ship.

[0333] Fig.25 is a diagram showing an example for explaining a method of optimizing the navigation of a ship according to an embodiment.

[0334] Referring to Fig.25 , the navigation optimization model 2520 can use the BOG generation amount and the storage tank pressure value 2510 to obtain the optimal navigation information 2530 considering the constraints 2540 of the ship. Among them, the navigation optimization model 2520 is a model used to implement the method of optimizing the navigation of a ship according to an embodiment, and can be a model used to implement the method of optimizing the navigation of a ship described above with reference to Figures 1 to 9 the method of optimizing the navigation of a ship described above. Therefore, the differences between the model for implementing the method of optimizing the navigation of a ship described above with reference to Figures 1 to 9 will be mainly described below.

[0335] According to an embodiment of the method of optimizing the navigation of a ship, the recommended navigation information of the ship is used to predict the BOG generation amount of the ship and the storage tank pressure of the ship. And, the optimal navigation information for each navigation section that satisfies the constraints of the ship is obtained by using the predicted BOG generation amount and storage tank pressure value, and the operation of the ship is controlled by using the obtained optimal navigation information for each navigation section. The specific content of the constraints will be described below.

[0336] Therefore, when implementing a method for optimizing the navigation of a ship according to an embodiment, economic navigation that minimizes the gas consumption of the ship can be achieved by utilizing the optimal navigation information for each navigation section.

[0337] Hereinafter, reference will be made to Figure 2 and Figure 26 to Figure 28b to describe in detail a method and an apparatus for optimizing the navigation of a ship according to an embodiment of the present disclosure. Herein, the apparatus may refer to the user terminal 100.

[0338] Referring to Figure 2 , the communication module 140 may receive information on existing navigation data, information on current navigation data, recommended navigation information, a navigation plan, weather information, etc. from an external server or an external device. In addition, various data such as data generated based on existing navigation data, current navigation data, recommended navigation information, a navigation plan, weather information, and the actions of the processor 110 may be stored in the memory 120.

[0339] The processor 110 may control the actions of the apparatus 100 by executing a program stored in the memory 120. As an example, the processor 110 may execute at least a part of the method for optimizing the navigation of a ship described with reference to Figure 26 to Figure 28b .

[0340] In other words, the processor 110 may utilize the BOG generation amount of the ship and the tank pressure value of the ship to obtain the optimal navigation information for each navigation section, update the optimal navigation information in consideration of the constraints of the ship, and control the actions of the ship by using the updated optimal navigation information.

[0341] The processor 110 may utilize the BOG generation amount of the ship and the tank pressure value of the ship to obtain the optimal navigation information for each navigation section. In addition, the processor 110 may update the optimal navigation information in consideration of the constraints of the ship. Herein, the constraints may be set based on at least one of the relationships among mass, energy, electric power amount, maximum / minimum liquefied gas consumption of equipment, efficiency of equipment, efficiency of a main engine, efficiency of a generator engine, efficiency of a shaft generator, pressure of a tank, the maximum / minimum speed of the ship, and the average speed of the ship.

[0342] For example, the processor 110 may obtain the optimal navigation information in different ways according to whether the navigation of the ship utilizes the speeds of each navigation section included in the recommended navigation information.

[0343] As an example, when using the speeds of each navigation section included in the recommended navigation information during the navigation of a ship, the processor 110 may use the BOG generation amount, the tank pressure value, and the recommended navigation information to obtain the optimal navigation information, and the recommended navigation information may include preset weather information.

[0344] In addition, the processor 110 may calculate the difference between the gas consumption included in the (n + 1)-th intermediate navigation information and the gas consumption included in the n-th intermediate navigation information, determine whether the difference is included within a preset range, and based on the determination result, determine the (n + 1)-th intermediate navigation information as the optimal navigation information. Here, n is a natural number greater than or equal to 1, and the (n + 1)-th intermediate navigation information may be generated based on updated values of at least one parameter included in the n-th intermediate navigation information.

[0345] As another example, when not using the speeds of each navigation section included in the recommended navigation information during the navigation of a ship, the processor 110 may use the BOG generation amount, the tank pressure value, and the recommended navigation information to obtain the optimal navigation information, and the recommended navigation information may include weather information updated according to the navigation of the ship.

[0346] In addition, the processor 110 may calculate the difference between the gas consumption included in the (n + 1)-th intermediate navigation information and the gas consumption included in the n-th intermediate navigation information, determine whether the difference is included within a preset range, and based on the determination result, determine the (n + 1)-th intermediate navigation information as the optimal navigation information. Here, n is a natural number greater than or equal to 1, and the (n + 1)-th intermediate navigation information may be generated based on updated values of at least one parameter included in the n-th intermediate navigation information.

[0347] In addition, the processor 110 may use the updated optimal navigation information to control the operation of the ship. For example, the processor 110 may control the ship in a driving mode set using the optimal navigation information, and the driving mode may include a driving mode that minimizes the gas consumption of the ship.

[0348] Fig.26 is a flowchart showing an example for explaining a method of optimizing the navigation of a ship according to an embodiment.

[0349] Referring to Fig.26 , the method of optimizing the navigation of a ship may include steps 2610 to 2630. However, it is not limited thereto, and in addition to the steps shown in Fig.26 , the method of optimizing the navigation of a ship may further include other general steps. In addition, as referred to above in Figure 2 and Fig.25 described, Fig.26 at least one of the steps in the flowchart shown in

[0350] In step 2610, the processor 110 may utilize the BOG generation amount of the ship and the tank pressure value of the ship to obtain the optimal navigation information for each navigation section.

[0351] First, the processor 110 may predict the BOG generation amount of the ship. As an example, the processor 110 may predict the BOG generation amount of the ship by the method described above with reference to Figure 6 As another example, the processor 110 may utilize the method and device for predicting the BOG generation amount of the ship as described above with reference to Figure 2 and Figures 10 to 17 to predict the BOG generation amount of the ship. However, the method for predicting the BOG generation amount of the ship is not limited to the above methods.

[0352] In addition, the processor 110 may predict the tank pressure of the ship. As an example, the tank pressure of the ship may be predicted by the method described above with reference to Figure 6 As another example, the tank pressure of the ship may be predicted by utilizing the method and device for predicting the tank pressure of the ship as described above with reference to Figure 2 and Figures 18 to 24 to predict the tank pressure of the ship. However, the method for predicting the tank pressure of the ship is not limited to the above methods.

[0353] The processor 110 may utilize the BOG generation amount of the ship and the tank pressure value of the ship to obtain the optimal navigation information for each navigation section. For example, the processor 110 may obtain the optimal navigation information in different ways according to whether the ship's navigation utilizes the speeds of each navigation section included in the recommended navigation information.

[0354] Among them, the recommended navigation information may be the recommended navigation information for the navigator to effectively navigate the ship from the departure place to the arrival place, and the processor 110 may generate the recommended navigation information by the method described above with reference to Figures 4 to 5 The recommended navigation information not only includes the recommended navigation information as described above with reference to Figures 4 to 5 but may further include the speeds of each navigation section, the total average speed of the ship, the latitude / longitude of the ship according to different times, and the weather information according to different times. However, the method for generating the recommended navigation information is not limited to the above methods, and the recommended navigation information is not limited to the above recommended navigation information.

[0355] Hereinafter, with reference to Fig. 27 an example of different ways distinguished according to whether the processor 110 utilizes the speeds of each navigation section included in the recommended navigation information during the ship's navigation will be described.

[0356] Fig. 27This is a diagram for explaining an example of obtaining optimal navigation information in different ways according to the speed of each navigation section included in the recommended navigation information during the navigation of a ship.

[0357] Referring to Fig. 27 , the processor 110 can obtain optimal navigation information in different ways according to whether the speed of each navigation section included in the recommended navigation information is utilized during the navigation of the ship (step 2710).

[0358] As an example, when the processor 110 utilizes the speed of each navigation section included in the recommended navigation information during the navigation of the ship (step 2720), it navigates according to the speed of each navigation section included in the recommended navigation information. Among them, regarding the speed of each navigation section included in the recommended navigation information, the speeds of all navigation sections are the same. In addition, regarding the speed of each navigation section included in the recommended navigation information, the speeds of all navigation sections are different. In addition, regarding the speed of each navigation section included in the recommended navigation information, only the speeds of some navigation sections are the same.

[0359] As another example, when the processor 110 does not utilize the speed of each navigation section included in the recommended navigation information during the navigation of the ship (step 2730), it navigates according to the speed of each navigation section included in the optimal navigation information. Among them, regarding the speed of each navigation section included in the optimal navigation information, the speeds of all navigation sections are the same. In addition, regarding the speed of each navigation section included in the optimal navigation information, the speeds of all navigation sections are different. In addition, regarding the speed of each navigation section included in the optimal navigation information, only the speeds of some navigation sections are the same. However, even when the processor 110 does not utilize the speed of each navigation section included in the recommended navigation information (step 2730), the total average speed included in the recommended navigation information can be utilized.

[0360] Hereinafter, the process of the processor 110 obtaining the optimal navigation information will be described in detail by dividing it into cases where the speed of each navigation section included in the recommended navigation information is utilized and not utilized during the navigation of the ship.

[0361] For example, when the speed of each navigation section included in the recommended navigation information is utilized during the navigation of the ship, the processor 110 can utilize the BOG generation amount, the tank pressure value, and the recommended navigation information to obtain the optimal navigation information, and the recommended navigation information may include preset weather information.

[0362] In addition, the processor 110 may calculate the difference between the gas consumption included in the (n + 1)-th intermediate navigation information and the gas consumption included in the n-th intermediate navigation information, determine whether the difference is included within a preset range, and determine the (n + 1)-th intermediate navigation information as the optimal navigation information based on the determination result. Among them, the (n + 2)-th intermediate navigation information may be generated based on updated values of at least one parameter included in the (n + 1)-th intermediate navigation information. Here, n is a natural number of 1 or more.

[0363] Hereinafter, with reference to Fig.28a an example in which the processor 110 obtains the optimal navigation information when using the speeds of the respective navigation sections included in the recommended navigation information during the navigation of the ship will be described.

[0364] Fig.28a is a flowchart for explaining an example in which the optimal navigation information is obtained when using the speeds of the respective navigation sections included in the recommended navigation information during the navigation of the ship according to an embodiment.

[0365] With reference to Fig.28a when using the speeds of the respective navigation sections included in the recommended navigation information during the navigation of the ship (refer to 2810), the processor 110 may use the recommended navigation information, the predicted value of the BOG generation amount of the ship, and the predicted value of the tank pressure of the ship to obtain the optimal navigation information.

[0366] First, in step 2811, the processor 110 obtains the recommended navigation information.

[0367] Among them, the recommended navigation information may include the above-mentioned recommended navigation information as it is. In step 2812, the processor 110 may predict the BOG generation amount of the ship and the tank pressure of the ship by the above method. Among them, the BOG generation amount may change according to meteorological conditions such as wind speed, wave height, and swell height. Therefore, the predicted value of the BOG generation amount and the predicted value of the tank pressure may also change according to meteorological conditions.

[0368] In step 2813, the processor 110 may obtain intermediate navigation information by using the recommended navigation information, the predicted BOG generation amount of the ship, and the predicted tank pressure of the ship. Among them, the intermediate navigation information may include the optimal speed of the ship in each navigation section, the gas consumption of the ship, and the usage amount of the equipment provided on the ship. Among them, the equipment may include a subcooler, a shaft generator, a main engine, a generator engine, a gas combustion unit, and a reliquefaction device provided on the ship, etc. In addition, the gas consumption can be calculated by using the gas consumption of the main engine, the gas consumption of the generator engine, the gas consumption of the gas combustion unit, and the gas consumption of the reliquefaction device.

[0369] In step 2814, the processor 110 calculates the difference between the gas consumption included in the (n + 1)-th intermediate navigation information and the gas consumption included in the n-th intermediate navigation information. In addition, the processor 110 may determine whether the difference between the (n + 1)-th gas consumption and the n-th gas consumption is included in a preset range. Among them, the preset range may be from 0 to less than 0.01.

[0370] When the difference between the (n + 1)-th gas consumption and the n-th gas consumption is not included in the preset range, the processor 110 executes again from step 2812.

[0371] In step 2815, since the processor 110 does not use the optimal speed of the ship included in the (n + 1)-th intermediate navigation information, the weather information included in the recommended navigation information does not change. Therefore, when the processor 110 obtains the (n + 2)-th intermediate navigation information, it uses the preset weather information included in the recommended navigation information.

[0372] When the processor 110 executes step 2812 again, the (n + 2)-th intermediate navigation information may be generated based on the updated value of at least one parameter included in the (n + 1)-th intermediate navigation information. For example, the at least one parameter may be gas consumption.

[0373] For example, when the processor 110 executes step 2812 again, the (n + 1)-th gas consumption may be used to replace the n-th gas consumption to change the predicted BOG generation amount of the ship. In addition, the intermediate navigation information may change with the change of the predicted BOG generation amount of the ship.

[0374] In step 2816, when the difference between the gas consumption at the (n + 1)-th time and the gas consumption at the n-th time is included within a preset range, the processor 110 may determine the (n + 1)-th intermediate navigation information as the optimal navigation information. The optimal navigation information may include a predicted value of the BOG generation amount of the ship, a predicted value of the tank pressure of the ship, the gas consumption of the ship included in the (n + 1)-th intermediate navigation information, the optimal speed of the ship, and the usage amount of the equipment provided on the ship.

[0375] For example, when the speeds of the respective navigation sections included in the recommended navigation information are not used during the navigation of the ship, the processor 110 may use the BOG generation amount, the tank pressure value, and the recommended navigation information to obtain the optimal navigation information, and the recommended navigation information may include weather information updated according to the navigation of the ship.

[0376] In addition, the processor 110 may calculate the difference between the gas consumption included in the (n + 1)-th intermediate navigation information and the gas consumption included in the n-th intermediate navigation information, determine whether the difference is included within the preset range, and determine the (n + 1)-th intermediate navigation information as the optimal navigation information based on the determination result. The (n + 2)-th intermediate navigation information may be generated based on updated values of at least one parameter included in the (n + 1)-th intermediate navigation information. Here, n is a natural number of 1 or more.

[0377] Hereinafter, with reference to Fig.28b , an example of the processor 110 obtaining the optimal navigation information when the speeds of the respective navigation sections included in the recommended navigation information are not used during the navigation of the ship will be described.

[0378] Fig.28b is a flowchart for explaining an example of obtaining the optimal navigation information when the speeds of the respective navigation sections included in the recommended navigation information are not used during the navigation of the ship according to an embodiment.

[0379] With reference to Fig.28b , when the speeds of the respective navigation sections included in the recommended navigation information are not used during the navigation of the ship (refer to 2820), the processor 110 may use the recommended navigation information, the predicted value of the BOG generation amount of the ship, and the predicted value of the tank pressure of the ship to obtain the optimal navigation information.

[0380] First, in step 2821, the processor 110 obtains the recommended navigation information.

[0381] Among them, the recommended navigation information can include the above-mentioned recommended navigation information without modification, and can also include weather information updated according to the navigation of the ship. In step 2822, the processor 110 can predict the BOG generation amount of the ship and the tank pressure of the ship through the above method. Among them, the BOG generation amount may change according to meteorological conditions such as wind speed, wave height, and swell height. Therefore, the predicted value of the BOG generation amount and the predicted value of the tank pressure may also change according to meteorological conditions.

[0382] In step 2823, the processor 110 can obtain intermediate navigation information by using the recommended navigation information, the predicted value of the BOG generation amount of the ship, and the predicted value of the tank pressure of the ship. Among them, the intermediate navigation information can include the optimal speed of the ship in each navigation section, the gas consumption of the ship, and the usage amount of the equipment installed on the ship. The equipment can include a subcooler, an engine shaft generator, a power generation engine, a propulsion engine, a gas combustion device, a re-liquefaction device, etc. installed on the ship.

[0383] In step 2824, the processor 110 calculates the difference between the gas consumption included in the (n + 1)-th intermediate navigation information and the gas consumption included in the n-th intermediate navigation information. In addition, the processor 110 can determine whether the difference between the (n + 1)-th gas consumption and the n-th gas consumption is included in a preset range. The preset range can be from 0 to less than 0.01.

[0384] When the difference between the (n + 1)-th gas consumption and the n-th gas consumption is not included in the preset range, the processor 110 executes again from step 3021.

[0385] When the processor 110 executes step 2821 again, the (n + 2)-th intermediate navigation information can be generated based on the updated value of at least one parameter included in the (n + 1)-th intermediate navigation information. As an example, at least one parameter can be the gas consumption. As another example, at least one parameter can be the optimal speed in each navigation section.

[0386] In step 2825, the processor 110 uses the optimal speed of the ship in each navigation section included in the (n + 1)-th intermediate navigation information. Therefore, the optimal speed of the ship included in the (n + 1)-th intermediate navigation information and the speed of the ship in each navigation section included in the recommended navigation information may be different. When the speed of the ship changes, the latitude and longitude of the ship at different times may change. Therefore, the weather information may also be different from the weather information included in the recommended navigation information. In addition, when the weather information changes, the BOG generation amount of the ship and the tank pressure of the ship may be changed.

[0387] For example, in step 2825, the processor 110 updates the weather information using the optimal speed of the ship included in the (n + 1)-th intermediate navigation information. In addition, when the processor 110 executes step 2822 again, the updated weather information is used.

[0388] For example, when the processor 110 executes step 2822 again, the (n + 1)-th gas consumption can be used to replace the n-th gas consumption to change the predicted value of the BOG generation amount of the ship. Therefore, the intermediate navigation information may change with the change of the predicted value of the BOG generation amount of the ship. In addition, when the processor 110 executes step 2822 again, the updated weather information can be used to replace the weather information included in the recommended navigation information, so as to change the tank pressure value of the ship, and the intermediate navigation information may change with the change of the tank pressure value of the ship.

[0389] In step 2826, when the difference between the (n + 1)-th gas consumption and the n-th gas consumption is included in a preset range, the processor 110 may determine the (n + 1)-th intermediate navigation information as the optimal navigation information. The optimal navigation information may include the predicted value of the BOG generation amount of the ship, the predicted value of the tank pressure of the ship, the gas consumption of the ship included in the (n + 1)-th intermediate navigation information, the optimal speed of the ship, and the usage amount of the equipment provided on the ship.

[0390] Refer again to Fig.26 , in step 2620, the processor 110 may update the optimal navigation information considering the constraints of the ship. The constraints may be set based on at least one of the relationship between mass, energy, electric power, the maximum / minimum liquefied gas consumption of the equipment, the efficiency of the equipment, the efficiency of the main engine, the efficiency of the generator engine, the efficiency of the shaft generator, the pressure of the tank, the maximum / minimum speed of the ship, and the average speed of the ship.

[0391] In other words, the constraints may include mass conditions, energy conditions, electric power conditions, maximum / minimum liquefied gas consumption conditions of the equipment, efficiency conditions of the equipment, efficiency conditions of the main engine, efficiency conditions of the generator engine, efficiency conditions of the shaft generator, tank pressure conditions, maximum / minimum speed conditions of the ship, and average speed conditions of the ship, etc. Hereinafter, each constraint will be described in detail.

[0392] For example, the quality condition can be set based on the quality of the BOG consumed by the equipment installed on the ship. Among them, the quality of the BOG consumed can be calculated by considering the relationship between the quality of the BOG used in the main engine and the generator engine, the quality of the BOG discharged from the gas combustion unit, and the quality of the BOG reliquefied in the reliquefaction unit.

[0393] For example, the energy condition can be set based on the difference in the change in the tank pressure in each navigation section of the ship. Among them, the difference in the change in the tank pressure in each navigation section of the ship can be calculated by considering the relationship between the BOG generation amount in each navigation section, the amount of BOG returned to the tank, the amount of liquefied gas returned to the tank, and the BOG consumption amount of the equipment installed on the ship.

[0394] For example, the power condition can be set based on the power of the equipment installed on the ship. Among them, the power of the equipment installed on the ship can be calculated by considering the relationship between the usage amounts of the compressor, gas combustion unit, reliquefaction unit, subcooler, and fuel gas pump.

[0395] For example, the maximum / minimum liquefied gas consumption condition of the equipment can be set based on the turndown ratio. When the required liquefied gas consumption of each equipment is greater than the minimum liquefied gas consumption condition of the equipment, the equipment operates at the minimum liquefied gas consumption.

[0396] For example, the efficiency condition of the equipment can be set based on the power change of the equipment using the liquefied gas usage amount in each equipment. Among them, the efficiency of the equipment refers to the ratio of the performance of the equipment to the liquefied gas usage amount used in the equipment. As an example, the performance of the compressor can refer to the compression target pressure. As another example, the performance of the reliquefaction unit can refer to the reliquefaction target temperature.

[0397] For example, the efficiency condition of the main engine can be set based on the speed of the ship and the amount of liquefied gas fuel required. Among them, the speed of the ship can be the optimal speed in each navigation section included in the optimal navigation information. In addition, the required liquefied gas fuel can be LNG gas or BOG.

[0398] For example, the efficiency condition of the generator engine can be set based on the power of the equipment installed on the ship and the basic power consumption of the ship. Among them, the power of the equipment installed on the ship can be the sum of the powers of all equipment. In addition, the basic power consumption of the ship can refer to the power basically used on the ship.

[0399] For example, the efficiency condition of the shaft generator can be set based on the power generation amount of the shaft generator at different rotational speeds of the propulsion engine. Among them, the sum of the power generation amount of the shaft generator and the power generation amount of the power generation engine can become the total power generation amount of the ship.

[0400] For example, the pressure condition of the storage tank can be set based on the maximum value and the minimum value of the storage tank pressure. Regarding the pressure of the storage tank, the storage tank pressure during a laden voyage and a ballast voyage can be obtained by different methods respectively.

[0401] For example, the maximum / minimum speed condition of the ship can be set based on the performance of the engine. Among them, when the navigation speed is below the minimum speed, the speed is 0 and the ship will stop.

[0402] For example, the average speed condition of the ship can be set based on the speeds of each navigation section of the ship. As an example, when the speeds of each navigation section included in the recommended navigation information are used during the navigation of the ship, the average of the speeds of each section may be the same as the total average speed calculated based on the total navigation time and the total navigation distance. As another example, when the speeds of each navigation section included in the optimal navigation information are used during the navigation of the ship, the average of the speeds of each section may also be the same as the total average speed calculated based on the total navigation time and the total navigation distance.

[0403] Therefore, the processor 110 can update the optimal navigation information that satisfies each constraint condition in consideration of the above various constraint conditions.

[0404] Refer again to Fig.26 , in step 2630, the processor 110 can control the operation of the ship using the updated optimal navigation information.

[0405] For example, the processor 110 can control the ship in a set driving manner using the optimal navigation information. Among them, the driving manner can include a driving manner that minimizes the gas consumption of the ship.

[0406] For example, when the processor 110 controls the operation of the ship using the optimal navigation information, the gas consumption of the ship can be minimized. In other words, the processor 110 can control the ship in a driving manner that minimizes the gas consumption of the ship.

[0407] Therefore, the processor 110 can control the ship in a driving manner that minimizes the gas consumption of the ship using the optimal navigation information updated in consideration of the constraint conditions.

[0408] Fig.29 is a diagram showing an example of a system for controlling the navigation of a ship according to an embodiment.

[0409] The ship 3220 may include a user terminal 3210 and a server 3240. For example, the user terminal 3210 and the server 3240 may be connected by wired or wireless communication means to transmit and receive data (e.g., navigation information) to and from each other.

[0410] For ease of explanation, Fig.29 it is shown that the system 3200 includes the user terminal 3210 and the server 3240, but is not limited thereto. For example, the system 3200 may include other external devices (not shown), and the operations of the user terminal 3210 and the server 3240 to be described below may be implemented by a single device (e.g., the user terminal 3210 or the server 3240) or multiple devices.

[0411] The user terminal 3210 may be a computing device including a display device and / or a device for receiving user input (e.g., a keyboard, a mouse, etc.) and including a memory and a processor. For example, the user terminal 3210 may include a notebook computer, a desktop computer, a laptop computer, a tablet computer, a smart phone, etc., but is not limited thereto.

[0412] The server 3240 may include a communication module capable of communicating with an external device (not shown) including the user terminal 3210 or communicating with other devices. The communication module may communicate with an external device (not shown) including the user terminal 3210 through a network. For example, the network may include a Value Added Network (VAN), a mobile radio communication network, a satellite communication network, and / or a combination thereof. The network is a data communication network in the comprehensive sense that enables Fig.29 the various configurations shown to communicate smoothly, and may include a wired communication network or a wireless communication network. As an example, the server 3240 may send preset navigation information and preset route information 3250 to the user terminal 3210. Alternatively, the server 3240 may be a computing device including a memory and a processor and having its own computing power. For example, the server 3240 may store various data including navigation information and route information 3250.

[0413] In the past, the operator of the ship 3220 controlled the pressure of the storage tank 3230 and the amount of liquefied gas evaporated from the storage tank 3230 based on an integrated automation system (IAS) that serves as an integrated control device. However, the IAS cannot accurately predict the pressure change of the storage tank 3230 and the change in the amount of liquefied gas evaporated from the storage tank 3230 according to meteorological changes during navigation. Therefore, during the navigation of the ship 3220, the operator of the ship 3220 repeatedly performs a process of judging the usage amount of the evaporated gas in order to control the pressure of the storage tank 3230. This results in uneconomical navigation of the ship 3220.

[0414] The user terminal 3210 according to an embodiment can calculate at least one predicted value for the navigation control of the ship 3220 and the energy efficiency operation index 3260 of the ship 3220. In addition, the user terminal 3210 can obtain measurement values measured in real time according to the navigation of the ship 3220, and compare the predicted values, the energy efficiency operation index 3260 with the measurement values.

[0415] Therefore, the user terminal 3210 can use the comparison results of the measurement values with the predicted values and the energy efficiency operation index 3260 to control the ship 3220, minimizing the judgment of the operator. Thus, the problem of uneconomical navigation caused by excessive judgment required of the operator can be solved. In addition, even without using the IAS, the operator can confirm whether economical navigation is being performed during navigation.

[0416] The ship 3220 may include a storage tank 3230. In addition, the storage tank 3290 may be located inside the arrival location 3280. Therefore, when the ship 3220 is navigating, the storage tank 3230 is located at sea, and the storage tank 3290 may be located on land. For example, the storage tank 3230 and the storage tank 3290 may have a double-wall structure and consist of an inner storage tank and an outer storage tank. The inner storage tank is a space for storing liquefied gas. The outer storage tank surrounds the inner storage tank and plays a role in insulating the liquefied gas.

[0417] The ship 3220 can move to the arrival location 3280 through a preset route 3270. The specific method of setting the route 3270 will be described below with reference to Fig.33 Description.

[0418] Hereinafter, reference will be made to Figure 2 And Figure 30 to Figure 36 To illustrate an example of the operation of the user terminal 3210.

[0419] Refer again to Figure 2 , Figure 2 The user terminal 100 of Fig.29 And the user terminal 3210 of

[0420] The processor 110 may obtain the preset navigation information and the preset route information 3250 of the ship 3220 from the server 3240. For example, the processor 110 may obtain the pressure of the storage tank 3230 when arriving at the destination, the in-port / out-port information of the ship 3220, the total navigation distance, the total navigation time, the average speed, and the meteorological information from the server 3240. In addition, the processor 110 may obtain the latitude, longitude, and speed of the ship 3220 at at least one preset time point.

[0421] Moreover, the processor 110 may calculate at least one predicted value for the navigation control of the ship 3220 by using the navigation information and the route information 3250. For example, the processor 110 may calculate at least one of the predicted value of the pressure inside the storage tank 3230, the predicted value of the amount of liquefied gas evaporated from the storage tank 3230, the predicted value of the flow rate of the liquefied gas pressurized by the pump in the storage tank 3230 and supplied to the internal device of the ship 3220 from the vaporizer, and the predicted value of the flow rate of the liquefied gas evaporated from the storage tank 3230 and supplied to the internal device of the ship 3220 from the compressor.

[0422] Moreover, the processor 110 may control the ship 3220 by comparing the predicted value with the measured value obtained in real time according to the navigation of the ship 3220.

[0423] On the other hand, although not shown in Figure 2 , the user terminal 100 may further include a display device. Alternatively, the user terminal 100 may be connected to an independent display device by wired or wireless communication to transmit and receive data therebetween. For example, the comparison result between the predicted value and the measured value may be provided to the user through the display device.

[0424] Fig.30 is a configuration diagram showing an example of a server according to an embodiment.

[0425] The server 3300 includes a processor 3310, a memory 3320, and a communication module 3330. For ease of explanation, Fig.30 only the components related to the present invention are shown. Therefore, in addition to Fig.30 the components shown, the server 3300 may further include other general components. In addition, Fig.30 it is obvious to those skilled in the technical field related to the present invention that the processor 3310, the memory 3320, and the communication module 3330 shown may be implemented as independent devices. In addition, Fig.30 the server 3300 of Fig.29 and the server 3240 of

[0426] The processor 3310 can set route information using navigation information. In addition, the processor 3310 can send the navigation information, route information, etc. to the user terminal 3210.

[0427] Navigation information and route information 3250, etc. can be stored in the memory 3320. Also, an operating system (OS) and at least one program (e.g., a program required for the operation of the processor 3310, etc.) can be stored in the memory 3320.

[0428] The communication module 3330 can provide a configuration or function for the server 3300 and the user terminal 3210 to communicate with each other via a network. Also, the communication module 3330 can provide a configuration or function for the server 3300 to communicate with other external devices. For example, control signals, instructions, data, etc. provided according to the control of the processor 3310 can be sent to the user terminal 3210 and / or external devices via the communication module 3330 and the network.

[0429] Fig.31 It is a flowchart showing an example for explaining a method of controlling the navigation of a ship according to an embodiment.

[0430] The method of controlling the navigation of the ship 3220 can include steps processed in time series in the Figure 2 and Fig.32 shown user terminal 3210, 100 or processor 110. Therefore, even if content is omitted hereinafter, the content described above regarding the Figure 2 and Fig.29 shown user terminal 100, 3210 or processor 110 can also be applied to the Fig.29 method of controlling the navigation of the ship 3220.

[0431] In step 3410, the processor 110 obtains preset navigation information of the ship 3220 from the server 3240.

[0432] For example, the navigation information can include the in-port / out-port information, total navigation distance, total navigation time, average speed, and meteorological information of the ship 3220. In addition, the navigation information can include the pressure of the storage tank 3230 included in the ship 3220 at the time point when the ship 3220 is expected to arrive at the arrival location. The pressure of the storage tank 3230 at the expected arrival time point can correspond to either the pressure of the storage tank 3290 provided at the arrival location or a preset pressure.

[0433] In step 3420, the processor 110 obtains the route information of the ship 3220 set from the server 3240 using the navigation information.

[0434] For example, the route information may include at least one of the latitude, longitude, and speed of the ship 3220 at at least one preset time point.

[0435] Hereinafter, reference will be made to Figure 32 to Figure 33 describe the navigation information and route information in detail.

[0436] Fig.32 FIG. is an example of a screen showing preset navigation information of a ship according to an embodiment.

[0437] Fig.32 An example of a screen 3510 for outputting various navigation information is shown. Specifically, various navigation information may be separated and displayed in regions 3511, 3512, 3513, and 3514 of the screen 3510. However, the layout of the screen 3510 and the output regions of the navigation information are not limited to Fig.32 the example shown.

[0438] In region 3511, the name of the departure location of the ship 3220, the departure time of the ship 3220, and the pressure of the liquefied gas cargo tank inside the departure location may be displayed. For example, the pressure at the time of departure of the storage tank 3230 may correspond to the pressure of the liquefied gas cargo tank inside the departure location.

[0439] In addition, in region 3512, the total navigation distance, total navigation time, and average speed of the ship 3220 may be displayed. For example, the total navigation distance may be calculated based on the distance traveled by the ship 3220 from the time point of leaving the departure location to the time point of arriving at the arrival location 3280. In addition, the total navigation time may be calculated based on the time consumed by the ship 3220 from the time point of leaving the departure location to the time point of arriving at the arrival location 3280. In addition, the average speed may be calculated by dividing the total navigation distance by the total navigation time.

[0440] In addition, in region 3513, the name of the arrival location of the ship 3220, the time when the ship 3220 will arrive at the arrival location, and the pressure of the storage tank 3290 may be displayed. For example, the pressure at the time of arrival of the storage tank 3230 may correspond to either the pressure of the storage tank 3290 or a preset pressure.

[0441] However, the pressure of the storage tank 3290 may not be included in the navigation information. In this case, the processor 110 may assume the pressure of the storage tank 3290 to be a specified value (for example, 100 mbarg) to calculate the predicted value.

[0442] In addition, in region 3514, information indicating the ratio of the navigation distance of the ship 3220 from the time of departure to the time of measurement to the total navigation distance, expressed as a percentage, may be displayed.

[0443] In addition, although not shown in Fig.32 shown in, but the navigation information may include meteorological information. For example, the meteorological information may refer to the meteorological information on the route 3270 from the time point when the ship 3220 departs from the departure location to the time point when it arrives at the arrival location 3280. In addition, the meteorological information may include air pressure, air temperature, wave height, etc.

[0444] Fig.33 is a diagram showing an example of a screen that can obtain either the manually set route of a ship or the route automatically set through the route optimization function according to an embodiment.

[0445] Fig.33 shows an example of the screen 3610 where the processor 110 can obtain route information. Specifically, various selection areas can be displayed in the areas 3611, 3612, 3613, 3614 of the screen 3610. However, the layout of the screen 3610 and the output area of the selection information are not limited to Fig.33 the example shown.

[0446] The processor 110 can obtain either the manually set route of the ship 3220 or the route automatically set through the route optimization function from the server 3240.

[0447] Among them, the manually set route and the automatically set route are set using preset navigation information.

[0448] For example, when the user selects the area 3611, the processor 110 can, in response thereto, activate the areas 3612 and 3613 that were previously in an inactive state. When the user selects the activated area 3612, the processor 110 can request the server 3240 to send the route information of the automatically set route through the Integrated Smartship Solution (ISS). Thus, the processor 110 can obtain the route information from the server 3240.

[0449] In addition, when the user selects the activated area 3613, the processor 110 can, in response thereto, request the server 3240 to send the route information of the automatically set route through the Integrated Smartship Solution (ISS). Thus, the processor 110 can obtain the route information from the server 3240.

[0450] In addition, when the user selects the area 3614, the processor 110 can, in response thereto, request the server 3240 to send the route information of the manually set route. Thus, the processor 110 can obtain the route information from the server 3240.

[0451] The route optimization function is a technology that optimizes the path and speed of the ship 3220 during navigation to minimize the consumption of liquefied gas fuel and optimize the navigation time. To optimize the route, various factors such as the position, speed, and meteorological information of the ship 3220 need to be considered. ISS and ECDIS are equivalent to a type of program that includes the route optimization function.

[0452] ISS is a system for managing the navigation of the ship 3220 and managing the operation of the device. It is a program that collects the main data of the ship 3220 in real time and provides analysis services for the main equipment including the engine and the navigation optimization function. In addition, ECDIS is a program that provides users with maps of navigation information and sea areas.

[0453] In addition, the information of the route manually set by the ship 3220 and the information of the route automatically set by the route optimization function include the latitude, longitude, and speed of the ship 3220 at at least one preset time point.

[0454] For example, the server 3240 can set N time points after the departure time point of the ship 3220. For example, the number of time points can be preset according to a specified period or adjusted according to the user's input. In addition, the 0th time point can correspond to the time point when the ship 3220 departs from the departure location, and the Nth time point can correspond to the time point when the ship 3220 arrives at the arrival location. The route information can include at least one of the latitude, longitude, and speed of the ship 3220 at at least any one of the N time points. Here, N refers to a natural number greater than or equal to 1.

[0455] For example, when the period is 2 days and the total navigation time is 24 days, the route information can include the information of the ship 3220 for a total of 12 locations. The route information can include the information of the latitude, longitude, and speed of the ship 3220 every two days after the ship 3220 departs. In addition, the pressure of the storage tank 3230 at the 12th time point can correspond to the pressure of the storage tank 3290 at the arrival location.

[0456] Refer again to Fig.31 , in step 3430, the processor 110 can calculate at least one predicted value for the navigation control of the ship 3220 using the navigation information and the route information 3250.

[0457] For example, the predicted value can include at least any one of the predicted value of the internal pressure of the storage tank 3230, the predicted value of the amount of liquefied gas evaporated from the storage tank 3230, and the predicted value of the flow rate of the liquefied gas evaporated from the storage tank 3230 supplied to the internal device of the ship 3220 by the compressor. For example, the device can include at least one of the compressor included inside the storage tank 3230, the vaporizer included inside the storage tank 3230, the gas combustion device, the reliquefaction device, the propulsion engine, and the power generation engine.

[0458] In the following, reference will be made to Fig.34 the process of calculating a predicted pressure inside a storage tank 3230 for ship 3220 navigation control using navigation information and route information 3250 will be described.

[0459] Fig.34 is a diagram for explaining an example of a method for calculating a predicted pressure value of a liquefied gas cargo tank according to an embodiment.

[0460] In step 3710, the processor 110 may obtain a preset pressure inside the storage tank 3290 at the arrival location from the server 3240.

[0461] When the pressure of the storage tank 3290 is not set, the processor 110 may calculate the predicted pressure value of the storage tank 3230 by assuming the pressure of the storage tank 3290 as a specified value (for example, 100 mbarg).

[0462] In step 3720, the processor 110 may divide the total navigation time of the ship 3220 into N time points at regular time intervals. The number of time points (i.e., N) is determined by the value obtained by dividing the total navigation time by the period. For example, the number of time points may be predetermined or arbitrarily determined by the user. Here, N refers to a natural number of 1 or more.

[0463] In step 3730, the processor 110 may calculate the pressure of the storage tank 3230 at the Nth time point as a value corresponding to either the pressure of the storage tank 3290 at the arrival location or the preset pressure.

[0464] In step 3740, the processor 110 may calculate the pressure change amount of the storage tank 3230 at each time point by comparing it with the pressure of the storage tank 3230 at the previous time point. For example, when the processor 110 calculates the pressure change amount of the storage tank 3230 at each time point by comparing it with the pressure of the storage tank 3230 at the previous time point, the pressure change amount of the storage tank 3230 is as shown in the following mathematical formula 1.

[0465] [Mathematical formula 1]

[0466] Storage tank pressure change amount = α (evaporation energy of LNG gas evaporated from the storage tank) + β (energy of gas flowing into the storage tank) - γ (energy of gas discharged from the storage tank)

[0467] The processor 110 may set the values of α, β, and γ by considering the cargo characteristics of the ship 3220, the pressure change characteristics of the storage tank 3230, the shape characteristics of the storage tank 3230, etc. The evaporation energy of the liquefied gas evaporated from the storage tank 3230, the energy of the gas flowing into the storage tank 3230, and the energy of the gas discharged from the storage tank 3230 are constant and can be determined according to the mass flowmeter at the gas consumption location of the ship 3220. For example, the gas consumption location may include a propulsion engine, a power generation engine, a gas combustion device, and a reliquefaction device.

[0468] In step 3750, the processor 110 may calculate the predicted value of the internal pressure of the storage tank 3230 at each time point based on the pressure change amount of the storage tank 3230 at each time point calculated in step 540.

[0469] Refer again to Fig.31 , in step 3430, the predicted value calculated by the processor 110 may include the predicted value of the amount of liquefied gas evaporated from the storage tank 3230.

[0470] In the past, the predicted value of the amount of liquefied gas evaporated from the storage tank 3230 was calculated by simply substituting unpredictable data such as the temperature of the liquefied gas inside the storage tank 3230 into a mathematical formula. This method has the problem that the amount of evaporated liquefied gas cannot be accurately predicted.

[0471] To solve the problem of inaccurate prediction in the traditional technology, the processor 110 may calculate the predicted value of the amount of evaporated liquefied gas using a deep learning model. In this case, the deep learning model may be learned using learning data such as navigation information and route information to calculate the predicted value of the evaporated liquefied gas amount.

[0472] The deep learning model refers to a statistical learning algorithm implemented based on the structure of a biological neural network in deep learning technology and cognitive science or the structure that executes its algorithm.

[0473] For example, the deep learning model may represent a model as described below. Just like in a biological neural network, nodes (Nodes) of artificial neurons that form a network through the combination of synapses learn by repeatedly adjusting the weights of the synapses to reduce the error between the correct output corresponding to a specific input and the inferred output, thereby having the ability to solve problems.

[0474] For example, a deep learning model can be implemented as a multilayer perceptron (MLP) composed of multiple layers of nodes and the connections between them. The deep learning model according to this embodiment can be implemented using one of various artificial neural network model structures including an MLP. For example, the deep learning model can consist of the following layers: an input layer that receives input signals or data from the outside; an output layer that outputs output signals or data corresponding to the input data; and at least one hidden layer located between the input layer and the output layer, which receives signals from the input layer, extracts features, and passes them to the output layer. The output layer receives signals or data from the hidden layer and outputs them to the outside.

[0475] In addition, the deep learning model that calculates the amount of liquefied gas evaporated from the storage tank 3230 can be stored in the user terminal 3210 and operate.

[0476] In step 3440, the processor 110 can calculate the energy efficiency operation index 3260 of the ship 3220 using the predicted value.

[0477] Among them, the energy efficiency operation index 3260 can include at least any one of the amount of liquefied gas loss inside the storage tank 3230, the consumption of liquefied gas used by the engine of the ship 3220, the amount of liquefied gas incinerated through the gas combustion device, the re-liquefaction flow rate of liquefied gas inside the storage tank 3230, and the boil-off rate (BOR).

[0478] For example, the processor 110 can calculate the energy efficiency operation index 3260 using the navigation information, route information, the predicted value of the amount of liquefied gas evaporated from the storage tank 3230, and the predicted value of the pressure of the storage tank 3230.

[0479] For example, the processor 110 can calculate the energy efficiency operation index 3260 using a driving optimization analysis model.

[0480] The driving optimization analysis model is a model that reduces the amount of liquefied gas loss by determining the liquefied gas flow rates supplied to devices such as the storage tank 3230, the engine, and the gas combustion device, and the liquefied gas flow rates consumed by each device.

[0481] For example, the processor 110 can calculate the energy efficiency operation index 3260 through the driving optimization analysis model using the navigation information, route information, the predicted value of the pressure of the storage tank 3230, and the predicted value of the amount of liquefied gas evaporated from the storage tank 3230.

[0482] In addition, the driving optimization analysis model can calculate the energy efficiency operation index 3260 by considering various constraints. For example, the model can consider the relationships among mass, energy, power consumption, maximum / minimum liquefied gas consumption of the device, efficiency of the equipment, efficiency of the propulsion engine, efficiency of the power generation engine, efficiency of the shaft generator, pressure in the storage tank 3230, maximum / minimum speed of the ship 3220, and average speed of the ship 3220 to calculate the energy efficiency operation index 3260.

[0483] In addition, the driving optimization analysis model that calculates the energy efficiency operation index 3260 can be stored in the user terminal 3210 for operation.

[0484] In step 3450, the processor 110 can compare the measured values obtained in real time according to the navigation of the ship 3220 with the predicted values and the energy efficiency operation index, and display the comparison results.

[0485] In step 3460, the processor 110 can use the comparison results to control the ship 3220.

[0486] Hereinafter, reference will be made to Figures 35a to 35c Describe an example of the result of the processor 110 comparing the measured values with the predicted values and the energy efficiency operation index.

[0487] Fig.35a FIG. is an example showing the comparison result of the predicted value and the measured value of the internal pressure of the liquefied gas cargo tank and the comparison result of the average speed and the measured value according to an embodiment.

[0488] As Fig.35a shown, the comparison result of the predicted value and the measured value can be calculated in the form of a chart 3810, but the display manner of the comparison result of the predicted value and the measured value is not limited to the chart 3810.

[0489] In the chart 3810, the first dashed line 3811 represents the predicted value of the internal pressure in the storage tank 3230, and the first solid line 3812 represents the measured value of the internal pressure in the storage tank 3230.

[0490] The processor 110 can control the ship 3220 so that the pressure in the storage tank 3230 is included in the pressure within the pressure control region set based on the predicted value of the internal pressure in the storage tank 3230. For example, when the ship 3220 is sailing fully loaded, the pressure control region can refer to the region above 60 mbarg and below 190 mbarg.

[0491] The processor 110 may control the ship 3220 to reduce the pressure in the storage tank 3230 of the ship 3220 when the pressure in the storage tank 3230 exceeds the pressure control region. For example, the processor 110 may reduce the pressure in the storage tank 3230 by increasing the flow rate of the evaporated liquefied gas supplied from the storage tank 3230 to the gas combustion device. In addition, the processor 110 may reduce the pressure in the storage tank 3230 by changing the combination of the liquefied gas supply device and the liquefied gas receiving device.

[0492] In addition, when the measured value is less than the predicted value, the processor 110 may control the storage tank 3230 to reduce the amount of liquefied gas supplied from the storage tank 3230 to the gas combustion device, the propulsion engine, the power generation engine, and the reliquefaction device, thereby increasing the pressure in the storage tank 3230.

[0493] In the graph 3810, the second dashed line 3813 represents the predicted value of the speed of the ship 3220, and the second solid line 3814 represents the measured value of the speed of the ship 3220.

[0494] The processor 110 may control the ship 3220 to make the measured value correspond to the predicted value. For example, when the measured value exceeds the predicted value, the processor 110 may control the ship 3220 to reduce the speed of the ship 3220. In addition, when the measured value is less than the predicted value, the processor 110 may control the ship 3220 to increase the speed of the ship 3220.

[0495] In the graph 3810, the third dashed line 3815 represents the predicted value of the load factor of the internal propulsion engine of the ship 3220, and the third solid line 3816 represents the measured value of the load factor of the internal propulsion engine of the ship 3220.

[0496] The processor 110 may control the ship 3220 to make the load factor of the internal propulsion engine of the ship 3220 correspond to the predicted value. For example, the processor 110 may change the combination of the liquefied gas supply device and the liquefied gas receiving device. In addition, the processor 110 may control the supply flow rate of the liquefied gas supply device.

[0497] For example, when the load factor of the internal propulsion engine of the ship 3220 exceeds the predicted value, the processor 110 may control the ship 3220 to increase the flow rate of the liquefied gas supplied from the storage tank 3230 to the propulsion engine. In addition, when the load factor of the internal propulsion engine of the ship 3220 is less than the predicted value, the processor 110 may control the ship 3220 to reduce the flow rate of the liquefied gas supplied from the storage tank 3230 to the propulsion engine.

[0498] Fig.35b It is a diagram showing an example of the comparison result between the predicted value and the measured value of the amount of evaporated liquefied gas in a liquefied gas cargo hold according to an embodiment.

[0499] As Fig.35bAs shown, the comparison result between the predicted value and the measured value can be output in the form of Chart 3820. However, the display method of the comparison result between the predicted value and the measured value is not limited to Chart 3820.

[0500] In Chart 3820, the first dashed line 3821 represents the predicted value of the amount of liquefied gas evaporated from the storage tank 3230, and the first solid line 3822 represents the measured value of the amount of liquefied gas evaporated from the storage tank 3230.

[0501] For example, the processor 110 can calculate the predicted value of the amount of liquefied gas evaporated through a deep learning model.

[0502] The processor 110 can control the ship 3220 based on the predicted value of the amount of liquefied gas evaporated. For example, the processor 110 can control the type of device for supplying the evaporated liquefied gas according to the predicted value. In addition, the processor 110 can control the supply flow rate of the device for supplying the evaporated liquefied gas.

[0503] For example, the processor 110 can control the ship 3220 according to the predicted value to limit the supply device of the evaporated liquefied gas to the compressor included in the storage tank 3230. In addition, the processor 110 can control the ship 3220 according to the predicted value so that the flow rate of the evaporated liquefied gas supplied by the compressor to the devices of the ship 3220 becomes 2500 kg / h. In addition, the processor 110 can control the ship 3220 according to the predicted value so that the flow rate of the evaporated liquefied gas supplied by the compressor to the gas combustion device becomes 1000 kg / h, and the flow rate of the evaporated liquefied gas supplied by the compressor to the propulsion engine and the power generation engine becomes 1500 kg / h.

[0504] In Chart 3820, the first area 3823 shows the predicted value of the flow rate of the evaporated liquefied gas supplied by the compressor included inside the storage tank 3230 to the gas combustion device. The second area 3824 shows the predicted value of the flow rate of the evaporated liquefied gas supplied by the compressor included inside the storage tank 3230 to the propulsion engine and the power generation engine.

[0505] In addition, although not shown in Chart 3820, the predicted value may include the predicted value of the flow rate of the evaporated liquefied gas supplied by the compressor to the reliquefaction device, the predicted value of the flow rate of the evaporated liquefied gas supplied by the vaporizer included inside the storage tank 3230 to the propulsion engine and the power generation engine, and the predicted value of the flow rate of the evaporated liquefied gas supplied by the storage tank included inside the storage tank 3230 to the subcooler.

[0506] Fig.35c It is a diagram showing an example of the comparison result between the energy efficiency operation index of a ship according to an embodiment and the measured value.

[0507] As Fig.35cAs shown, the comparison result between the energy efficiency operation index 3260 and the measured value can be calculated in the form of Table 3830, but the display method of the comparison result between the energy efficiency operation index 3260 and the measured value is not limited to Table 3830.

[0508] The first item 3831 refers to the amount of liquefied gas loss inside the storage tank 3230. For example, the processor 110 can calculate the sum of the cumulative value of the liquefied gas flow rate supplied from the storage tank 3230 to the propulsion engine, the cumulative value of the liquefied gas flow rate supplied from the storage tank 3230 to the power generation engine, and the cumulative value of the liquefied gas flow rate supplied from the storage tank 3230 to the gas combustion device from the time when the ship 3220 leaves the port to the measurement time as the measured value of the first item 3831.

[0509] In addition, the second item 3832 refers to the amount of liquefied gas consumed by the engines of the ship 3220. For example, the processor 110 can calculate the sum of the cumulative value of the liquefied gas flow rate supplied from the storage tank 3230 to the propulsion engine and the cumulative value of the liquefied gas flow rate supplied from the storage tank 3230 to the power generation engine from the time when the ship 3220 leaves the port to the measurement time as the measured value of the second item 3832.

[0510] In addition, the third item 3833 refers to the amount of liquefied gas burned by the gas combustion device of the ship 3220. For example, the processor 110 can calculate the measured value of the third item 3833 through the cumulative value of the liquefied gas flow rate supplied from the storage tank 3230 to the gas combustion device from the time when the ship 3220 leaves the port to the measurement time.

[0511] In addition, the fourth item 3834 refers to the re-liquefaction flow rate inside the storage tank 3230. For example, the processor 110 can calculate the cumulative value of the liquefied gas flow rate passing through the re-liquefaction device from the time when the ship 3220 leaves the port to the measurement time as the measured value of the fourth item.

[0512] In addition, the fifth item 3835 refers to the daily evaporation rate. For example, the processor 110 can calculate the measured value of the fifth item 3835 through the ratio of the total volume of liquefied gas stored in the storage tank 3230 from the time when the ship 3220 leaves the port to the measurement time to the daily average value of the liquefied gas evaporation amount.

[0513] Fig.36 It is a diagram showing an example of a screen displayed by a processor according to an embodiment.

[0514] In Fig.36 An example of an execution screen 3900 of a program for executing the method described above with reference to Figure 29 to Figure 35c is shown.

[0515] For example, preset navigation information of the ship 3220 may be displayed in the area 3910. Specifically, at least one of the pressure of the storage tank 3230 when the ship 3220 arrives at the arrival location, the in-port / out-port information, the total navigation distance, the total navigation time, the average speed, and the meteorological information may be displayed.

[0516] In addition, a screen for the processor 110 to obtain route information may be displayed in the area 3920. The processor 110 may obtain any one of the manually set route of the ship 3220 and the automatically set route through the route optimization function from the server 3240.

[0517] In addition, the comparison result between the predicted value and the measured value of the pressure of the storage tank 3230, the comparison result between the average speed of the ship 3220 and the measured value, and the comparison result between the predicted value and the measured value of the pressure of the storage tank 3230 may be displayed in the area 3930.

[0518] In addition, the comparison result between the predicted value and the measured value of the amount of liquefied gas evaporated from the storage tank 3230, the predicted flow rate of the liquefied gas supplied by the internal compressor of the storage tank 3230 to the power generation engine and the propulsion engine, and the predicted flow rate of the liquefied gas supplied by the internal compressor of the storage tank 3230 to the gas combustion device may be displayed in the area 3940.

[0519] In addition, the comparison result between the energy efficiency operation index 3260 and the measured value may be displayed in the area 3950. Specifically, the energy efficiency operation index 3260 may include at least one of the amount of liquefied gas loss inside the storage tank 3230, the amount of liquefied gas consumed by the engine of the ship 3220, the amount of liquefied gas burned by the gas combustion device, the liquefied gas reliquefaction flow rate inside the storage tank 3230, and the daily evaporation rate.

[0520] In addition, the comparison result between the flow rate supplied to the devices inside the ship 3220 in real time and the preset flow rate may be displayed in the area 3960. Additionally, whether the devices are powered may be displayed. Specifically, the devices may include the compressor included inside the storage tank 3230, the vaporizer included inside the storage tank 3230, the gas combustion device, the reliquefaction device, etc.

[0521] According to the above, the present invention generates recommended navigation information about the navigation path of the ship based on the navigation plan information related to the departure location and the arrival location of the ship, predicts the BOG generation amount of the ship and the storage tank pressure value of the ship based on the recommended navigation information, and obtains the optimal navigation information related to the motion control of the ship based on the BOG generation amount and the storage tank pressure value. In addition, the present invention may control the ship in a preset driving manner using the optimal navigation information.

[0522] As described above, the present invention can predict the BOG generation amount and the storage tank pressure value based on one or more environmental information including meteorological and climate information, tidal current information, marine information, and ocean current information of each position on the navigation path of the ship, and obtain the optimal navigation information based on the predicted BOG generation amount and the storage tank pressure value to calculate the entire navigation operation, so as to provide direction suggestions for cargo management from the departure place to the arrival place of the ship, and implement safe cargo handling based on the predicted storage tank pressure value.

[0523] In addition, the present invention can propose a navigation method that consumes a large amount of fuel at positions where a large amount of fuel is required during navigation to reduce the storage tank pressure, and consumes a small amount of fuel at positions where a small amount of fuel is required to increase the storage tank pressure, so that the final target storage tank pressure can be maintained.

[0524] In addition, the present invention controls the ship based on the optimal navigation information in a driving mode that minimizes the consumption of liquefied gas to provide ship driving guidance to the driver, so as to assist navigation, and can provide a carbon tax reduction effect by reducing the GCU incineration amount and the fuel gas amount of the engine.

[0525] In addition, the present invention can help the driver make decisions about navigation by predicting the BOG generation amount and the storage tank pressure value in the navigation path of an unfamiliar ship.

[0526] On the other hand, the above method can be written as a program executable by a computer and can be implemented in a general digital computer that runs the program using a computer-readable recording medium. In addition, the structure of the data used in the above method can be recorded in the computer-readable recording medium in various ways. The computer-readable recording medium includes storage media such as magnetic storage media (e.g., ROM, RAM, USB, floppy disk, hard disk, etc.), optically readable media (e.g., CD-ROM, DVD, etc.).

[0527] On the other hand, the method can be provided in a computer program product. The computer program product is a commodity that can be traded between a seller and a buyer. The computer program product can be in the form of a device-readable storage medium (e.g., CD-ROM (compact disc read only memory)) or distributed directly or online (e.g., downloaded or uploaded) between two user devices through an application store (e.g., Play Store TM). In the case of online distribution, at least a part of the computer program product can be at least temporarily stored or temporarily generated in a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0528] Those of ordinary skill in the art related to the technical field of this embodiment can understand that this embodiment can be implemented in a modified form without departing from the above-described basic features. Therefore, the disclosed method should be considered from an interpretive rather than a restrictive perspective, and the scope of rights is reflected by the patent claims rather than the foregoing description, and should be construed to include all differences within its equivalent scope.

Claims

1. A method for optimizing the navigation of a ship, characterized in that, including: a generating step of generating recommended navigation information about the navigation path of the ship based on navigation plan information related to the departure location and arrival location of the ship; a predicting step of predicting the evaporation gas generation amount of the ship and the storage tank pressure value of the ship based on the recommended navigation information; and an optimal navigation information obtaining step of obtaining optimal navigation information related to the motion control of the ship based on the evaporation gas generation amount and the storage tank pressure value.

2. The method for optimizing the navigation of a ship according to claim 1, characterized in that, the navigation plan information includes position information of the departure time, arrival time and location; the generating step includes the following steps: obtaining environmental information about the navigation path of the ship based on the navigation plan information, and generating the recommended navigation information based on the navigation plan information and the environmental information with the fuel consumption amount and evaporation gas generation amount of the navigation path of the ship as a reference.

3. The method for optimizing the navigation of a ship according to claim 1, characterized in that, the recommended navigation information includes at least one of position information of each navigation section of the navigation path, speed information of each navigation section and environmental information of each navigation section.

4. The method for optimizing the navigation of a ship according to claim 3, characterized in that, the predicting step includes the following steps: predicting the evaporation gas generation amount of the ship based on at least one of the position information of each navigation section, the speed information of each navigation section and the environmental information of each navigation section, and predicting the storage tank pressure value of the ship based on at least one of the position information of each navigation section, the speed information of each navigation section, the environmental information of each navigation section and a preset liquefied gas consumption amount.

5. The method for optimizing the navigation of a ship according to claim 1, characterized in that, the optimal navigation information obtaining step includes: an nth intermediate navigation information generating step of generating nth intermediate navigation information related to the motion control of the ship based on the evaporation gas generation amount and the storage tank pressure value, and a determining step of determining the (n + 1)th intermediate navigation information as the optimal navigation information based on a comparison between the nth intermediate navigation information and the (n + 1)th intermediate navigation information with a preset threshold as a reference; the (n + 1)th intermediate navigation information is generated based on an updated value of at least one of the speed information and liquefied gas consumption amount of each navigation section included in the nth intermediate navigation information; n is a natural number of 1 or more.

6. The method for optimizing the navigation of a ship according to claim 5, characterized in that, the determining step includes the following steps: calculating a difference value based on the nth intermediate navigation information and the (n + 1)th intermediate navigation information, and in response to the difference value being less than or equal to the preset threshold, determining the (n + 1)th intermediate navigation information as the optimal navigation information, and In response to the difference exceeding a preset threshold, update at least one of the speed information and the liquefied gas consumption of each navigation section included in the (n + 1)-th intermediate navigation information to generate the (n + 2)-th intermediate navigation information.

7. The method for optimizing the navigation of a ship according to claim 1, wherein the optimal navigation information includes at least one of the evaporation gas generation amount of the ship, the storage tank pressure value of the ship, the speed information of each navigation section of the ship, the liquefied gas consumption of the ship, and the usage amount of the equipment provided on the ship.

8. The method for optimizing the navigation of a ship according to claim 1, wherein it further includes a control step of controlling the ship in a preset driving manner by using the optimal navigation information; the driving manner includes a driving manner that minimizes the liquefied gas consumption of the ship.

9. A computer-readable recording medium, wherein a program for executing the method according to claim 1 on a computer is recorded.

10. A computing device, wherein it includes: at least one memory, and at least one processor; the processor is configured to generate recommended navigation information about the navigation path of the ship based on navigation plan information related to the departure location and the arrival location of the ship, predict the evaporation gas generation amount and the storage tank pressure value of the ship based on the recommended navigation information, obtain optimal navigation information related to the action control of the ship based on the evaporation gas generation amount and the storage tank pressure value.

11. A method for predicting the evaporation gas generation amount of a ship, wherein it includes: a selection step of using input data selection model to select input data of an evaporation gas generation amount prediction model from a part of pre-stored navigation data, a learning step of using the input data to learn an evaporation gas generation amount prediction model including a plurality of deep learning models, and a prediction step of predicting the evaporation gas generation amount from the learned evaporation gas generation amount prediction model by using the current navigation data of the ship.

12. The method for predicting the evaporation gas generation amount of a ship according to claim 11, wherein the selection step includes the following steps: calculate the correlation coefficient between the part of pre-stored navigation data and the evaporation gas generation amount, learn the input data selection model by using the calculated correlation coefficient, and select the data with a correlation coefficient above a specified value as the input data by using the learned input data selection model.

13. The method for predicting the evaporation gas generation amount of a ship according to claim 11, wherein the learning step includes the following steps: calculate the correct data for the learning, learn by using the input data and the calculated correct data, and verify the evaporation gas generation amount prediction model by using another part of pre-stored navigation data.

14. The method for predicting the evaporation gas generation amount of a ship according to claim 11, wherein the prediction step includes: An output step of outputting respective initial evaporation gas generation amount prediction values of the plurality of deep learning models, and An operation step of applying different weights to the initial evaporation gas generation amount prediction values respectively to calculate a final evaporation gas generation amount prediction value.

15. The method for predicting the evaporation gas generation amount of a ship according to claim 14, wherein The operation step includes the following steps: Applying a maximum weight to the initial evaporation gas generation amount prediction value output by the stacked model among the initial evaporation gas generation amount prediction values.

Images