Smart Agriculture System and Aquaculture System Using Digital Twin And Operation Method of the Same

Abstract

The present invention discloses a smart aquaculture system using a digital twin and a method of operation thereof, which simulates and monitors the energy flow and usage of an aquaculture farm using a digital twin, monitors the water flow and air quality of the aquaculture farm through a physics engine and fluid dynamics simulation, and automatically manages an indoor aquaculture farm through reinforcement learning of a robot. The smart aquaculture system using a digital twin according to the present invention comprises: a digital twin visualization module that virtually reproduces an aquaculture farm and visualizes it identically to the actual environment of the aquaculture farm; an energy simulation module that simulates the amount of electrical energy generated in the aquaculture farm and the amount of electricity used in the aquaculture farm; a fluid dynamics simulation module that simulates the flow of fluids used in the aquaculture farm; a robot control module that controls a robot managing the aquaculture farm; a data collection module that collects data of the aquaculture farm in real time; an artificial intelligence analysis module that analyzes the data collected from the data collection module; and an aquaculture farm control module that controls the aquaculture farm based on the data analyzed by the artificial intelligence analysis module.

Description

Technology Field

[0001] The present invention relates to a smart aquaculture system using a digital twin and a method of operating the same. More specifically, it relates to a smart aquaculture system using a digital twin and a method of operating the same that simulates and monitors the energy flow and usage of an aquaculture farm using a digital twin, monitors the water flow and air quality of the farm through a physics engine and fluid dynamics simulation, and automatically manages an indoor aquaculture farm through robot reinforcement learning to increase the harvest of agricultural and fishery products. In agriculture, it can be applied to agricultural plants used in smart farms, etc. Background Technology

[0002] Modern aquaculture farms are adopting various advanced technologies for more efficient and sustainable operations. Among these, digital twin technology is emerging as an important tool for maximizing the efficiency of aquaculture farm operations.

[0003] A digital twin is a virtual model that precisely replicates a physical object or system digitally. This virtual model maintains synchronization by exchanging data with the actual object in real time. By doing so, the performance, status, and quality of the object or system can be monitored and analyzed in real time. The characteristics of a digital twin can be summarized in three points. First, it simulates using various data and connects objects with phenomena. Second, it encompasses the entire system actually in operation throughout its lifecycle. Third, it proposes solutions by analyzing data from problems that occur in the real world. If this digital twin technology is applied to the operation of aquaculture farms, it can predict and resolve potential issues that may arise during operations; therefore, further research in this area is necessary. Prior art literature

[0004] Republic of Korea Published Patent Application No. 10-2022-0076753 Republic of Korea Published Patent Application No. 10-2023-0100092 The problem to be solved

[0005] The present invention aims to solve the aforementioned problems by providing a smart aquaculture system using a digital twin and a method of operation thereof, which simulates and monitors the energy flow and usage of an aquaculture farm using a digital twin, monitors the water flow and air quality of the aquaculture farm through a physics engine and fluid dynamics simulation, and automatically manages an indoor aquaculture farm through robot reinforcement learning. means of solving the problem

[0006] A smart aquaculture system using a digital twin according to an embodiment of the present invention for achieving the above-mentioned purpose comprises: a digital twin visualization module that virtually reproduces an aquaculture farm and visualizes it identically to the actual environment of the aquaculture farm; an energy simulation module that simulates the amount of electrical energy generated in the aquaculture farm and the amount of electricity used in the aquaculture farm; a fluid dynamics simulation module that simulates the flow of fluids used in the aquaculture farm; a robot control module that controls a robot managing the aquaculture farm; a data collection module that collects data of the aquaculture farm in real time; an artificial intelligence analysis module that analyzes the data collected from the data collection module; and an aquaculture farm control module that controls the aquaculture farm based on the data analyzed by the artificial intelligence analysis module.

[0007] The digital twin visualization module includes a 3D virtual space section in which a fish farm is implemented in 3D, a preliminary design section that allows for preliminary design before actually constructing the fish farm, and a data display section that enables data collected by the data collection module to be displayed in real time in the 3D virtual space section.

[0008] The above energy simulation module is a smart aquaculture system using a digital twin, comprising a power generation simulation unit in which the amount of electric energy generated from eco-friendly energy production devices installed in the aquaculture farm is simulated, a usage simulation unit in which the amount of electricity used by devices installed in the aquaculture farm is simulated, and a cost prediction unit in which the cost of using electric energy in the aquaculture farm is predicted.

[0009] The above fluid dynamics simulation module includes a water flow simulation unit in which the flow of water used in the aquaculture farm is simulated, and an air flow analysis unit in which the flow of air used in the aquaculture farm is analyzed.

[0010] The above-described robot control module includes a robot reinforcement learning unit in which reinforcement learning is performed to pre-learn the robot's movement path and actions to be performed during tank management in an aquaculture farm, a robot additional learning unit in which additional learning information for the robot is generated based on the robot's current state and feedback, and a robot data collection unit in which data within the aquaculture farm is collected through the robot.

[0011] In addition, a method of operating a smart aquaculture system using a digital twin according to an embodiment of the present invention for achieving the above-mentioned purpose comprises: a first step in which an aquaculture farm is virtually reproduced and visualized by a digital twin; a second step in which electrical energy generated and used in the aquaculture farm is simulated; a third step in which the flow of water used in the aquaculture farm is simulated; a fourth step in which the flow of air used in the aquaculture farm is simulated; a fifth step in which data is collected by a robot used in the aquaculture farm and the robot is controlled; and a sixth step in which the simulation data and collected data are analyzed and the aquaculture farm is controlled.

[0012] The above first step includes a first-1 step in which information on the construction of a fish farm is input, a first-2 step in which a 3D model of the fish farm is created, a first-3 step in which equipment and devices are placed in the fish farm, a first-4 step in which design information of the fish farm is stored, a first-5 step in which data of the fish farm is linked, and a first-6 step in which the data of the first-5 step is visualized in the 3D model of the fish farm.

[0013] The above second step includes a 2-1 step in which electrical energy produced from eco-friendly energy production devices installed in the fish farm and the amount of electricity used by devices installed in the fish farm are collected; a 2-2 step in which the total amount of electrical energy is simulated; a 2-3 step in which the energy costs of the fish farm are predicted; and a 2-4 step in which efficient energy usage scheduling and eco-friendly energy usage are recommended.

[0014] The above third step includes a 3-1 step in which water flow data of the fish farm's pipelines and tanks is collected, a 3-2 step in which the water flow rate for each device in the fish farm is simulated, a 3-3 step in which the capacity of the fish farm's replenishment water and discharge water is predicted, and a 3-4 step in which the operation of the filter and UV disinfection of the water are scheduled.

[0015] The above-mentioned fourth step includes a fourth step (4-1) in which air flow data around the fish farm and tank is collected, a fourth step (4-2) in which the movement of air is simulated, a fourth step (4-3) in which the opening time of an air filter for external air ventilation is predicted, and a fourth step (4-4) in which the location of the air filter is set and air UV disinfection is scheduled.

[0016] The above 5th step includes 5-1, in which digital twin data of the fish farm and data of the robot model are collected; 5-2, in which the robot's movement path, management actions, and standby actions are set; 5-3, in which digital twin-based reinforcement learning is performed; 5-4, in which the operation of the robot is tested; and 5-5, in which the operation and movement of the robot, the robot's arm movements, and sensor data are transmitted in real time. Effects of the invention

[0017] As described above, the present invention has the advantage of enabling the operation of a fish farm through simulation before actual operation, thereby allowing for the detection and correction of problems that may occur during the actual construction of the fish farm, and facilitating the design of an efficient fish farm.

[0018] In addition, if the present invention is used in conjunction with an actual fish farm, there is an advantage in that a simulation can be performed using a digital twin before any measures are taken to verify whether there are any problems, and then actual measures can be implemented. Brief explanation of the drawing

[0019] Figure 1 shows a fish farm implemented by a smart aquaculture system using a digital twin according to one embodiment of the present invention. FIG. 2 is a configuration diagram of a smart aquaculture system using a digital twin according to an embodiment of the present invention. FIG. 3 is a configuration diagram of a digital twin visualization module according to one embodiment of the present invention. FIG. 4 is a configuration diagram of an energy simulation module according to one embodiment of the present invention. FIG. 5 is a configuration diagram of a fluid dynamics simulation module according to one embodiment of the present invention. FIG. 6 is a configuration diagram of a robot simulation module according to one embodiment of the present invention. FIG. 7 is a flowchart of the operation method of a smart aquaculture system using a digital twin according to an embodiment of the present invention. FIG. 8 is a flowchart of the detailed steps of the first step in the operation method of a smart aquaculture system using a digital twin according to an embodiment of the present invention. FIG. 9 is a flowchart of the detailed steps of the second step in the operation method of a smart aquaculture system using a digital twin according to an embodiment of the present invention. FIG. 10 is a flowchart of the detailed steps of the third step in the operation method of a smart aquaculture system using a digital twin according to one embodiment of the present invention. FIG. 11 is a flowchart of the detailed steps of the fourth step in the operation method of a smart aquaculture system using a digital twin according to an embodiment of the present invention. FIG. 12 is a flowchart of the detailed steps of the fifth step in the operation method of a smart aquaculture system using a digital twin according to one embodiment of the present invention. Specific details for implementing the invention

[0020] Expressions such as “comprising” or “may comprise” that may be used in various embodiments of the present disclosure indicate the presence of the disclosed corresponding function, operation, or component, etc., and do not limit one or more additional functions, operations, or components, etc. Furthermore, in various embodiments of the present disclosure, terms such as “comprising” or “having” are intended to specify the presence of the features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0021] 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.

[0022] Expressions such as "first," "second," "first," or "second" used in various embodiments of the present disclosure may modify various components of the various embodiments, but do not limit such components. For example, such expressions do not limit the order and / or importance of such components. Such expressions may be used to distinguish one component from another. For example, the first user device and the second user device are both user devices and represent different user devices. For example, without departing from the scope of the various embodiments of the present disclosure, the first component may be named the second component, and similarly, the second component may be named the first component.

[0023] When it is stated that a component is "connected" or "connected" to another component, it should be understood that the component may be directly connected or connected to the other component, but that a new component may exist between the component and the other component. On the other hand, when it is stated that a component is "directly connected" or "directly connected" to another component, it should be understood that no new component exists between the component and the other component.

[0024] In embodiments of the present disclosure, terms such as "module," "unit," "part," etc. are used to refer to a component that performs at least one function or operation, and such component may be implemented in hardware or software, or a combination of hardware and software. Additionally, a plurality of "modules," "units," "parts," etc. may be integrated into at least one module or chip and implemented as at least one processor, except where each needs to be implemented in specific individual hardware.

[0025] The terms used in the various embodiments of this disclosure are used merely to describe specific embodiments and are not intended to limit the various embodiments of this disclosure. The singular expression includes the plural expression unless the context clearly indicates otherwise.

[0026] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the various embodiments of this disclosure pertain.

[0027] Terms such as those defined in commonly used dictionaries should be interpreted as having meanings consistent with their meanings in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in the various embodiments of the present disclosure.

[0029] Hereinafter, a smart aquaculture system (10) using a digital twin according to an embodiment of the present invention will be described with reference to the drawings. FIG. 1 shows a fish farm implemented by a smart aquaculture system (10) using a digital twin according to an embodiment of the present invention, and FIG. 2 is a configuration diagram of a smart aquaculture system (10) using a digital twin according to an embodiment of the present invention. Referring to FIG. 1 and FIG. 2, a smart aquaculture system (10) using a digital twin according to an embodiment of the present invention may be configured to include a digital twin visualization module (100), an energy simulation module (200), a fluid dynamics simulation module (300), a robot control module (400), a data collection module (500), an artificial intelligence analysis module (600), and a fish farm control module (700). The smart aquaculture system (10) using a digital twin of the present invention may include one or more processors, one or more memories, one or more storage, and one or more communication interfaces, and these may be connected to each other via a bus. In addition, the smart aquaculture system (10) using a digital twin may include hardware such as input devices and output devices. Furthermore, the smart aquaculture system (10) using a digital twin may be equipped with various software, including an operating system capable of running programs and 3D modeling.

[0030] First, the digital twin visualization module (100) virtually reproduces the fish farm and visualizes it in the same way as the actual environment of the fish farm. FIG. 3 is a configuration diagram of the digital twin visualization module (100) according to an embodiment of the present invention. Referring to FIG. 3, the digital twin visualization module (100) according to an embodiment of the present invention may be configured to include a 3D virtual space unit (110), a pre-design unit (120), and a data display unit (130).

[0031] The 3D virtual space unit (110) implements the fish farm in 3D and displays data of the fish farm in real time. As illustrated in FIG. 1, the 3D virtual space unit (110) implements the fish farm in 3D, and the implemented virtual fish farm is displayed through an output device. The 3D virtual space unit (110) uses 3D modeling technology to virtually configure aquaculture equipment and facilities. In addition, the 3D virtual space unit (110) displays data received from the data display unit (120), including the activity level of aquaculture organisms, water quality status, status of fish farm equipment, energy efficiency, toxicity concentration and flow of discharged water and circulating water, water level information of the tank, and the current status and scheduling status of the robot.

[0032] The preliminary design unit (120) enables preliminary design before the actual construction of the fish farm. Through the preliminary design unit (120), the indoor fish farm can be designed in advance before actual construction by utilizing fish farming equipment and facilities composed of various 3D models. Through the preliminary design unit (120), the manager can design the fish farm in a virtual 3D space and plan the placement of various facilities and devices in advance. This allows for the discovery and correction of problems that may occur during actual construction in advance, and enables efficient fish farm design. The preliminary design unit (120) is equipped with a design data storage unit that stores the designed content.

[0033] The data display unit (130) enables data collected from the data collection module (500) to be displayed in real time on the 3D virtual space unit (110). The data display unit (120) displays the data of the fish farm in real time in a chronological manner on the 3D virtual space unit (110). The data of the fish farm includes data regarding the activity level of aquaculture organisms, water quality status, status of fish farm equipment, energy efficiency, toxicity concentration and flow of discharged water and circulating water, water level information of the tank, and the current status and scheduling status of the robot. The data display unit (120) receives this fish farm data in real time from the data collection module (500) and displays it on the 3D virtual space unit (110). Through this, the manager can intuitively understand the current status of the fish farm.

[0034] Next, the energy simulation module (200) simulates the amount of electricity generated in the fish farm and the amount of electricity used in the fish farm. FIG. 4 is a configuration diagram of the energy simulation module (200) according to an embodiment of the present invention. Referring to FIG. 4, the energy simulation module (200) according to an embodiment of the present invention may be configured to include a power generation simulation unit (210), a usage simulation unit (220), and a cost prediction unit (230).

[0035] The power generation simulation unit (210) simulates the amount of electric energy generated from eco-friendly energy production devices installed in the fish farm. The smart aquaculture of the present invention can be operated by generating electric energy from eco-friendly energy production devices such as solar panels. The power generation simulation unit (210) simulates the amount of electric energy actually generated by implementing an actual solar panel as a digital twin and extracts the total amount of electric energy generated.

[0036] The usage simulation unit (220) simulates the electricity usage used by devices installed in the fish farm. The devices installed in the fish farm are driven by electricity, and the total electricity energy usage is extracted by simulating the electricity usage actually consumed by these devices.

[0037] The cost prediction unit (230) predicts the cost of using electric energy in the aquaculture farm. The cost prediction unit (230) can predict the cost of drawing electric energy from an external source by comparing the total electric energy generation amount extracted from the power generation simulation unit (210) with the total electric energy usage amount extracted from the usage simulation unit (220) to calculate the electric energy usage amount that the generated electric energy cannot cover. Additionally, the cost prediction unit (230) recommends an efficient energy usage method based on the production of eco-friendly energy, and the manager can reduce energy costs by receiving recommendations for an optimal schedule for using eco-friendly energy. Since the present invention aims for an eco-friendly aquaculture farm, the manager can manage efficient energy usage through the cost prediction unit (240) so that it can be operated by eco-friendly energy produced internally. Furthermore, the cost prediction unit (230) transmits the total electric energy generation amount extracted from the power generation simulation unit (210), the total electric energy usage amount extracted from the usage simulation unit (220), and the total energy cost to the data collection module (500).

[0038] Next, the fluid dynamics simulation module (300) simulates the flow of fluid used in the aquaculture farm. FIG. 5 is a configuration diagram of the fluid dynamics simulation module (300) according to an embodiment of the present invention. Referring to FIG. 5, the fluid dynamics simulation module (300) according to an embodiment of the present invention may be configured to include a water flow simulation unit (310) and an air flow analysis unit (320).

[0039] The water flow simulation unit (310) simulates the flow of water used in the fish farm. The water flow simulation unit (310) includes a function to determine the replenishment water and discharge water that need to be added, as well as the operating schedule and capacity of the filter, through fluid dynamics simulation of the water flow used in the fish farm in advance. Through water flow simulation, the manager can precisely simulate the flow of water within the fish farm and accurately predict the amount of replenishment water and discharge water required. In addition, the water flow simulation unit (310) enables efficient water management by optimizing the operating schedule and capacity of the filter. The water flow simulation unit (310) transmits the simulated water flow and data related to the amount of replenishment water and discharge water to the data collection module (500).

[0040] The air flow analysis unit (320) simulates and analyzes the air flow used in the fish farm. The air flow analysis unit (320) includes the function of analyzing the air flow around the fish tanks in the fish farm to block external harmful substances, provide sufficient air supply within the closed fish farm, and provide information on the installation locations of appropriate air filters inside and outside the farm. Through the air flow unit, the manager can optimize the air flow within the fish farm and effectively block the inflow of external harmful substances. In addition, the air quality can be improved by identifying the installation locations of appropriate air filters inside and outside the farm through the air flow analysis unit (320). The air flow analysis unit (320) transmits the data analyzed from the air flow around the fish tanks in the fish farm to the data collection module (500).

[0041] Next, the robot control module (400) controls a robot that manages a fish farm. FIG. 6 is a configuration diagram of a robot control module (400) according to an embodiment of the present invention. Referring to FIG. 6, the robot control module (400) according to an embodiment of the present invention may be configured to include a robot reinforcement learning unit (410), a robot additional learning unit (420), and a robot data collection unit (430). Here, unlike the energy simulation module (200) and the fluid dynamics simulation module (300), the robot control module (400) controls a robot that manages an actual fish farm rather than a virtual simulation, and can be virtually tested through a digital twin for the test run of the robot.

[0042] The robot reinforcement learning unit (410) performs reinforcement learning to pre-learn the robot's movement path and the actions it must perform when managing the fish tanks in the aquaculture farm. The robot reinforcement learning unit (410) includes a function to create a reinforcement learning model to pre-learn the robot's movement path and the actions it must perform when managing the fish tanks in the indoor aquaculture farm. Through the robot reinforcement learning unit (410), the manager can perform pre-learning so that the robot can efficiently manage the aquaculture farm. By optimizing the robot's movement path and actions through reinforcement learning, the automation and efficiency of the aquaculture farm can be increased. Here, reinforcement learning refers to one of the methods of learning through trial and error. It is an algorithm in which the robot learns through mistakes and rewards to find the goal. Similar to how existing neural networks learn weights and biases through labeled data, it learns weights and biases using the concept of rewards. The purpose of reinforcement learning is to learn the optimal movement path and the actions it must perform when managing the fish tanks in the aquaculture farm.

[0043] The robot additional learning unit (420) generates additional learning information for the robot based on the robot's current state and feedback. The robot additional learning unit (420) generates additional learning information for the robot based on the robot's current state and feedback within the operating aquaculture farm. Through the robot additional learning unit (420), the manager can continuously improve the robot's performance by performing additional learning based on the robot's real-time feedback. The robot's state and feedback are monitored in real-time, and the reinforcement learning model is updated based on this to promote the efficient operation of the robot.

[0044] The robot data collection unit (430) collects data within the fish farm through the robot. The robot data collection unit (430) utilizes various data within the fish farm observed by the robot to supplement the fish farm production facilities. The robot data collection unit (430) is equipped with a sensor to measure data on the water quality of the tank and a camera to photograph the aquaculture species. The data collected by the robot data collection unit (430) is transmitted to the data collection module (500) and can be immediately utilized in the fish farm production facilities. Through the robot data collection unit (430), the manager can analyze the data collected by the robot and supplement the fish farm facilities based on this, and through the robot's data collection and analysis, increase the productivity of the fish farm and maximize operational efficiency.

[0045] The data collection module (500) collects data from the fish farm in real time. The data collection module (500) collects data on the total amount of electric energy generated from the power generation simulation unit (210), the total amount of electric energy used from the usage simulation unit (220), and the total energy cost from the cost prediction unit (230). Additionally, the data collection module (500) collects data on the simulated water flow and the amounts of replenishment water and discharge water from the water flow simulation unit (310), and collects data on the analysis of the air flow around the fish tank from the air flow analysis unit (320). Furthermore, the data collection module (500) collects various sensor data and images collected by the robot data collection unit (430). The data collection module (500) is equipped with memory for storing collected data, and the memory may include at least one type of storage medium among flash memory type, hard disk type, SSD type (Solid State Disk type), SSD type (Silicon Disk Drive type), multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (random access memory; RAM), SRAM (static random access memory), ROM (read-only memory; ROM), EEPROM (electrically erasable programmable read-only memory), PROM (programmable read-only memory), magnetic memory, magnetic disk, and optical disk. Additionally, the data collection module (500) may be operated in conjunction with web storage that performs the storage function of the memory on the internet.Additionally, the data collection module (500) transmits the relevant data to the data display unit (130) so that the collected data is displayed in the 3D virtual space unit (110).

[0046] The artificial intelligence analysis module (600) analyzes data collected from the data collection module (500). The artificial intelligence analysis module (600) analyzes data collected in real time from the data collection module (500) using artificial intelligence. The artificial intelligence analysis module (600) monitors electricity usage through simulated data from the energy simulation module (200) and can analyze points where differences occur by comparing the simulated data with the actual electricity usage of the fish farm. Additionally, the artificial intelligence analysis module (600) analyzes water flow and air flow data simulated through the fluid dynamics simulation module (300) to analyze the amount of replenishment water and discharge water and the air flow around the fish tanks of the fish farm. Furthermore, the artificial intelligence analysis module (600) analyzes sensor data and image data of the aquaculture species transmitted from the robot control module (400) to analyze the state of water quality and the state of the aquaculture species. The artificial intelligence analysis module (600) can use a machine learning model or a deep learning model as the artificial intelligence model, and can use supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning in combination.

[0047] The fish farm control module (700) controls the fish farm based on data analyzed by the artificial intelligence analysis module (600). When data is analyzed by the artificial intelligence analysis module (600), the fish farm control module (700) controls the devices, equipment, and robots of the fish farm based on the analyzed data. The content controlled by the fish farm control module (700) is displayed in real-time in the 3D virtual space section (110), allowing the manager to check the work being performed in the actual fish farm through the digital twin in the 3D virtual space section (110). Additionally, the fish farm control module (700) is equipped with a virtual reproduction section that inputs virtual data and reproduces it in the 3D virtual space section (110) through the digital twin. Through the virtual reproduction section, problems that may occur in the fish farm can be predicted by inputting virtual data in advance without relying on actual data. For example, problems occurring in the aquaculture species can be checked in real-time through the digital twin by inputting desired water quality data.

[0049] Hereinafter, a method of operation of a smart aquaculture system (10) using a digital twin according to an embodiment of the present invention will be described with reference to the drawings. FIG. 7 is a flowchart of a method of operation of a smart aquaculture system (10) using a digital twin according to an embodiment of the present invention. Referring to FIG. 7, the method of operation of a smart aquaculture system (10) using a digital twin according to an embodiment of the present invention may be configured to include the following six steps.

[0050] The first step (S10) is a step in which the fish farm is virtually reproduced and visualized by a digital twin. FIG. 8 is a flowchart of the detailed steps of the first step (S10) in a method for managing a fish farm using a smart aquaculture system (10) utilizing a digital twin according to an embodiment of the present invention. Referring to FIG. 8, the first step (S10) may be configured to include the following six steps.

[0051] First, Step 1-1 (S11) is a step in which information regarding the construction of a fish farm is input. In order to construct a digital twin of a fish farm, it must be implemented exactly like the actual fish farm, so information such as the size of the fish farm, the number of tanks, the size of the tanks, and the location of the tanks is input through an input device and reflected in the 3D model.

[0052] Step 1-2 (S12) is a step in which a 3D model of the fish farm is created. A 3D model of the fish farm is created by a 3D modeling program based on the information input in Step 1-1 (S11). In the present invention, a fish farm is implemented as a digital twin through 3D modeling and machine learning, and data is collected in real time and reflected so that the actual fish farm and the digital twin operate under the same conditions.

[0053] Step 1-3 (S13) is the step of placing equipment and devices in the fish farm. Once the fish farm and tanks are reflected in the 3D model at their locations, the number of fish farm equipment and devices, the size of the fish farm equipment and devices, and the location of the fish farm equipment and devices are entered to place the equipment and devices in the fish farm.

[0054] Step 1-4 (S14) is a step in which design information of the fish farm is stored. The design information data entered in Step 1-1 (S11) and Step 1-3 (S13) is stored in the design data storage unit of the pre-design unit (130).

[0055] Step 1-5 (S15) is a step in which data from the fish farm is linked. In this step, Step 3 (S30), Step 4 (S40), and Step 5 (S50) related to the fish farm are all linked and reflected in the fish farm digital twin. The data collection module (500) collects fish farm data from the energy simulation module (200), the fluid dynamics simulation module (300), and the robot control module (400). Here, the fish farm data includes data regarding the activity of aquaculture organisms, water quality status, fish farm equipment status, energy efficiency, toxicity concentration and flow of discharged and circulating water, water level information of the tank, and the current status and scheduling status of the robot.

[0056] Step 1-6 (S16) is a step in which the data from Step 1-5 (S51) is visualized in a 3D model of the fish farm. The fish farm data collected by the data collection module (500) is visualized and displayed in real-time in the 3D virtual space section (110) through the data display section (130).

[0057] Next, the second step (S20) is a step in which electrical energy generated and used in the aquaculture farm is simulated. FIG. 9 is a flowchart of the detailed steps of the second step (S20) in the operation method of a smart aquaculture system (10) using a digital twin according to an embodiment of the present invention. Referring to FIG. 9, the second step (S20) may be configured to include the following four steps.

[0058] Step 2-1 (S210) is a step in which the electrical energy produced from eco-friendly energy production devices installed in the fish farm and the amount of electricity used by the devices installed in the fish farm are collected. The amount of electricity generated from eco-friendly energy production devices, such as solar panels installed in the fish farm, and the amount of electricity used by the devices in the fish farm are collected.

[0059] Step 2-2 (S22) is the step in which the total electricity usage is simulated. The amount of electricity generated and the electricity usage collected in Step 2-1 (S21) are simulated.

[0060] Step 2-3 (S23) is the stage where the energy costs of the fish farm are predicted. By subtracting the amount of electricity generated from the amount of electricity consumed, the amount of electricity drawn from an external source at a cost can be calculated, thereby predicting the cost of electricity that must be paid for the operation of the fish farm.

[0061] Step 2-4 (S24) is a step in which efficient energy usage scheduling and the use of eco-friendly energy are recommended. If the cost predicted in Step 2-3 (S23) is excessive, the cost prediction unit (230) may schedule the usage time for efficient energy use to reduce energy consumption, and if more power generation is needed, may increase the amount of energy generated by adding an eco-friendly energy production device.

[0062] Next, the third step (S30) is a step in which the flow of water used in the aquaculture farm is simulated. FIG. 10 is a flowchart of the detailed steps of the third step (S30) in the operation method of a smart aquaculture system (10) using a digital twin according to an embodiment of the present invention. Referring to FIG. 10, the third step (S30) may be configured to include the following four steps.

[0063] Step 3-1 (S31) is the step in which water flow data for the pipelines and tanks of the fish farm is collected. It is the step in which data regarding the flow of water passing through the pipelines of the fish farm and the flow of water filling and discharging from the tanks is collected by the digital twin based on fluid dynamics.

[0064] Step 3-2 (S32) is a step in which the water flow rate for each device in the fish farm is simulated. The water flow rate used by the devices installed in the fish farm is simulated, allowing the actual amount of water used to be estimated.

[0065] Step 3-3 (S33) is the step in which the capacity of the replenishment water and discharge water of the fish farm is predicted. The capacity of water discharged from the fish farm and the capacity of water replenished to the fish farm can be predicted through the simulation of Step 3-2 (S32).

[0066] Step 3-4 (S34) is the stage where the operation of the filter and UV disinfection of the water are scheduled. Once the capacity of the replenishment water and discharge water of the aquaculture farm is predicted in Step 3-3 (S33), the filter is operated and UV disinfection is performed to filter the water replenishing the aquaculture farm, and the time and frequency of the filter operation and UV disinfection can be scheduled.

[0067] Next, the fourth step (S40) is a step in which the airflow used in the aquaculture farm is simulated. FIG. 11 is a flowchart of the detailed steps of the fourth step (S40) in the operation method of a smart aquaculture system (10) using a digital twin according to an embodiment of the present invention. Referring to FIG. 11, the fourth step (S40) may be configured to include the following four steps.

[0068] Step 4-1 (S41) is the step in which air flow data around the fish farm and tank is collected. It is the step in which data regarding the air flow around the fish farm and tank is collected by the digital twin based on fluid dynamics.

[0069] Step 4-2 (S42) is the step in which the movement of air is simulated. If data on air flow was collected in Step 4-1 (S41), the movement of air within the fish farm is simulated based on this data.

[0070] Step 4-3 (S43) is a step in which the timing of opening the air filter for external air ventilation is predicted. When a simulation of air movement is performed in Step 4-2 (S42), the timing for air ventilation is calculated, and thereby the timing of opening the air filter can be predicted.

[0071] Step 4-4 (S44) is the step in which the location of the air filter is set and air UV disinfection is scheduled. When a simulation of air movement is performed in Step 4-2 (S42), the location of the air filter can be set, and the timing and frequency of air UV disinfection required after external air ventilation can be scheduled.

[0072] In the present invention, the third step (S30) and the fourth step (S40) can be performed simultaneously. That is, the third step (S30) may be performed first and the fourth step (S40) may be performed, but it is preferable to perform the third step (S30) and the fourth step (S40) simultaneously so that the simulation of water and air can be performed simultaneously.

[0073] Next, the fifth step (S50) is a step in which data is collected and the robot is controlled by a robot used in the aquaculture farm. FIG. 12 is a flowchart of the detailed steps of the fifth step (S50) in the operation method of a smart aquaculture system (10) using a digital twin according to an embodiment of the present invention. Referring to FIG. 12, the fifth step (S50) may be configured to include the following five steps. In the present invention, the robot may move between the tanks of the aquaculture farm to measure water quality data of the tanks or take photographs of the aquaculture species.

[0074] Step 5-1 (S51) is a step in which digital twin data of the fish farm and data of the robot model are collected. In order for the robot to move and operate on the digital twin, the digital twin data of the fish farm and data of the robot model are collected and input through an input device.

[0075] Step 5-2 (S52) is the step in which the robot's movement path, management actions, and standby actions are set. The robot's movement path, management actions, and standby actions are set via an input device so that the robot can move between tanks in the aquaculture farm.

[0076] Stage 5-3 (S53) is the stage where digital twin-based reinforcement learning is implemented. Reinforcement learning by artificial intelligence is conducted to enable the robot to move between tanks and perform tasks. Reinforcement learning involves the robot observing the current situation within the fish farm and learning which action yields the greatest reward among the available choices, thereby training the robot to move along the optimal path and operate efficiently.

[0077] Step 5-4 (S54) is the stage where the robot's operation is tested. The robot, having completed reinforcement learning, is tested by being operated by a digital twin before actual operation.

[0078] Step 5-5 (S55) is a step in which the operation and movement of the robot, the movement of the robot's arm, and sensor data are transmitted in real time. The operation and movement of the robot and the movement of the robot's arm are measured in real time and transmitted to the robot additional learning unit (420) so that additional learning of the robot is performed. In addition, water quality data measured by the sensor equipped on the robot is transmitted in real time to the real-time data collection module (500). In addition, images of cultured species captured by the camera equipped on the robot are transmitted in real time to the data collection module (500).

[0079] Step 6 (S60) is a step in which simulation data and collected data are analyzed and the fish farm is controlled. The data collection module (500) collects fish farm data from the energy simulation module (200), the fluid dynamics simulation module (300), and the robot control module (400), and the collected data is analyzed by the artificial intelligence analysis module (600). After the data is analyzed, the fish farm control module (700) controls the devices, equipment, and robots of the fish farm based on the analyzed data.

[0081] The smart aquaculture system (10) using a digital twin of the present invention creates a digital twin in advance when designing an aquaculture farm, allowing the aquaculture farm to be operated through simulation in advance before operating the actual aquaculture farm, and thereby predicting problems or total costs that may occur during the operation of the aquaculture farm. In addition, if the smart aquaculture system (10) using a digital twin of the present invention is used in parallel with an actual aquaculture farm, there is an advantage in that a simulation is performed by the digital twin in advance before taking any measures to verify whether there are any problems, and then actual measures are taken.

[0083] The system described above may be implemented as a hardware component, a software component, and / or a combination of a hardware component and a software component. For example, the system and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are also possible.

[0084] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or command the processing unit independently or collectively. Software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0085] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiment, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

[0086] Although the embodiments have been described above with reference to limited examples and drawings, those skilled in the art can make various modifications and variations from the description above. For example, suitable results can be achieved even if the described techniques are performed in a different order than described, and / or the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0087] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below. Explanation of the symbols

[0088] 10: Smart Aquaculture System 100 : Digital Twin Visualization Module 110 : 3D virtual space section 120 : Pre-design department 130 : Data display section 200: Energy Simulation Module 210 : Power generation simulation section, 220 : Usage Simulation Section 230 : Cost Forecasting Section 300: Fluid Dynamics Simulation Module 310: Water Flow Simulation Section 320 : Airflow Analysis Unit 400: Robot Control Module 410 : Robot Reinforcement Learning Unit 420 : Robot additional learning unit 430 : Robot Data Collection Unit 500: Data Collection Module 600: Artificial Intelligence Analysis Module 700: Fish farm control module

Claims

Claim 1 A digital twin visualization module that virtually recreates the fish farm and visualizes it identically to the actual environment of the fish farm; an energy simulation module that simulates the amount of electrical energy generated in the fish farm and the amount of electricity used in the fish farm; a fluid dynamics simulation module that simulates the flow of fluids used in the fish farm; a robot control module that controls a robot managing the fish farm; a data collection module that collects data from the fish farm in real time; and an artificial intelligence analysis module that analyzes the data collected from the data collection module. and a fish farm control module in which the fish farm is controlled by data analyzed by the artificial intelligence analysis module; wherein the digital twin visualization module includes a 3D virtual space section in which the fish farm is implemented in 3D, a pre-design section for pre-designing the fish farm before actually constructing it, and a data display section that allows data collected by the data collection module to be displayed in real-time in the 3D virtual space section; wherein the energy simulation module includes a power generation simulation section in which the amount of electrical energy generated from eco-friendly energy production devices installed in the fish farm is simulated, a usage simulation section in which the amount of electricity used by devices installed in the fish farm is simulated, and a cost prediction section in which the cost of using electrical energy in the fish farm is predicted; wherein the fluid dynamics simulation module includes a water flow simulation section in which the flow of water used in the fish farm is simulated, and an air flow analysis section in which the flow of air used in the fish farm is analyzed; and wherein the robot control module includes a robot reinforcement learning section in which reinforcement learning is performed to pre-learn the robot's movement path and actions to be performed during tank management in the fish farm, a robot additional learning section in which additional learning information for the robot is generated based on the robot's current state and feedback, and robot data in which data within the fish farm is collected through the robot. It includes a collection unit, and the data collection module includes the total electric energy generation amount extracted from the cost prediction unit and the power generation simulation unit,The data on total electricity consumption and total energy costs extracted from the usage simulation unit is collected, and the data collection module collects data on the simulated water flow and the amounts of replenishment and discharge water from the water flow simulation unit. The data collection module collects data on the analysis of air flow around the fish tanks in the aquaculture farm from the air flow analysis unit. The data collection module collects various sensor data and images collected by the robot data collection unit. The data collection module transmits relevant data to the data display unit so that the collected data is displayed in the 3D virtual space. The artificial intelligence analysis module analyzes the data collected in real time from the data collection module using artificial intelligence. The artificial intelligence analysis module monitors electricity consumption through the simulated data from the energy simulation module and analyzes the points where discrepancies occur by comparing the simulation data with the actual electricity consumption of the aquaculture farm. The artificial intelligence analysis module analyzes the simulated water flow and air flow data through the fluid dynamics simulation module to analyze the amounts of replenishment and discharge water and the air flow around the fish tanks in the aquaculture farm. The artificial intelligence analysis module analyzes the sensor data and image data of the aquaculture species transmitted from the robot control module to analyze the state of water quality and the state of the aquaculture species. A smart aquaculture system using a digital twin, characterized by analyzing, and when data is analyzed by the artificial intelligence analysis module, the aquaculture control module controls the devices, equipment, and robots of the aquaculture farm based on the analyzed data. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 delete Claim 6 delete

Images