KR20210080773A - Deep learning system for control and operation of multiple mobile water quality improvement devices - Google Patents

Abstract

The present invention relates to a deep-learning system for controlling and operating a movable water quality improving device, capable of rapidly and effectively removing algae occurring in a water system, such as a river, a lake, or a dam. According to an embodiment of the present invention, the deep-learning system for controlling and operating a plurality of movable water quality improving device includes: a movable water quality improving device (10); and a deep learning device (20). A plurality of movable water quality improving devices (10) float in a fluid included in the algae, searches for a contaminated area of the fluid, and moves toward the contaminated area. The movable water quality improving devices (10) spread a coagulant for aggregating nanobubbles and the fluid of the contaminated area to lift the algae included in the contaminated area, and collect the coagulant and the lifted algae to purify the contaminated area. The deep learning device (20) includes a simulation unit (22) and an AI neural network unit (24). The simulation unit (22) provides a simulation for determining a moving path, an operating point, and an operating time of the movable water quality improving device (10). The AI neural network unit (24) determines that the water quality of the contaminated area is purified or deteriorated, based on an operating time of the movable water quality improving device (10) and the rate of purification of the contaminated area during the operating time. The AI neural network unit (24) reflects the moving path, the operating point, and the operating time of the movable water quality improving device (10) in the simulation, such that the water quality of the contaminated area is purified.

Description

Deep learning system for control and operation of multiple mobile water quality improvement devices

The present invention relates to a deep learning system for controlling and operating a plurality of mobile water quality improvement devices, and more particularly, to a mobile water quality improvement device capable of quickly and effectively removing algae generated in water systems such as rivers, lakes, and dams. It relates to a deep learning system for controlling and operating.

Water is an essential resource not only for mankind but also for all living things. In particular, rivers play a greater role than ever as a beautiful and pleasant resting place for leisure life in hot summer.

Green algae is a phenomenon in which green algae proliferate in large quantities mainly in summer and the color of the water changes to blue or green. Algae form the basis of the food chain as the primary producers of rivers and lakes ecosystems and are responsible for the energy cycle in the ecosystem. plays an important role. Phytoplankton living in a temperate climate with distinct four seasons, such as Korea, largely transitions according to seasonal changes such as water temperature and light intensity. In the case of cyanobacteria, dormant cells or dormant spores settle in the sedimentary layer in winter and remain dormant until the water temperature rises. exists as When the water temperature rises due to seasonal changes, the algae cells in the sedimentary layer grow into vegetative cells and float to the surface layer to form a phytoplankton community, which may also cause outbreaks depending on the conditions.

It is known that the reproduction of these algae is largely due to the inflow of nutrients such as nitrogen and phosphorus contained in artificially used fertilizers, domestic sewage, livestock wastewater, etc. into the water system.

Since most of the generated algae exist near the surface of the water system, it is difficult for sunlight to reach the water, and this phenomenon may cause photosynthesis inhibition of aquatic organisms and mass death of aquatic organisms. In addition, when algae proliferate in this way, there is a problem in that it is difficult to purify water due to toxins generated from these algae, and the purification cost is greatly increased.

In addition, it can act as a cause of lowering confidence in drinking water due to dissatisfaction of nearby residents due to the occurrence of taste and hobbies and anxiety that it may remain even after purification, so prevent the occurrence of algae in advance or remove the algae quickly. Therefore, there is an urgent need for a technology that can solve various problems caused by these algae.

Prior art document Korean Patent Publication No. 1436813 discloses a body, a floating body installed in the lower part of the body, a pressure pump installed in the body to suck in contaminated raw water such as a lake, a bubble refinement device connected to the pressure pump, and a bubble refinement device It is connected to and is installed in front of the front end of the floating body and includes an injection means for spraying contaminated water containing microbubbles flowing out from the bubble refiner, and the air inlet for introducing external air to the side of the bubble refiner is installed It is a tube-shaped flow tube that is installed inside the flow tube and consists of a fine filter with micropores, so it does not require a large-capacity air tank, so the weight is reduced, the mobility is improved, and the dewatering treatment for sludge is possible. have.

However, in the case of the ship described in the prior art, since the mesh-shaped conveyor belt that removes the algae lumps attached or combined with the coagulant and the microbubbles is located in close proximity to the partitioning device, a significant amount of algae can pass through the mesh-shaped conveyor belt. Passing through it can happen frequently. In addition, since the partitioning device is located in the front of the ship, the ship cannot move quickly, and there is a problem in that the safety of the ship is lowered because it depends only on a pair of fans during the movement or operation of the ship.

Furthermore, in the case of the ship described in the prior art, it would be preferable to operate one or more in plurality in order to improve the water quality of a wide area, but the control and operating system for controlling and operating the ship in plurality is not configured. However, there is also a problem that the safety of the control and operation of the ship is lowered.

Korean Patent Publication No. 1436813

The present invention has been devised to solve the above problems, and provides a deep learning system for controlling and operating a mobile water quality improvement device that can quickly and effectively remove algae generated in water systems such as rivers, lakes, dams, etc. there is a purpose to

In addition, the present invention performs deep learning learning through a data-based simulation collected from a mobile water quality improvement device operated in plurality in a water system in a wide area, and the mobile water quality improvement device moves through deep learning learning of an artificial neural network. It aims to provide a deep learning system for controlling and operating a mobile water quality improvement device that is controlled and operated based on the operation point and operating time.

On the other hand, the technical problems to be achieved in the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned are clearly to those of ordinary skill in the art to which the present invention belongs from the description below. can be understood

As a technical means for achieving the above object, a deep learning system for controlling and operating a plurality of mobile water quality improvement devices according to an embodiment of the present invention is a plurality of floating doedoe in a fluid containing algae, the contaminated area of the fluid A mobile type that searches for and moves toward the contaminated area, sprays nanobubbles to float the algae contained in the contaminated area and a coagulant to coagulate the fluid in the contaminated area, and collects the coagulant and the floating algae to purify the contaminated area. Water quality improvement device (10); and a simulation unit 22 that provides a simulation for determining the movement path, operation point, and operation time of the mobile water quality improvement device 10, and the operating time and operation time of the mobile water quality improvement device 10 in the simulation It is determined that the quality of the water in the contaminated area has been purified or deteriorated based on the purification rate of the contaminated area, and the movement path, operation point, and operation time of the portable water quality improvement device 10 to purify the water in the contaminated area are reflected in the simulation. It includes; a deep learning learning device 20 provided with an artificial neural network unit 24 .

And the deep learning learning device 20, the control unit 21 for receiving the collected data from the mobile water quality improvement device 10 through the network, and transmits the simulation data to the mobile water quality improvement device (10); and a labeling unit 23 that labels the operation time of the mobile water quality improvement device 10 in the simulation and the purification rate of the contaminated area during the operation time as purification or deterioration, and transmits the labeling to the artificial neural network unit 24; do.

In addition, the collected data includes first variable data including one of the algae of the fluid, the flow rate for each algae, the pollutant category, the polluted area, the temperature, and the influent material introduced into the fluid, and the speed of the mobile water quality improvement device 10 . and second variable data including one of the rotation directions and third variable data including one of a pollutant item and a purification rate of pollutants purified by the mobile water quality improvement device 10 .

The simulation unit 22 receives the collected data from the control unit 21 and corrects the simulation by reflecting the first, second, and third variable data included in the received collected data in the simulation.

In addition, the simulation data includes data on the movement path, operation point, and operation time of the mobile water quality improvement device 10 for purifying the water quality in the contaminated area.

And the artificial neural network unit 24 performs deep learning learning based on the purification labeling or deterioration labeling received from the labeling unit 23, and determines that the water quality of the contaminated area is purified through the purification labeling, and performs the deterioration labeling It is judged that the quality of the water in the contaminated area has deteriorated.

In addition, when the artificial neural network unit 24 determines that the water quality of the contaminated area has been purified based on the purification labeling, data on the movement path, operation point, and operation time of the portable water quality improvement device 10 is stored, The stored data is transmitted to the simulation unit 22 .

And the artificial neural network unit 24, while avoiding the movement path, the movable point, and the surrounding radius surrounding the movable point of the other movable water quality improvement device, the movement route and the movable point for purifying the contaminated area of the movable water quality improvement device (10) It can be set as a movement path and a moving point.

In addition, the artificial neural network unit 24 passes a part of the movement path of another mobile water quality improvement device at least once, but purifies the contaminated area while avoiding the moving point and the surrounding radius surrounding the moving point of the other mobile water quality improving device It is possible to set the moving path and the moving point to the moving path and the moving point of the mobile water quality improvement device (10).

And the artificial neural network unit 24 passes through the movable point and the peripheral radius surrounding the movable point of the other movable water quality improvement device at least once to purify the contaminated area while passing the movement path and the movable point of the movable water quality improvement device (10). It can be set as a movement path and a moving point.

In addition, when the artificial neural network unit 24 determines that the water quality in the contaminated area has deteriorated based on the deterioration labeling, the data on the movement path, operation point and operation time of the portable water quality improvement device 10 is corrected, The corrected data is transmitted to the simulation unit 22 .

Then, the simulation unit 22 corrects the simulation by reflecting the modified data-based simulation received from the artificial neural network unit 24 .

In addition, the labeling includes data on the area of the contaminated area in the simulation, the pollutant items, the algae of the fluid, and the flow rate by algae.

And the artificial neural network unit 24 performs deep learning learning based on the labeling received from the labeling unit 23, and the mobile water quality improvement device 10 through the deep learning learning of the contaminated area for searching the contaminated area. The determination criterion is stored, and the stored determination criterion of the contaminated area is transmitted to the simulation unit 22 .

In addition, the simulation unit 22 receives the determination standard of the contaminated area from the artificial neural network unit 24, and reflects the received determination standard of the contaminated area in the simulation to search for the contaminated area of the mobile water quality improvement device 10 simulation is provided.

According to an embodiment of the present invention, the artificial neural network unit deep-learning the movement path, operation point, operation time, and contamination area determination criteria of the mobile water quality improvement device, and reflecting the deep learning learning result in the mobile water quality improvement device, The improvement device can efficiently purify the water quality in the contaminated area.

And, according to an embodiment of the present invention, by performing deep learning learning so that the artificial neural network unit can control and operate a plurality of mobile water quality improvement devices, a plurality of mobile water quality improvement devices are installed on each movement path, operation point, and operation time. can be controlled and operated accordingly.

On the other hand, the effects obtainable in the present invention are not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by those of ordinary skill in the art to which the present invention belongs from the following description. will be able

1 is a schematic configuration diagram of a deep learning system for controlling and operating a plurality of mobile water quality improvement devices according to an embodiment of the present invention.
2 is a flowchart illustrating a deep learning simulation learning process of a deep learning learning apparatus according to an embodiment of the present invention.
3 to 5 are schematic diagrams showing the movement path and operation point setting process of the portable water quality improvement apparatus according to an embodiment of the present invention.
6 is a schematic diagram of a mobile water quality improvement device in accordance with an embodiment of the present invention viewed from above while moving.
7 is a schematic view of the mobile water quality improvement device shown in FIG. 6 as viewed from the side.
8 is a schematic view of the mobile water quality improvement apparatus shown in FIG. 6 as viewed from the front.
9 is a schematic view of the water quality improvement operation of the portable water quality improvement device according to an embodiment of the present invention as viewed from above.
FIG. 10 is an enlarged view of part A of FIG. 9 .

Hereinafter, with reference to the accompanying drawings, embodiments of the present invention will be described in detail so that those of ordinary skill in the art can easily carry out the present invention. However, since the description of the present invention is merely an embodiment for structural or functional description, the scope of the present invention should not be construed as being limited by the embodiment described in the text. That is, since the embodiment may have various changes and may have various forms, it should be understood that the scope of the present invention includes equivalents capable of realizing the technical idea. In addition, since the object or effect presented in the present invention does not mean that a specific embodiment should include all of them or only such effects, it should not be understood that the scope of the present invention is limited thereby.

The meaning of the terms described in the present invention should be understood as follows.

Terms such as “first” and “second” are for distinguishing one component from another, and the scope of rights should not be limited by these terms. For example, a first component may be termed a second component, and similarly, a second component may also be termed a first component. When a component is referred to as being “connected” to another component, it may be directly connected to the other component, but it should be understood that other components may exist in between. On the other hand, when it is mentioned that a certain element is "directly connected" to another element, it should be understood that the other element does not exist in the middle. Meanwhile, other expressions describing the relationship between elements, that is, “between” and “immediately between” or “neighboring to” and “directly adjacent to”, etc., should be interpreted similarly.

The singular expression is to be understood as including the plural expression unless the context clearly dictates otherwise, and terms such as "comprises" or "have" refer to the described feature, number, step, action, component, part or these It is intended to indicate that a combination exists, and it should be understood that it does not preclude the possibility of the existence or addition of one or more other features or numbers, steps, operations, components, parts, or combinations thereof.

All terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. Terms defined in the dictionary should be interpreted as being consistent with the meaning of the context of the related art, and cannot be interpreted as having an ideal or excessively formal meaning unless explicitly defined in the present invention.

Hereinafter, a deep learning system for controlling and operating a plurality of portable water quality improvement devices according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

1 is a schematic configuration diagram of a deep learning system for controlling and operating a plurality of mobile water quality improvement apparatuses according to an embodiment of the present invention, and FIG. 2 is a deep learning simulation learning of a deep learning learning apparatus according to an embodiment of the present invention. It is a flowchart showing the process, and FIGS. 3 to 5 are schematic diagrams showing the movement path and operation point setting process of the mobile water quality improvement apparatus according to an embodiment of the present invention, and FIG. 6 is a mobile water quality improvement apparatus according to an embodiment of the present invention is a schematic diagram viewed from the top while moving, FIG. 7 is a schematic diagram viewed from the side of the portable water quality improvement device shown in FIG. 6, and FIG. 8 is a schematic diagram viewed from the front of the portable water quality improvement device shown in FIG. 9 is a schematic view of the water quality improvement operation of the portable water quality improvement apparatus according to an embodiment of the present invention as viewed from above, and FIG. 10 is an enlarged view of part A of FIG. 9 .

Referring to FIG. 1 , a deep learning system for controlling and operating a plurality of mobile water quality improvement devices according to an embodiment of the present invention is configured to include a mobile water quality improvement device 10 and a deep learning learning device 20 .

The mobile water quality improvement apparatus 10 transmits the collected data including the variable data collected from the water system to the control unit 21 of the deep learning learning apparatus 20, and received from the control unit 21 of the deep learning learning apparatus 20 It is controlled and operated based on data on the movement route, operation point and operation time.

Here, the mobile water quality improvement device 10 may transmit/receive data to and from the deep learning learning device 20 through a network. However, the data transmission/reception means between the mobile water quality improvement device 10 and the deep learning learning device 20 is not limited to the network, and wireless means (eg, Wi-Fi, Bluetooth, Zigbee, etc.) or the mobile water quality improvement device 10 Since the deep learning learning device 20 is mounted, data transmission and reception may be possible through wired means (eg, a cable, an electrical connection circuit, etc.).

In addition, the mobile water quality improvement device 10 will preferably be provided with a collection means (eg, a sensor, not shown) for generating collection data to be transmitted to the control unit 21, and the collected data is a fluid algae, algae First variable data including star flow rate, pollutant items, temperature, and influent material items introduced into the fluid, second variable data including the speed and rotation direction of the mobile water quality improvement device 10, and the mobile water quality improvement device ( 10) may include a third variable data including a pollutant item purified by the method and a purification rate of the pollutant.

In addition, it is preferable that the portable water quality improvement device 10 is provided with a purification means (configuration of the portable water quality improvement device 10 to be described later) for purifying the water quality in the contaminated area.

The deep learning learning apparatus 20 is configured to include a control unit 21 , a simulation unit 22 , a labeling unit 23 , and an artificial neural network unit 24 .

The control unit 21 receives the collected data from the mobile water quality improvement device 10 , and transmits the collected data to the simulation unit 22 so that the simulation unit 22 reflects the collected data to be executed.

And the control unit 21 receives simulation data, which is the result data according to the simulation executed by the simulation unit 22, from the simulation unit 22, and transmits the received simulation data to the portable water quality improvement device 10 to improve the portable water quality. Let the device 10 be controlled and operated based on simulation data.

Here, the simulation data means data on the movement path, operation point, operation time, and pollution area determination criteria of the mobile water quality improvement device 10 for purifying the water quality of the contaminated area from the fluid (water system) including the contaminated area. .

Furthermore, the movement path is a path for the mobile water quality improvement device 10 to move to the contaminated area, and the movable point is a point at which the purification means of the portable water quality improvement device 10 is operated to purify the water quality in the contaminated area. It may be a point included in an area of the same area as or a contaminated area, and the operation time means the time (eg, 1 minute to 30 minutes) during which the purification means of the portable water quality improvement apparatus 10 is operated.

The simulation unit 22 performs a simulation to determine the movement path, operation point, and operation time of the mobile water quality improvement device 10 based on the collected data including the first, second, and third variable data received from the control unit 21 . run

Also, whenever the simulation unit 22 receives collected data from the controller 21 , the simulation unit 22 may correct the simulation settings (environment) by reflecting the received collected data in the simulation.

In addition, although not shown in the drawing, the simulation unit 22 implements a simulation space for a wide water system based on a geographic information system such as a Geographic Information System (GIS), and as properties of the simulation space, the flow of fluid, the flow rate of each current, Contaminant items, contaminant areas, temperatures, and influent materials entering the fluid can be simulated in the simulation space.

In addition, the simulation unit 22 can quantitatively simulate the speed and rotation direction of the mobile water quality improvement device 10 and the pollutant items and pollutant purification rate purified through the mobile water quality improvement device 10 in the simulation space. .

In addition, the simulation unit 22 may simulate the movement path, operation point, operation time, and contamination area determination criteria of one or more of the plurality of portable water quality improvement apparatuses 10 in the simulation space. This is to allow the artificial neural network unit 24 to perform deep learning learning based on the movement path, operation point, operation time, and pollution area determination criteria of the plurality of mobile water quality improvement devices 10 .

The labeling unit 23 receives the operation time and the pollution area purification rate during the operation time of the mobile water quality improvement device 10 in the simulation, and labels it as purification or deterioration based on the received operation time and the pollution area purification rate, The clean labeling or the worse labeling is transmitted to the artificial neural network unit 24 . In addition, the labeling unit 23 may label the clean labeling as (1, 0) and the worsening labeling as (0, 1) as an example.

In addition, the labeling unit 23 performs labeling including data on the area of the contaminated area in the simulation, the pollutant items, the algae of the fluid, and the flow rate for each algae. That is, the purification labeling and the deterioration labeling include data on the area of the contaminated area in the simulation, the pollutant item, the algae of the fluid, and the flow rate by algae, respectively.

At this time, the artificial neural network unit 24 stores the pollution area determination criteria for searching the contaminated area through data on the area of the contaminated area included in the labeling, the pollutant item, the algae of the fluid, and the flow rate for each algae, and then simulates sent to the unit 22 . In addition, the simulation unit 22 executes a simulation of the search for the contaminated area through the contaminated area determination standard.

The artificial neural network unit 24 performs deep learning learning to determine that the contaminated area is purified or deteriorated by the mobile water quality improvement device 10 in the simulation through the purification labeling or deterioration labeling received from the labeling unit 23, and , transmits to the simulation unit 22 the movement path, operation point, operation time, and criteria for determining the contaminated area of the mobile water quality improvement device 10 for purifying the water quality in the contaminated area.

At this time, the simulation unit 22 corrects the simulation settings by reflecting the judgment criteria of the movement path, the operation point, the operation time, and the contaminated area of the mobile water quality improvement apparatus 10 in the simulation.

A process in which the deep learning learning apparatus 20 including the above components performs deep learning simulation learning is as follows.

Referring to FIG. 2 , the simulation unit 22 executes a simulation, and the mobile water quality improvement apparatus 10 in the simulation searches for a contaminated area and, when the contaminated area is searched, moves toward the searched contaminated area (S10). ).

Here, the mobile water quality improvement apparatus 10 in the simulation is learned by the artificial neural network unit 24 and moves toward the contaminated area along the movement path set in the simulation.

Thereafter, the mobile water quality improvement device 10 in the simulation moves along the movement path, is located at the operation point, is operated during the operation time (S20), and purifies the water quality in the contaminated area (S30).

Here, the movable point of the mobile water quality improvement device 10 in the simulation means a point included in the contaminated area or an area having the same area as the contaminated area.

At this time, if the mobile water quality improvement device 10 in the simulation purifies the water quality of the contaminated area (S30-YES), the labeling unit 23 purifies the water quality of the contaminated area during the operation time and the contaminated area during the operation time The purification rate is labeled with purification labeling (S40).

Here, the criteria for judging whether the water quality of the polluted area is purified or deteriorated by the mobile water quality improvement device 10 may be the pollutant items purified by the mobile water quality improvement device 10 and the polluted zone purification rate, and the judgment subject is the simulation It may be the unit 22 or the artificial neural network unit 24 .

Furthermore, the purification rate of the polluted area means subtracting the total content of each pollutant item to be purified from the total content of the content of each pollutant item in the polluted area when the mobile water quality improvement device 10 is located from the operation point, and the measurement The unit may be measured and determined in percent (%).

Thereafter, the artificial neural network unit 24 determines that the water quality of the contaminated area has been purified through purification labeling (S50), and the movement path, the movable point, and the movable water quality improvement device 10 for purifying the water quality of the contaminated area. The data for the operation time and the contamination area determination criteria are stored (S60), and the data is transmitted to the simulation unit 22. At this time, the simulation unit 22 reflects the data stored in the artificial neural network unit 24 in the simulation to correct the simulation.

On the other hand, if the mobile water quality improvement device 10 in the simulation is operated during the operating time and the water quality in the contaminated area deteriorates (S30-NO), the labeling unit 23 purifies the contaminated area during the operation time and operation time (S30-NO) The rate is labeled as worsening labeling (S70).

After that, the artificial neural network unit 24 determines that the water quality of the contaminated area has deteriorated through the deterioration labeling (S80), and the movement path, the movable point, and the movable water quality improvement device 10 that causes the water quality of the contaminated area to deteriorate. The data on the operation time and the pollution area determination criteria are corrected so that the water quality of the contaminated area is purified ( S90 ), and the corrected data is transmitted to the simulation unit 22 . At this time, the simulation unit 22 corrects the simulation by reflecting the corrected data of the artificial neural network unit 24 in the simulation, and executes the corrected simulation.

Here, when the artificial neural network unit 24 corrects the data for the movement path, the operation point, the operation time, and the contamination area determination criterion of the mobile water quality improvement apparatus 10, it is preferable to correct at least one data of the items. .

On the other hand, among the data set by the artificial neural network unit 24 and provided through the simulation unit 22, the movement path and operation point of the portable water quality improvement device 10 may be set as shown in FIGS. 3 to 5 . have.

As shown in Figs. 3 to 5, the artificial neural network unit 24 is a moving path of the first mobile water quality improvement device 10a, the second mobile water quality improvement device 10b, and the third mobile water quality improvement device 10c. 241 and the movable point 243 can be set, respectively. However, the number of mobile water quality improvement devices in which the artificial neural network unit 24 sets the movement path and the operation point may be less or more than the above.

As a first method for setting the movement path 241 and the movable point 243 of the mobile water quality improvement device 10, the artificial neural network unit 24 is a first mobile water quality improvement device ( 10a) avoids the movement paths 241b and 241c, the movable points 243b, 243c, and the movable points 243b and 243c of the other movable water quality improvement devices 10b and 10c, and the peripheral radii 245b and 245c surrounding the movable points 243b and 243c. The moving path 241a and the movable point 243c of the first mobile water quality improvement device 10a may be set to purify the water quality in the contaminated area while doing so.

Here, the artificial neural network unit 24 sets the movement path 241 and the movable point 243 of the mobile water quality improvement apparatus 10 as in the setting method of the above example, thereby setting the movement path of the mobile water quality improvement apparatus 10 ( 241) can be prevented from being duplicated unnecessarily.

In addition, the peripheral radius 245 surrounds the movable point 243, and may form a relatively larger radius than the movable point, for example, 1 m to 10 m larger than the radius of the movable point. .

As a second method for setting the movement path 241 and the movable point 243 of the mobile water quality improvement device 10, the artificial neural network unit 24 is a first mobile water quality improvement device ( 10a) passes through a part of the movement paths 241b and 241c of the other portable water quality improvement devices 10b and 10c at least once, but the movable points 243b and 243c and the surrounding areas of the other movable water quality improvement devices 10b and 10c The moving path 241a and the movable point 243c of the first mobile water quality improvement apparatus 10a may be set to purify the water quality in the contaminated area while avoiding the radii 245b and 245c.

Here, the artificial neural network unit 24 sets the moving path 241 and the movable point 243 of the mobile water quality improvement device 10 as in the setting method of the other example, so that one mobile water quality improvement device 10 is changed to another. A part of the movement path 241 of the other portable water quality improvement apparatus 10 on which the portable water quality improvement apparatus 10 moves may be checked.

As a third method for setting the movement path 241 and the movable point 243 of the mobile water quality improvement device 10, the artificial neural network unit 24 is a first mobile water quality improvement device ( The first mobile water quality improvement device 10a so that the 10a) passes through the movable points 243b and 243c and the peripheral radius 245b and 245c of the other mobile water quality improvement devices 10b and 10c at least once to purify the water quality in the contaminated area. ) of the movement path 241a and the movable point 243c can be set.

Here, the artificial neural network unit 24 sets the movement path 241 and the movable point 243 of the mobile water quality improvement device 10 as in the setting method of the other example, so that one mobile water quality improvement device 10 is It is possible to check the operation point 243 of the other mobile water quality improvement device 10 whose water quality has been purified by the other mobile water quality improvement device 10 .

As such, the artificial neural network unit 24 adopts one of the setting methods of the movement path 241 and the movable point 243 to obtain the movement path 241 and the movable point of the mobile water quality improvement device 10 in the simulation ( 243), and may transmit it to the simulation unit 22 .

Furthermore, in the simulation, the artificial neural network unit 24 is operated at least once after the mobile water quality improvement device 10 is located at one movable point 243 to purify the water quality in the contaminated area, and the other movable point 243 ) to move along the movement path 241 and set the movement path 241 and the operation point 243 of the portable water quality improvement device 10 to purify the water quality of the contaminated area at another operation point 243 .

The mobile water quality improvement device 10 is a contaminated area (movable) based on the movement path, operation point, operation time, and determination criteria of the contaminated area included in the simulation data that the control unit 21 receives from the simulation unit 22 and then transmits. point), move to the contaminated area along the movement path, and operate the uptime purification means from the operation point to purify the water quality in the contaminated area.

6 to 9, the mobile water quality improvement device 10, the ship body portion 100 is a main floating body 110, a first auxiliary floating body 120, a second auxiliary floating body 130, Gateway 140, algae storage tank 150, air compression tank 160, coagulant tank 170, control unit 180, nano bubble generator 190, hopper 200, conveyor 210, guide 220 ) and a skimmer 230 .

The main floating body 110 is for floating various equipment such as the algae storage tank 150, the air compression tank 160, the coagulant tank 170 and the control unit 180 on the water, and consists of a pair having a rectangular shape. They are placed at a distance and spaced apart from each other. By arranging in this way, it is possible to secure the safety of the ship, and to form an inlet 111 and an outlet 112 through which a fluid containing algae can be introduced.

More specifically, since the pair of main floating bodies 110 are fixed at a certain distance as shown in FIG. 9 , one direction is the inlet 111 through which the fluid containing algae is introduced, the other direction. is an outlet 112 through which microbubbles, coagulants and cold air to be described later are discharged and a mass of algae forming a large colony is discharged. Here, the floating body 110 is not particularly limited as long as it can impart buoyancy, but is preferably a sealed metal strong against impact.

A plate-shaped gateway 140 may be further provided at the entrance 111 side. The gateway is for introducing or blocking the fluid into the inlet 111 and is provided in a pair of main floating bodies 110, respectively, and when the inlet 111 is blocked, the cross section viewed from above is a streamlined shape with a pointed end, and vice versa. When the (111) is opened, it is preferable that it can be opened at a predetermined angle.

Algae may occur only in some areas of the water body, but in most cases, they occur in large quantities in a large area, so after removing the current in a certain water area, it should be moved to a nearby water area promptly. However, the conventional vessel for removing algae does not have any special opening/closing means at the inlet where the fluid is introduced, so the introduced fluid continuously contacts the skimmer for collecting the algae and acts as a resistance, so there is a limit to increasing the moving speed of the vessel. have.

However, as shown in FIG. 6, the ship of the present invention minimizes the resistance of water by blocking the inlet 111 using the gateway 140 during movement, and opens the inlet 111 only when removing algae. Not only can the power required to move the machine can be reduced, but it can also be moved quickly.

Here, the gateway 140 is preferably opened and closed through the gateway opening and closing means 142 on one side of the pair of gateways 140 as shown in FIG. 10 .

It is more preferable to employ a structure that closes the skimmer 230 provided at the rear of the main floating body 110 in order to block the movement of the floating algae mass. That is, referring to FIGS. 6 to 9 , one end portion of a pair of skimmer 230 having a predetermined length is fixed at an appropriate position such as the main floating body 110 or a support plate 113 to be described later, and the other end portion is provided with a known fastening means capable of interconnecting or separating each of the pair of skimmers 230, and separates the pair of skimmers 230 from each other to minimize resistance when moving the ship, but when removing algae A pair of skimmers 230 are interconnected using a connecting means attached to the other end. In addition, it is more preferable to provide a skimmer lifting string 232 near the other end of the pair of skimmers 230 so that the separated pair of skimmers 230 can be easily fastened.

Here, the skimmer 230 is not particularly limited as long as it is a material that can float, but preferably has a predetermined height so that the algae mass floating near the water surface can be confined in a predetermined area, and flows freely from the flow of fluid, etc. It is more preferable that it is possible.

A support plate 113 for loading and fixing various devices may be provided on the upper portion of the pair of floating bodies 110 . The support plate 113 may use a perforated plate having a plurality of through holes or a mesh network having a predetermined strength.

On the other hand, in lakes and dams, relatively calm waves are common due to low flow rates, but in some areas of rivers, if the flow speed is high and the wind blows strongly due to sudden bad weather, there may be a risk of algae removal.

Since the ship of the present invention further includes a first auxiliary floating body 120 connected to the support plate 113, it is possible to improve the safety of the operation. Here, one side of the support 121 interconnecting the support plate 113 and the first auxiliary floating body 120 is rotatable with respect to the support plate 113, and a lifter 122 is provided at a predetermined position of the support plate 121. More may be provided.

8, when the length of the lifter 122 is shortened, the support 121 connected to the lifter 122 rotates with respect to the support plate 113. As a result, the support 121 ) The first auxiliary floating body 120 coupled to one end of the surface is moved above the water surface. As described above, in order for the vessel to move quickly, it is required to minimize the resistance of the fluid. The ship of the present invention is provided with a first auxiliary floating body 120 that can move vertically as described above, and when moving, by moving the auxiliary floating body 120 over the water surface, the resistance of the fluid due to the auxiliary floating body 120 can be minimized, and during the algae removal operation, the safety of the operation can be improved by contacting the auxiliary floating body 120 with the water surface. Of course, when the wind blows a lot or the flow speed is fast and the safety of the ship is required, it is obvious that safety can be secured by using the auxiliary floating body 120 even while moving.

Here, the configuration of adjusting the length of the lifter 122 or allowing one side of the support 121 to rotate is a well-known technique, so a detailed description will be omitted.

Each of the pair of main floaters 110 may further include second auxiliary floaters 130 spaced apart from each other by a predetermined interval.

To compensate for the load generated by the movement of the facility and the operator for removing the algae, it can be installed to be removable or vertically movable in the same way as the above-described auxiliary floating body 120 .

A coagulant tank 170 is provided at a predetermined position of the support plate 113 , and the coagulant tank 170 is connected to the coagulant spray nozzle 171 through a connection pipe (not shown). In addition, a nanobubble generator 190 for generating fine bubbles in water may be provided near the vessel inlet 111 . These configurations are to facilitate removal by floating the generated algae in a large mass.

Algae mainly inhabit near the water surface, where light passes well, but it is not easy to remove because the size is small and some algae are located somewhat below the water surface. Therefore, in the ship of the present invention, a coagulant is injected to float the algae by injecting fine air bubbles into the water so that the algae having these characteristics can be effectively removed.

6, 7 and 10 will be described in more detail, the nano-bubble generator 190 provided near the inlet 111 generates fine bubbles in the water to levitate the algae near the water surface, and the nano-bubble generator 190 ) From a plurality of coagulant injection nozzles 171 positioned at the rear, a coagulant mixture in which the coagulant supplied from the coagulant tank 170 and water from the water body are mixed is strongly sprayed.

Then, the algae floating near the surface of the water increase in volume due to the charge-and-load mechanism by the coagulant, and the buoyancy force acts as a force greater than gravity and rises to the surface.

Here, the nanobubble generator 190 is not particularly limited as long as it is a device that generates small bubbles having a size of several nanometers to several tens of nanometers, but is preferably an electrolysis device using electrodes.

The electrolysis device not only can agglomerate pollutants by supplying electricity to electrodes arranged at a predetermined interval, but also generate fine bubbles such as hydrogen or oxygen during the electrolysis of water, so a flotation effect and agglomeration effect can be expected. can On the other hand, since such an electrolysis device corresponds to a known technology, a detailed description thereof will be omitted.

In addition, as the coagulant used in the present invention, a known coagulant such as aluminum-based, iron-based, or polymeric coagulant may be used.

A compression tank 160 is provided on the support plate 113 , and the compression tank 160 is connected to a compressed air supply pipe 161 located behind the coagulant injection nozzle 171 . In addition, a vortex tube for generating cold air of 10° C. or less is further provided between the compression tank 160 and the compressed air supply pipe 161 .

A vortex tube is a tube that uses the principle that when compressed air is supplied to the vortex tube, it rotates at high speed in the vortex chamber, and cold air is discharged on one side and hot air is discharged on the other side. Since it corresponds to a technology applied in the field, a detailed description thereof will be omitted.

When cold air is injected into the water using the vortex tube as described above, the temperature of the water can be lowered to suppress the breeding of algae. In particular, it is possible to float the algae mass generated by the coagulant injection and the microbubble generator more quickly, as well as to float the fine algae mass that does not float properly, so that the algae is removed faster than the conventional vessel for removing algae. There are advantages to being able to

In this way, the algae mass floating due to the cold air supplied from the microbubbles, the coagulant and the vortex tube is discharged to the outlet 112 through the passage formed in the pair of main floaters 110, and the main float 110 is behind the The installed skimmer 230 blocks the algae mass from leaking to the outside.

In addition, the algae captured by the skimmer 230 is connected to the hopper 200, the conveyor 210, and the hopper 200 and the other end is stored in the algae via the algae transfer pipe 201 provided in the support plate 113. It is stored in the tank 150 .

Here, it is preferable to further include a support 202 that can fix the hopper 200 , the conveyor 210 and the transfer pipe 201 . In order to completely collect the algae captured by the skimmer 230, the hopper 200 and the conveyor 210 must be able to reach all areas partitioned by the skimmer 230, and since they are relatively heavy, There may be risks when moving.

However, as shown in FIGS. 6 and 9, in the present invention, a guide 220 capable of adjusting the length of the support 202 for fixing them is further provided on the support plate 113, so that the ship can move quickly. In addition, safe movement is possible.

On the other hand, when the generated current is widely distributed in the water body, it is preferable to further include an auxiliary gateway 141 as shown in FIG. 9 .

The auxiliary gateway 141 is preferably provided at the distal end of the gateway 140, and more preferably at least one detachable and foldable.

The detailed description of the preferred embodiments of the present invention disclosed as described above is provided to enable any person skilled in the art to make and practice the present invention. Although the above has been described with reference to preferred embodiments of the present invention, it will be understood by those skilled in the art that various modifications and changes can be made to the present invention without departing from the scope of the present invention. For example, a person skilled in the art may use each configuration described in the above-described embodiments in a way that is combined with each other. Accordingly, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

The present invention may be embodied in other specific forms without departing from the spirit and essential characteristics of the present invention. Accordingly, the above detailed description should not be construed as restrictive in all respects but as exemplary. The scope of the present invention should be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the present invention are included in the scope of the present invention. The present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein. In addition, claims that are not explicitly cited in the claims may be combined to form an embodiment, or may be included as new claims by amendment after filing.

10: portable water quality improvement device,
20: deep learning learning device,
21: control unit;
22: simulation unit;
23: labeling unit,
24: artificial neural network unit,
100: ship body portion,
110: main float,
111: entrance,
112: exit,
113: support plate,
120: a first auxiliary float,
121: support,
122: lifter,
130: a second auxiliary float,
140: gateway,
141: secondary gateway;
142 gateway opening and closing means;
150: algae storage tank,
160: air compression tank,
161: compressed air supply pipe,
170: flocculant tank,
171: spray nozzle,
180: control unit;
190: nanobubble generator,
200: Hopper,
201: bird feed tube,
202: support,
210: conveyor,
220: guide,
230: skimmer,
231: skimmer fastener,
232: skimmer lifting straps.

Claims (15)

A plurality of doedoe floating in the fluid containing algae, searching for the contaminated area of the fluid and moving toward the contaminated area, for flocculating the nanobubbles and the fluid in the contaminated area for floating the algae contained in the contaminated area a mobile water quality improvement device 10 for spraying a coagulant, collecting the coagulant and floating algae to purify the contaminated area; and
A simulation unit 22 that provides a simulation for determining the movement path, operation point, and operation time of the mobile water quality improvement device 10, and the operating time and the operating time of the mobile water quality improvement device 10 in the simulation Based on the purification rate of the contaminated area during the period, it is determined that the quality of the water in the contaminated area has been purified or deteriorated, and the movement path, operation point and operation time of the portable water quality improvement device 10 for purifying the water quality of the contaminated area A deep learning system for controlling and operating a plurality of mobile water quality improvement devices, characterized in that it includes; a deep learning learning device 20 provided with an artificial neural network unit 24 to be reflected in the simulation. The method of claim 1,
The deep learning learning device 20,
a control unit 21 that receives collected data from the mobile water quality improvement device 10 through a network and transmits the simulation data to the mobile water quality improvement device 10; and
Labeling unit 23 that labels the operation time of the mobile water quality improvement device 10 in the simulation and the purification rate of the contaminated area during the operation time as purification or deterioration, and transmits the labeling to the artificial neural network unit 24 A deep learning system for controlling and operating a plurality of mobile water quality improvement devices, comprising a. 3. The method of claim 2,
The collected data is
First variable data including one of the algae of the fluid, the flow rate for each algae, the pollutant category, the polluted area, the temperature, and the influent material introduced into the fluid, and the speed and rotation direction of the mobile water quality improvement device 10 A plurality of data characterized by including second variable data including one of the second variable data and third variable data including one of a pollutant item purified by the mobile water quality improvement device 10 and a purification rate of the pollutant A deep learning system for controlling and operating a mobile water quality improvement device. 4. The method of claim 3,
The simulation unit 22,
A plurality of mobile water quality improvement, characterized in that receiving the collected data from the control unit 21, and correcting the simulation by reflecting the first, second, and third variable data included in the received collected data to the simulation Deep learning systems for device control and operation. 3. The method of claim 2,
The simulation data is
A deep learning system for controlling and operating a plurality of mobile water quality improvement devices, characterized in that it includes data on the movement path, operation point, and operation time of the mobile water quality improvement device 10 for purifying the water quality in the contaminated area . 3. The method of claim 2,
The artificial neural network unit 24,
Deep learning learning is performed based on the purification labeling or deterioration labeling received from the labeling unit 23, it is determined that the water quality of the contaminated area is purified through the purification labeling, and the deterioration of the contaminated area is performed through the labeling. A deep learning system for controlling and operating a number of mobile water quality improvement devices, characterized in that it is determined that the water quality has deteriorated. 7. The method of claim 6,
The artificial neural network unit 24,
When it is determined that the water quality of the contaminated area is purified based on the purification labeling, data on the movement path, operation point, and operation time of the mobile water quality improvement device 10 are stored, and the stored data is used in the simulation unit (22) A deep learning system for controlling and operating a plurality of mobile water quality improvement devices, characterized in that it is transmitted to. 8. The method of claim 7,
The artificial neural network unit 24,
The movement path and operation point for purifying the contaminated area while avoiding the movement path, the operation point, and the peripheral radius surrounding the operation point of the other portable water quality improvement apparatus are the movement path and the operation point of the portable water quality improvement apparatus 10 A deep learning system for controlling and operating a number of mobile water quality improvement devices, characterized in that setting. 8. The method of claim 7,
The artificial neural network unit 24,
Pass a part of the movement path of another mobile water quality improvement device at least once, while avoiding the movable point of the other mobile water quality improvement device and the surrounding radius surrounding the movable point, the movement path and the movable point for purifying the contaminated area A deep learning system for controlling and operating a plurality of mobile water quality improvement devices, characterized in that it is set as a movement path and an operation point of the mobile water quality improvement device (10). 8. The method of claim 7,
The artificial neural network unit 24,
The moving path and the moving point for purifying the contaminated area while passing through the moving point of another mobile water quality improvement device and the peripheral radius surrounding the moving point at least once as the moving path and the moving point of the mobile water quality improvement device 10 A deep learning system for controlling and operating a number of mobile water quality improvement devices, characterized in that setting. 7. The method of claim 6,
The artificial neural network unit 24,
When it is determined that the quality of the water in the contaminated area has deteriorated based on the deterioration labeling, the data on the movement path, operation point, and operation time of the mobile water quality improvement device 10 are corrected, and the modified data is simulated A deep learning system for controlling and operating a plurality of mobile water quality improvement devices, characterized in that it is transmitted to the unit 22. 12. The method of claim 11,
The simulation unit 22,
A deep learning system for controlling and operating a plurality of mobile water quality improvement devices, characterized in that the simulation is corrected by reflecting the modified data-based simulation received from the artificial neural network unit (24). 3. The method of claim 2,
The labeling is
A deep learning system for controlling and operating a plurality of mobile water quality improvement devices, characterized in that it includes data on the area of the polluted area in the simulation, the pollutant items, the algae of the fluid, and the flow rate for each algae. 14. The method of claim 13,
The artificial neural network unit 24,
Perform deep learning learning based on the labeling received from the labeling unit 23, and through the deep learning learning, the mobile water quality improvement device 10 stores the determination criteria of the contaminated area for searching the contaminated area And, a deep learning system for controlling and operating a plurality of mobile water quality improvement devices, characterized in that transmitting the judgment criteria of the stored contaminated area to the simulation unit (22). 15. The method of claim 14,
The simulation unit 22,
Receives the determination criteria of the contaminated area from the artificial neural network unit 24, and reflects the received determination standard of the contaminated area in the simulation to provide a simulation of the search for the contaminated area of the mobile water quality improvement device 10 A deep learning system for controlling and operating a number of mobile water quality improvement devices, characterized in that.

Images