WO2023054834A1

WO2023054834A1 - Method and device for ai cluster-controlling mobile dof robot for water purification

Info

Publication number: WO2023054834A1
Application number: PCT/KR2022/007752
Authority: WO
Inventors: 김민환
Original assignee: 주식회사 캐스트
Priority date: 2021-10-01
Filing date: 2022-05-31
Publication date: 2023-04-06

Abstract

The present invention relates to a device for artificial intelligence-based cluster-controlling a mobile DOF robot for water purification. The device for AI cluster-controlling a mobile DOF robot for water purification may comprise: an acquisition unit for acquiring image water quality information collected from a drone; an analysis unit for analyzing the acquired image water quality information using a pre-trained neural network model; and a control unit for generating control signals for controlling the DOF robot, the control signals being generated on the basis of the analysis results. The DOF robot comprises: a water quality sensor for measuring the water quality where the DOF robot is located; a control unit for controlling the driving of the DOF robot by means of the generated control signals; and a micro-plasma generator which induces micro-discharges at atmospheric pressure by concentrating electromagnetic fields using micro-patterns and generates plasma by means of glow discharges.

Description

AI cluster control method and apparatus for mobile DOF robot for water purification

The present application relates to an AI group control method and apparatus of a mobile DOF robot for water purification.

Plasma created in an ultra-high temperature state generates highly reactive chemical species (radicals) in a completely dissociated molecule or incompletely ionized molecular state without a high gas temperature. Ozone is one of the active species produced by the reaction of chemical species generated in a plasma state based on oxygen. Ozone has strong sterilizing and oxidizing power, and is environmentally friendly because it oxidizes or sterilizes materials and is reduced to oxygen after the reaction.

In addition, the core of the microplasma technology is to minimize the two discharge spaces to a micro size to lower the breakdown voltage, and to concentrate the electromagnetic field using the micro pattern to induce the micro discharge at atmospheric pressure and generate the plasma as a glow discharge. As a result, electron density can be increased and miniaturized plasma is generated, thereby reducing power consumption and thereby increasing its efficiency. When oxygen and air are injected as a reaction gas using this principle, ozone is generated as an active species, and the generated ozone can be used for various purposes such as removing pests, decomposing odorous substances, and sterilizing harmful bacteria.

On the other hand, in the case of a medium or large reservoir, efficient water treatment is possible using a mobile DOF robot and its crowd control technology. Dissolved Gas Floating (DGF) or Dissolved AIr Floating (DAF) systems are used worldwide in a variety of applications. This process floats solids, oils and other contaminants to the liquid surface and removes physically separated contaminants. Oil and gas production facilities use DGF systems to remove oil and solids from produced and treated water (wastewater) for many years. DOF (Dissolved Ozone Flotation) technology is applied to the dissolved air flotation method along with replacement of supply gas by ozone instead of air to obtain better sterilization and water treatment results to DGF technology, and high efficiency by applying ozone's high sterilization and decomposability. It is a high skill to obtain. When the DOF method is applied, it is very effective in improving water quality and removing fine pollutants by ozone. The DOF method can also be applied in a variety of applications for the pretreatment of industrial wastewater, fracturing fluids, water containing algae, or for the final separation of wastewater and excess sludge from municipal wastewater treatment plants.

The background technology of the present application is disclosed in Korean Patent Publication No. 10-2005-0035780.

The purpose of the present invention is to solve the problems of the prior art described above, and to provide an AI group control apparatus and method of a mobile DOF robot for water purification based on microplasma AOP and ultrasonic inactivation technology.

However, the technical problem to be achieved by the embodiments of the present application is not limited to the technical problems described above, and other technical problems may exist.

As a technical means for achieving the above technical problem, an AI cluster control method of a mobile DOF robot for water quality purification according to an embodiment of the present application includes acquiring image water quality information collected from a drone, using a pre-learned neural network model analyzing the acquired image quality information; and generating a control signal for controlling the DOF robot based on the analysis result.

In addition, the analyzing step further includes inputting water quality measurement information collected by an external server to a pre-learned neural network model, and generating the control signal comprises using the pre-learned neural network model, The method may include generating a control signal corresponding to the image water quality information and the water quality measurement information.

In addition, the analyzing may include analyzing at least one state information of water quality temperature, oxidation-reduction potential (ORP), turbidity, and dissolved ozone concentration by applying the image water quality information and water quality measurement information to a pretrained neural network model. can

The method may further include a monitoring step for monitoring a water quality state, wherein the generating of the control signal corresponds to an analysis result in which first water quality state information among a plurality of water quality state information does not satisfy a preset condition as a result of the analysis. to generate a first control signal, and in the monitoring step, monitoring may be performed based on the image water quality information and water quality measurement information collected after a predetermined time period in which the DOF robot is driven by the first control signal.

In addition, the DOF robot uses a water quality sensor for measuring the state of water quality at which the DOF robot is located, a control unit for controlling driving of the DOF robot by the generated control signal, and a micro-pattern to concentrate an electromagnetic field and micro-discharge at normal pressure. It may include at least one of micro plasma generators for inducing and generating plasma as a glow discharge.

According to an embodiment of the present application, in the apparatus for cluster control of mobile DOF robots for water quality purification based on artificial intelligence, an acquisition unit for acquiring image water quality information collected from a drone, and the acquired image using a pre-learned neural network model It may include an analyzer that analyzes water quality information and a controller that generates a control signal for controlling the DOF robot based on the analysis result.

According to an embodiment of the present application, in a system for cluster control of mobile DOF robots for water purification based on artificial intelligence, control for controlling the DOF robot by analyzing image water quality information obtained from a drone using a pre-learned neural network model A device for generating a signal and a DOF robot that is driven based on a control signal provided from the device to perform water processing, wherein the device includes: an acquisition unit for acquiring image water quality information collected from the drone; It may include an analysis unit that analyzes the obtained image quality information using a neural network model, and a control unit that generates a control signal for controlling the DOF robot based on an analysis result.

The above-described problem solving means are merely exemplary and should not be construed as intended to limit the present disclosure. In addition to the exemplary embodiments described above, additional embodiments may exist in the drawings and detailed description of the invention.

According to the above-mentioned problem-solving means of the present application, efficient water treatment is possible through swarm robot control in medium-sized or large-sized reservoirs, and accurate water pollution status based on image processing using a water quality measurement sensor mid-drone that measures flow rate and flow rate And there is an effect of increasing the efficiency of controlling the water treatment robot by measuring the change in the concentration of contamination.

However, the effects obtainable herein are not limited to the effects described above, and other effects may exist.

1 is a schematic configuration diagram of an AI group control system of a mobile DOF robot for water purification according to an embodiment of the present invention.

2 is a schematic block diagram of an AI group control device of a mobile DOF robot for water purification according to an embodiment of the present invention.

3 is a schematic diagram of a DOF robot according to an embodiment of the present application.

4 is a schematic flowchart of an AI group control method of a mobile DOF robot for water purification according to an embodiment of the present invention.

Hereinafter, embodiments of the present application will be described in detail so that those skilled in the art can easily practice with reference to the accompanying drawings. However, the present disclosure may be implemented in many different forms and is not limited to the embodiments described herein. And in order to clearly describe the present application in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the present specification, when a part is said to be “connected” to another part, it is not only “directly connected”, but also “electrically connected” or “indirectly connected” with another element in between. ”Including cases where it is.

Throughout the present specification, when a member is referred to as being “on,” “above,” “on top of,” “below,” “below,” or “below” another member, this means that a member is located in relation to another member. This includes not only the case of contact but also the case of another member between the two members.

Throughout the present specification, when a certain component is said to "include", it means that it may further include other components without excluding other components unless otherwise stated.

The present application relates to an AI cluster control method of a mobile DOF robot for water purification based on microplasma AOP and ultrasonic inactivation technology. is possible, and the image process is performed using sensors and drones that measure the flow rate, flow rate, and water quality, thereby increasing the efficiency of water treatment robot control by measuring the exact water pollution status and change in pollution concentration.

Hereinafter, for convenience of description, the AI cluster control system 1 of the mobile DOF robot for water purification will be referred to as the present system 1, and the AI cluster control device 20 of the mobile DOF robot for water purification will be referred to as the present device 20. . In addition, for convenience of description, the mobile DOF robot 30 for water quality purification will be referred to as the robot 30 .

Referring to FIG. 1 , the present system 1 according to an embodiment of the present application may include a drone 10, the present device 20, and a robot 30, and the drone 10 and the present device 20 And the robot 30 may transmit and receive various communication signals through a network.

The system 1 according to an embodiment of the present application analyzes image water quality information obtained from a drone using a pre-learned neural network model to control the mobile DOF robot 30 for water quality purification based on artificial intelligence to control the DOF robot It may include a device 20 that generates a control signal for controlling the device 30 and a DOF robot 30 that performs water treatment by driving based on the control signal provided from the device 20 .

An example of a network for sharing information between the drone 10, the present device 20, and the robot 30 is a 3rd Generation Partnership Project (3GPP) network, a Long Term Evolution (LTE) network, a 5G network, and a World Interoperability for WIMAX (WIMAX) network. Microwave Access network, wired and wireless Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), Bluetooth network, Wifi network, A Near Field Communication (NFC) network, a satellite broadcasting network, an analog broadcasting network, a Digital Multimedia Broadcasting (DMB) network, and the like may be included, but are not limited thereto.

The drone 10 may be connected wirelessly or wired to the device 20 or a separate controller to receive location information of a destination. In addition, the drone 10 recognizes the current location using GPS, obtains route information from the current location to the destination using data of the map database, and then can fly while detecting the surrounding environment. For example, it may include an unmanned aerial vehicle, an unmanned aerial vehicle (UAV), and the like. In addition, the drone 10 may acquire a plurality of images and a plurality of water quality data by having one or more drones, but is not limited thereto.

The drone 10 may include a photographing device for photographing a place requiring water quality improvement (eg, a medium-sized or large-sized reservoir, dam, river, lake, and sea), and the drone 10 may include a mobile DOF robot for water quality purification. Image water quality information may be provided to the AI group control device 20 . In other words, the drone 10 including the photographing device can take images of medium-sized or large-sized reservoirs, dams, rivers, lakes, and seas, and transmit the captured images to the AI swarm control device 20 of the mobile DOF robot for water purification. can be sent to Here, the image water quality information includes an aerial image captured by the drone 10, location information of a place where the image was captured, temperature and humidity information of the location (eg, region), and altitude information of the drone 10 when the image was captured. may be included, but is not limited thereto.

The drone 10 may include a plurality of sensors such as a photographing device, an ultrasonic sensor, a gyro sensor, an acceleration sensor, a humidity sensor, a wind direction sensor, and a temperature sensor. For example, the drone 10 may include an ultrasonic sensor, an optical sensor, etc., but is not necessarily limited thereto, and may include an image sensor including known water quality data and an image sensor to be developed in the future. In addition, the image sensor may include a communication sensor in the form of wirelessly communicating with objects around the drone to check an identification number.

The AI swarm control device 20 of the mobile DOF robot for water purification may analyze water quality information based on the image and water quality data obtained from the drone 10 and control the DOF robot 30 based on the analysis result.

Referring to FIG. 2 , the device 20 may include an acquisition unit 21 , an analysis unit 220 , a control unit 23 and a monitoring unit 24 . According to one embodiment of the present application, the device 20 transmits and receives data and various communication signals with the drone 10 and the robot 30 through a network, and all kinds of servers, terminals, or device may be included. According to another embodiment of the present application, the device 20 may be provided by being embedded in the robot 30 to transmit and receive data and various communication signals to and from the drone 10 through a network, and to perform data storage and processing functions. Branches may include all types of servers, terminals or devices.

According to an embodiment of the present application, the acquisition unit 21 may acquire image quality information collected from the drone 10 . The acquisition unit 21 may acquire an image captured in the air from the drone 10 . The acquisition unit 210 may acquire and reconstruct image quality information. The acquisition unit 210 may obtain image water quality information and reconstruct information such as a water depth, a water supply line, and a direction of water flow in a photographed image to be displayed.

According to an embodiment of the present application, the analysis unit 22 may analyze image quality information obtained from the drone 10 by using a pretrained neural network model.

According to one embodiment of the present application, the analyzer 22 may input the water quality measurement information collected by the external server to a pretrained neural network model. Here, the water quality measurement information may be information obtained from a sensor provided in an external server (eg, a river or a reservoir). The water quality measurement information may be information obtained by measuring flow velocity and flow rate, but is not limited thereto.

According to an embodiment of the present disclosure, the analyzer 22 may derive an analysis result by applying image water quality information and water quality measurement information to a pre-learned neural network model. Analysis results include water temperature, oxidation reduction potential (ORP), turbidity, dissolved ozone concentration, information on pathogenic microorganisms, and information on harmful substances (chlorine, non-degradable organic substances, industrial chemicals, toxic chemicals, persistent organic substances, endocrine disruptors, etc.) , odor (smell) information, heavy metal and carcinogenic substance information, green algae information, etc., and may be a plurality of water quality state information, but the plurality of water quality state information is not limited thereto.

According to an embodiment of the present application, the analyzer 22 may analyze image water quality information and water quality measurement information based on a pretrained neural network model. For example, the neural network model may be applied to a convolutional neural network (CNN), but is not limited thereto, and an algorithm previously developed or developed in the future may be applied.

According to one embodiment of the present application, the control unit 23 may generate a control signal for controlling the robot 30 based on the analysis result.

The control unit 23 may generate a control signal for controlling the robot 30 corresponding to the image water quality information and the water quality measurement information by utilizing a pretrained neural network model.

As a result of the analysis, a first signal may be generated in response to an analysis result in which first water quality state information among a plurality of water quality state information does not satisfy a preset condition.

For example, when the pathogenic microorganism information, which is the first water quality state information among the plurality of water quality information, does not satisfy the preset pathogenic microorganism condition, the robot 30 sets the pathogenic microorganism information, which is the first water quality state information, to satisfy the preset pathogenic microorganism condition. ) can generate a control signal for driving. For example, the control unit 23 may generate a control signal for controlling the robot 30 to perform an advanced oxidation process (AOP). The Advanced Oxidation Process (AOP) is a chemical process used in water treatment or wastewater treatment, which uses a combination of ozone, ultraviolet (UV), and hydroproxide to remove highly reactive hydroxyl radicals (OH-Radical) and various active species. It may be a chemical oxidation process that creates and removes organic contaminants. In addition, the advanced oxidation process (AOP) may be performed in the micro plasma generator 33 of the robot 30 to be described later.

As another example, when the green algae information, which is second water quality state information, among the plurality of water quality information, does not satisfy a preset green algae information condition, the robot 30 is operated so that the green algae information, which is second water quality state information, satisfies the preset green algae information condition. A control signal for driving may be generated. For example, the controller 23 may generate a control signal for controlling the robot 30 to output inactive ultrasonic waves. In addition, the inactive ultrasound may be generated by the inactive ultrasound generator 34 of the robot 30 to be described later.

As another example, when the turbidity information, which is the third water quality state information among the plurality of water quality information, does not satisfy the preset turbidity information condition, the robot 30 sets the turbidity information, the third water quality state information, to satisfy the preset turbidity information condition. A control signal for driving may be generated. For example, the control unit 23 may generate a control signal for controlling the robot 30 to generate ozone. In addition, ozone may be generated in a Dissolved Ozone Flotation (DOF) 35 of the robot 30 to be described later.

The monitoring unit 24 according to an embodiment of the present application may monitor the state of water quality. The monitoring unit 24 may perform monitoring based on image water quality information and water quality measurement information collected after a predetermined period of time when the robot 30 is driven by the first control signal.

According to another embodiment of the present application, the monitoring unit 24 collects image water quality information and water quality measurement information after a predetermined period of time when the robot 30 is driven according to a control signal from the control unit 23, and thus the water quality derived as a result of the analysis. It may be determined whether the state information satisfies a preset condition.

Referring to FIG. 3 , the DOF robot 30 according to an embodiment of the present application includes a water quality sensor 31, a controller 32, a micro plasma generator 33, an inactive ultrasonic generator 34, and a DOF 35. can do.

The water quality sensor 31 according to an embodiment of the present application may measure the state of water quality where the DOF robot is located. The water quality sensor 31 may measure the state of water quality where the DOF robot 30 is located and obtain information on the water quality. Here, water quality information includes water temperature, oxidation-reduction potential (ORP), turbidity, dissolved ozone concentration, information on pathogenic microorganisms, harmful substances (chlorine, non-degradable organic substances, industrial chemicals, toxic chemicals, persistent organic substances, endocrine disrupting substances, etc.) ) information, odor (smell) information, heavy metal and carcinogenic substance information, green algae information, etc. may be included, but is not limited thereto.

The control unit 32 according to an embodiment of the present application may control driving of the DOF robot by a control signal generated by the device 20 .

The control unit 32 according to an embodiment of the present application may include an IOT control unit (not shown) and a battery unit (not shown). The IOT control unit may control driving of the DOF robot based on the control signal received through the network. For example, the IOT control unit may control driving of the micro plasma generator 33, the inactive ultrasonic generator 34, and the DOF 35 based on the control signal received through the network.

The micro-plasma generator 33 according to an embodiment of the present application may induce micro-discharge at atmospheric pressure by concentrating an electromagnetic field using a micro-pattern, and may generate plasma as a glow discharge.

The micro-plasma generator 33 according to an embodiment of the present application may induce micro-discharge at atmospheric pressure by concentrating an electromagnetic field using a micro-pattern, and may generate plasma as a glow discharge. The microplasma generator 33 according to an embodiment of the present application may perform an advanced oxidation process (AOP), that is, a cast microplasma AOP method according to a control signal received from the IOT controller. The cast microplasma AOP method generates a large amount of OH radicals that are fused and combined with ultraviolet (UV) and ozone (O₃), 　 sterilizes pathogenic microorganisms (e.g., bacteria, fungi, viruses, etc.) ) It can mean a chemical oxidation process that decomposes and removes substances and odors (odors).

The inactive ultrasonic generator 34 according to an embodiment of the present application can generate a constant pressure cycle around algae cells by emitting low-power ultrasonic waves, and naturally decompose toxins that interfere with the growth rhythm of algae and organics. The inactive ultrasonic generator 34 according to an embodiment of the present application may emit low-power ultrasonic waves according to a control signal received from the IOT control unit.

The DOF 35 according to an embodiment of the present application may remove contaminants through dissolved ozone flotation. The DOF 35 is capable of pre-treatment of industrial wastewater, fracturing fluids, water containing algae and final separation of wastewater and excess sludge by performing dissolved air flotation and replacement of feed gas by air versus ozone for disinfection and water treatment. can The DOF 35 according to an embodiment of the present application may perform the dissolved ozone flotation method according to the control signal received from the IOT control unit.

Hereinafter, based on the details described above, the operation flow of the present application will be briefly reviewed.

4 is an operation flowchart of an AI group control method of a mobile DOF robot for water purification according to an embodiment of the present invention. The AI group control method of the mobile DOF robot for water purification shown in FIG. 4 may be performed by the computing device 100 described above. Therefore, even if omitted below, the description of the computing device 100 can be equally applied to the description of the AI group control method of the mobile DOF robot for water purification.

In the above description, the AI crowd control method of the mobile DOF robot for water purification may be further divided into additional steps or combined into fewer steps according to an embodiment of the present invention. Also, some steps may be omitted if necessary, and the order of steps may be changed.

A method for cluster control of mobile DOF robots for water quality purification based on artificial intelligence according to an embodiment of the present application includes the steps of acquiring image water quality information collected from a drone, and using a pre-learned neural network model to obtain the obtained image water quality information. The step of analyzing and generating a control signal for controlling the DOF robot based on the analysis result may be included.

In addition, the analyzing step further includes inputting water quality measurement information collected by an external server into a pre-learned neural network model, and generating a control signal includes image water quality information using the pre-learned neural network model. and generating a control signal corresponding to the water quality measurement information.

In addition, in the analysis step, at least one state information of water quality temperature, oxidation-reduction potential (ORP), turbidity, and dissolved ozone concentration may be analyzed by applying the image water quality information and water quality measurement information to a pretrained neural network model. .

In addition, a monitoring step for monitoring the water quality state may be further included, and the step of generating the control signal may include generating the control signal in response to an analysis result in which the first water quality state information among the plurality of water quality state information does not satisfy a preset condition as a result of the analysis. In the step of generating 1 control signal and monitoring, monitoring may be performed based on image water quality information and water quality measurement information collected after a predetermined time when the DOF robot is driven by the first control signal.

The AI group control method of the mobile DOF robot for water purification according to an embodiment of the present application may be implemented in the form of program commands 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. alone or in combination. Program instructions recorded on the medium may be those specially designed and configured for the present invention or those known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to act as one or more software modules to perform the operations of the present invention, and vice versa.

In addition, the above-described AI group control method of the mobile DOF robot for water purification may be implemented in the form of a computer program or application stored in a recording medium and executed by a computer.

The above description of the present application is for illustrative purposes, and those skilled in the art will understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present application. Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present application is indicated by the following claims rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and equivalent concepts thereof should be construed as being included in the scope of the present application.

Claims

A method for group control of a mobile DOF robot for water purification based on artificial intelligence,

Acquiring image water quality information collected from a drone;

analyzing the acquired image quality information using a pretrained neural network model; and

An AI group control method of a mobile DOF robot for water purification, comprising: generating a control signal for controlling the DOF robot based on the analysis result.
According to claim 1,

The analyzing step further includes inputting water quality measurement information collected by an external server to a pre-learned neural network model,

The generating of the control signal includes generating a control signal corresponding to the image water quality information and the water quality measurement information by utilizing the pretrained neural network model,

The analysis step is

AI group control of a mobile DOF robot for water purification that analyzes at least one state information among water temperature, oxidation-reduction potential (ORP), turbidity, and dissolved ozone concentration by applying the image water quality information and water quality measurement information to a pre-learned neural network model method.
According to claim 2,

Further comprising a monitoring step for monitoring the water quality condition,

Generating the control signal,

As a result of the analysis, a first control signal is generated in response to an analysis result in which first water quality state information among a plurality of water quality state information does not satisfy a preset condition;

The monitoring step is

AI cluster control method of a mobile DOF robot for water quality purification that performs monitoring based on the image water quality information and water quality measurement information collected after a predetermined time when the DOF robot is driven by the first control signal.
According to claim 1,

The DOF robot,

A water quality sensor for measuring the state of water quality where the DOF robot is located;

a control unit controlling driving of the DOF robot by the generated control signal; and

An AI group control method of a mobile DOF robot for water purification including a micro plasma generator that induces micro discharge at normal pressure by concentrating an electromagnetic field using a micro pattern and generates a glow discharge plasma.
A device for group control of a mobile DOF robot for water purification based on artificial intelligence,

an acquisition unit that acquires image quality information collected from the drone;

an analysis unit that analyzes the obtained image quality information by using a pretrained neural network model; and

An AI group control device for a mobile DOF robot for water purification, including a control unit that generates a control signal for controlling the DOF robot based on the analysis result.