KR102488182B1 - Unattended station monitoring system using machine learning and operation method thereof - Google Patents

Abstract

Various embodiments of the present disclosure relate to an unmanned substation monitoring system and an operating method thereof, and the unmanned substation monitoring system may include a monitoring device and a monitoring server. The monitoring device may include a radar sensor and a thermal imaging camera. The monitoring server includes a communication circuit, a memory, and a processor connected to the communication circuit and the memory. Detects an intruder trespassing into the unmanned substation without permission, transmits a control signal for adjusting the angle of the thermal imaging camera based on the moving line of the intruder to the thermal imaging camera through the communication circuit, and communicates with the intruder An image of an associated thermal imaging camera may be stored in the memory. Other embodiments are also possible.

Description

Unmanned substation monitoring system using machine learning and its operation method {UNATTENDED STATION MONITORING SYSTEM USING MACHINE LEARNING AND OPERATION METHOD THEREOF}

Various embodiments of the present invention relate to an unmanned substation monitoring system using machine learning and an operation method thereof.

Substations are installed for voltage or current transformation and power distribution in the process of sending power generated by power plants to consumers through transmission lines or distribution lines, and are facilities that supply appropriate power to each load using special high-voltage power. can include For example, a substation may include facilities such as transformers, disconnectors, circuit breakers, ancestor facilities, lightning arresters, and switchboards. When an abnormality occurs in such a substation, consumers may experience serious inconvenience, and if prompt measures are not taken, a major accident or fire may occur. Therefore, a monitoring solution for detecting an abnormal state of a substation may be required.

The background art of the present invention is disclosed in Korean Patent Registration No. 10-1008956 (registered on January 11, 2011, substation monitoring system using color information for each system facility).

Various embodiments of the present disclosure disclose a method and apparatus for detecting an abnormal situation in an unmanned substation using a thermal imaging camera and a radar sensor.

A monitoring server according to various embodiments of the present disclosure includes a communication circuit, a memory, and a processor connected to the communication circuit and the memory, wherein the processor includes at least one of a radar sensor and a thermal imaging camera disposed around an unmanned substation Detects an intruder trespassing into an unmanned substation based on information obtained through the communication circuit and transmits a control signal for adjusting the angle of the thermal imaging camera based on the moving line of the intruder. and may store an image of a thermal imaging camera associated with the intruder in the memory.

According to various embodiments, the processor identifies information about an object around the unmanned substation based on information obtained through at least one of the radar sensor and the thermal imaging camera, and based on the information about the object At least one of a moving distance and a moving speed of the object may be identified, and when at least one of the moving distance and the moving speed does not satisfy a specified condition, the object may be filtered.

According to various embodiments, as at least part of the operation of detecting the intruder, the processor obtains information about an object through the radar sensor, and uses a database pre-stored in the memory to obtain information about the object. By performing machine learning, an intruder intruding into the unmanned substation without permission is detected, and the information about the object includes at least some of the location information of the object, the size information of the object, and the moving speed information of the object. can include

According to various embodiments of the present disclosure, as at least part of the operation of detecting the intruder, the processor acquires a thermal image through the thermal imaging camera, and uses a database pre-stored in the memory to obtain a thermal image as a machine for the thermal image. By performing running, an intruder entering the unattended substation without permission may be detected.

According to various embodiments, as at least part of the operation of detecting the intruder, the processor obtains information on objects around the unmanned substation through the radar sensor and obtains a thermal image through the thermal imaging camera. In addition, by performing machine learning on information about the object and the thermal image using a database pre-stored in the memory, an intruder entering the unmanned substation without permission may be detected.

According to various embodiments, the monitoring server further includes an output device, and the processor, in response to detecting the intruder, through the output device so that a manager of the monitoring server can recognize the intruder. Guidance information indicating that an intruder is detected may be output to the unmanned substation.

According to various embodiments, the processor, in response to detecting the intruder, guide information indicating that an intruder is detected in the unmanned substation through the communication circuit so that the administrator of the monitoring server can recognize the intruder It can be transmitted to the portable terminal of the manager.

A monitoring server according to various embodiments of the present disclosure includes a communication circuit, a memory, and a processor connected to the communication circuit and the memory, wherein the processor includes a first image received through a thermal imaging camera disposed around an unmanned substation. The temperature of the unmanned substation is identified based on the thermal image, and when it is identified that the temperature of at least some zones of the unmanned substation is equal to or higher than the reference temperature, the angle of the thermal imaging camera is adjusted based on the location of the at least some zones. transmits a control signal to the thermal imaging camera through the communication circuit, receives a second thermal image through the thermal imaging camera whose angle is adjusted, and uses a database pre-stored in the memory to generate the second thermal image; By performing machine learning on the video image, it is possible to detect a fire occurring in the at least part of the area.

According to various embodiments of the present disclosure, the processor may store the second thermal image in the memory in response to detecting a fire in the unmanned substation.

According to various embodiments, the processor may further include an output device, in response to detecting a fire in the unmanned substation, so that a manager of the monitoring server can recognize the occurrence of a fire, the unmanned substation through the output device. Information indicating that a fire has occurred in a substation can be output.

According to various embodiments, the processor, in response to detecting a fire in the unmanned substation, detects that a fire has occurred in the unmanned substation through the communication circuit so that the manager of the monitoring server can recognize the occurrence of a fire. The indicated information may be transmitted to the portable terminal of the manager.

Various embodiments of the present invention can minimize damage to an unmanned substation caused by an intruder or fire by detecting an unauthorized intruder entering the unmanned substation or detecting a fire in the unmanned substation using a thermal imaging camera and a radar sensor. .

1 is a block diagram of an unmanned substation monitoring system according to various embodiments.
2 is an exemplary diagram illustrating the arrangement of a thermal imaging camera and a radar sensor in an unmanned substation monitoring system according to various embodiments.
3 is a block diagram of a monitoring server according to various embodiments.
4 is a flowchart illustrating a method of detecting an intruder trespassing into an unmanned substation in a monitoring server according to various embodiments.
5 is a flowchart illustrating a method of detecting a fire in an unmanned substation in a monitoring server according to various embodiments of the present disclosure.

Hereinafter, a system for detecting a disconnection of a distribution line according to the present invention and an operation method thereof will be described with reference to the accompanying drawings.

In this process, the thickness of lines or the size of components shown in the drawings may be exaggerated for clarity and convenience of explanation. In addition, terms to be described later are terms defined in consideration of functions in the present invention, which may vary according to the intention or custom of a user or operator. Therefore, definitions of these terms will have to be made based on the content throughout this specification.

Examples and terms used therein are not intended to limit the technology described in this document to specific embodiments, and should be understood to include various modifications, equivalents, and/or substitutes of the embodiments. In connection with the description of the drawings, like reference numerals may be used for like elements. Singular expressions may include plural expressions unless the context clearly dictates otherwise. In this document, expressions such as "A or B" or "at least one of A and/or B" may include all possible combinations of the items listed together. Expressions such as "first", "second", "first", or "second" may modify the elements in any order or importance and may be used to distinguish one element from another. but not limited to those components. When a (e.g., first) element is referred to as being "(functionally or communicatively) coupled to" or "connected to" another (e.g., second) element, that element refers to the other (e.g., second) element. It may be directly connected to the component or connected through another component (eg, a third component).

In this document, "configured (or configured to)" means "suitable for", "having the ability to", "changed to" depending on the situation, for example, hardware or software ", "made to", "capable of", or "designed to" can be used interchangeably. In some contexts, the expression "device configured to" can mean that the device is "capable of" in conjunction with other devices or components. For example, the phrase "a processor configured (or configured) to perform A, B, and C" may include a dedicated processor (eg, an embedded processor) to perform those operations, or by executing one or more software programs stored in a memory device. , may mean a general-purpose processor (eg, CPU or application processor) capable of performing corresponding operations.

1 is a block diagram of an unmanned substation monitoring system according to various embodiments.

Referring to FIG. 1 , an unmanned substation monitoring system 100 may include a monitoring device 110 and a monitoring server 120 .

According to various embodiments, the monitoring device 110 is disposed around the unmanned substation and may detect an intruder trespassing into the unmanned substation or obtain information for identifying an abnormal state such as a fire. For example, the monitoring device 110 may detect an intruder trespassing into an unmanned substation through the radar sensor 111 and the thermal imaging camera 113 or obtain information for identifying an abnormal condition such as a fire. . When information is obtained, the monitoring device 110 may provide the obtained information to the monitoring server 120 periodically, non-periodically, or in real time. According to an embodiment, the radar sensor 111 is installed around the unmanned substation, emits electromagnetic waves in a designated direction, and receives electromagnetic waves reflected from objects to detect objects around the unmanned substation. For example, the radar sensor 111 may obtain information about the location (eg, coordinates) of an object around the unmanned substation, the size of the object, and the moving speed of the object. According to an embodiment, the thermal imaging camera 113 is installed around the unmanned substation and may obtain a thermal image around the unmanned substation.

According to various embodiments, the monitoring server 120 may identify an intruder trespassing into an unmanned substation based on information provided from the monitoring device 110 . For example, when information is received from at least one of the radar sensor 111 and the thermal imaging camera 113 installed around the unmanned substation, the monitoring server 120 performs machine learning on the received data based on a pre-stored database ( By performing machine learning, it may be determined whether an object detected by at least some of the radar sensor 111 and the thermal imaging camera 113 is an intruder trespassing into the unmanned substation. When an object detected by at least some of the radar sensor 111 and the thermal imaging camera 113 is an intruder trespassing into an unmanned substation, the monitoring server 120 provides related information (eg, the radar sensor 111 and/or thermal imaging camera 113). Information obtained from the image camera 113) may be stored, and an angle of the thermal image camera 113 may be adjusted based on a movement line of an object determined to be an intruder. According to an embodiment, when the monitoring server 120 identifies an intruder in the unmanned substation, the manager of the monitoring server 120 may provide information indicating that an intruder occurs in the unmanned substation. For example, the monitoring server 120 may output information indicating that an intruder occurs in an unmanned substation through an output device. For another example, the monitoring server 120 may transmit information indicating that an intruder occurs in an unmanned substation to a manager's portable terminal.

According to various embodiments, the monitoring server 120 may identify a fire occurring in an unmanned substation based on information provided from the monitoring device 110 . For example, when a thermal image is received from the thermal imaging camera 113 installed around the unmanned substation, the monitoring server 120 determines whether the temperature of at least a part of the unmanned substation is equal to or higher than a reference temperature based on the thermal image. When the temperature of at least some zones of the substation is higher than the reference temperature and a temperature change (eg, increase) is continuously detected, it may be determined that a fire has occurred in the corresponding zone. According to an embodiment, when the monitoring server 120 detects a fire in an unmanned substation, by continuously tracking the temperature change of the unmanned substation, the monitoring server 120 identifies the path of the fire, and transmits information on the identified fire path to the monitoring server. (120) can be provided to the manager. For example, the monitoring server 120 may output information on a path of a fire through an output device or transmit information on a path of a fire to a portable terminal of a manager. According to an embodiment, when detecting a fire in an unmanned substation, the monitoring server 120 may provide information indicating that a fire occurs in an unmanned substation to a manager. For example, the monitoring server 120 may output information indicating that a fire occurs in an unmanned substation through an output device or transmit information indicating that a fire occurs in an unmanned substation to a manager's portable terminal.

As described above, the unmanned substation monitoring system 100 uses the information obtained through the monitoring device 110 to detect an intruder trespassing into the unmanned substation or detects a fire occurring in the unmanned substation and guides the manager by However, damage to unmanned substations by intruders or fire can be minimized.

2 is an exemplary diagram illustrating the arrangement of a thermal imaging camera and a radar sensor in an unmanned substation monitoring system according to various embodiments.

Referring to FIG. 2 , a plurality of thermal imaging cameras 211, 213, 215, and 217 and a plurality of radar sensors 221, 223, 225, and 227 may be disposed around a substation 201 (or an unmanned substation). there is.

According to various embodiments, the plurality of thermal imaging cameras 211 , 213 , 215 , and 217 may be disposed to photograph the substation 201 and the surroundings of the substation 201 . According to an embodiment, hardware specifications (eg, angle of view) of each of the plurality of thermal imaging cameras 211, 213, 215, and 217 may be the same or not the same. According to an embodiment, while the plurality of thermal imaging cameras 221, 213, 215, and 217 are operating, the substation 201 and the surroundings of the substation 201 are photographed, and the captured thermal images are periodically It can be transmitted periodically or in real time to the monitoring server (eg, monitoring server 120 of FIG. 2 ). In this case, the monitoring server may detect an intruder trespassing into the substation 201 or a fire occurring in the substation 201 by using the thermal image transmitted from the thermal imaging camera.

According to various embodiments, angles of the plurality of thermal imaging cameras 211, 213, 215, and 217 may be adjusted according to control of the monitoring server. For example, when the monitoring server detects an intruder trespassing into the substation 201 based on thermal images obtained through at least some thermal imaging cameras among the plurality of thermal imaging cameras 211, 213, 215, and 217. , the angle of some thermal imaging cameras can be adjusted to track trespassers under the control of the monitoring server. For another example, when the monitoring server detects a fire in the substation 201 based on thermal images obtained through at least some of the plurality of thermal imaging cameras 211, 213, 215, and 217, the monitoring Under the control of the server, the angle of some thermal imaging cameras can be adjusted to track the path of the fire.

According to various embodiments, the plurality of radar sensors 221 , 223 , 225 , and 227 may be disposed to detect the substation 201 and objects around the substation 201 . According to an embodiment, hardware specifications (eg, object detection distance) of each of the plurality of radar sensors 221, 223, 225, and 227 may or may not be the same. According to an embodiment, the plurality of radar sensors 221, 223, 225, and 227 detect the substation 201 and objects around the substation 201 while operating, and information on the detected objects (eg, location ( For example, coordinates), size of an object, and moving speed of an object) may be transmitted to the monitoring server periodically, aperiodically, or in real time. In this case, the monitoring server may detect an intruder trespassing into the substation 201 without permission by using the thermal image transmitted from the thermal imaging camera.

As described above, the monitoring device proposed in the present invention is disposed around the substation 201 and can be used to detect an intruder trespassing into the substation 201 or a fire occurring in the substation 201. Information (eg thermal imagery or radar information) can be provided to the monitoring server.

3 is a block diagram of a monitoring server according to various embodiments.

Referring to FIG. 3 , the monitoring server 120 may include a processor 121, a memory 123, an input device 125, an output device 127, and a communication circuit 129. According to one embodiment, the monitoring server 120 does not include at least some of the above-described components (eg, the input device 125 or the output device 127), or additional components other than the above-described components are further added. may also include

According to various embodiments, the processor 121 may execute software to control at least one other component (eg, hardware or software component) of the monitoring server 120 connected to the processor 121, and may control various data Can perform processing or calculation. According to one embodiment, as at least part of data processing or operation, the processor 121 transfers instructions or data received from other components (e.g., input device 125) or communication circuitry 129 to memory 123. , process commands or data stored in the memory 123, and store resultant data in the memory 123. According to one embodiment, the processor 121 may include a main processor (eg, a central processing unit or an application processor), and a secondary processor (eg, a graphic processing unit, an image signal processor, a sensor hub processor, or communication processor). Additionally or alternatively, the secondary processor may be configured to use less power than the main processor or to be specialized for a designated function. A secondary processor may be implemented separately from, or as part of, the main processor.

According to various embodiments, the processor 121 may obtain information for detecting an intruder trespassing into an unmanned substation from the monitoring device 110 . For example, the processor 121 obtains information (eg, location, size, movement speed, etc.) of objects around the unmanned substation from the radar sensor 111 disposed around the unmanned substation through the communication circuit 129. can do. For another example, the processor 121 may acquire a thermal image of the unmanned substation and its surroundings from the thermal imaging camera 113 disposed around the unmanned substation through the communication circuit 129 .

According to various embodiments, the processor 121 may detect an intruder unauthorizedly intruding into an unmanned substation based on information obtained from the monitoring device 110 . For example, when information on objects around the unmanned substation is obtained from the radar sensor 111, the processor 121 performs machine learning on the acquired information using a database pre-stored in the memory 123, thereby It is possible to determine whether an object sensed through the sensor 111 is an intruder. For another example, when an unmanned substation and a thermal image photographed around the unmanned substation are obtained from the thermal imaging camera 113, the processor 121 uses a database pre-stored in the memory 123 to generate a machine for the thermal image. By performing the running, it is possible to determine whether an object included in the thermal image is an intruder. In the case of objects (e.g. trees) around the unmanned substation, the movement displacement is limited, in the case of the manager (or non-intruder) of the unmanned substation, the movement path (or behavior pattern) is fixed, and in the case of the intruder of the unmanned substation, Since the movement path is not fixed (or is different from the above-described behavior pattern), the processor 121 may determine whether or not an intruder is present using machine learning in consideration of this. According to an embodiment, the processor 121 may determine whether to filter the object based on at least one of a moving distance and a moving speed of the object. For example, when information about an object is acquired through the radar sensor 111, the processor 121 identifies a moving distance and a moving speed of the object based on the information about the object, and the moving distance of the object is less than or equal to the reference distance. , and if the moving speed of the object is less than or equal to the reference speed, the object may be regarded as an object irrelevant to the intruder (eg, a swaying tree or an animal), and the object may be filtered (or the object may be determined not to be detected). . For another example, the processor 121 analyzes the thermal image obtained through the thermal imaging camera 113 to identify the moving distance and moving speed of the object, and if the moving distance of the object is less than or equal to the reference distance, the object If the movement speed is less than or equal to the reference speed, the corresponding object may be regarded as an object irrelevant to the intruder (eg, a swaying tree or an animal), and the object may be filtered (or the object may be determined not to be detected).

According to various embodiments, the processor 121 may adjust the angle of the thermal imaging camera 113 in response to detecting an intruder trespassing into the unmanned substation. For example, when the processor 121 detects an intruder using information obtained from at least one of the radar sensor 111 and the thermal imaging camera 113, the processor 121 continuously captures (or tracks) a thermal image of the intruder. A control signal for adjusting the angle of the thermal imaging camera 113 may be transmitted to the thermal imaging camera 113 through the communication circuit 129 in consideration of the movement line of the intruder. According to an embodiment, while the processor 121 is tracking an intruder through a specific thermal imaging camera among a plurality of thermal imaging cameras disposed in an unmanned substation, when the intruder moves to an area that cannot be photographed through the specific thermal imaging camera, Other thermal imaging cameras can be used to continuously track intruders. For example, when an intruder being photographed by a specific thermal imaging camera moves to a location that cannot be captured by the specific thermal imaging camera, the processor 121 determines the location (or coordinates) of the last captured intruder at the unmanned substation. At least one thermal imaging camera capable of photographing an intruder may be determined among a plurality of thermal imaging cameras disposed around, and the intruder may be continuously tracked using the determined at least one thermal imaging camera. According to an embodiment, while tracking an intruder through the thermal imaging camera 113, the processor 121 uses the radar sensor 111 even if the intruder moves to a location that cannot be captured by the thermal imaging camera 113. Thus, the intruder's location can be continuously tracked.

According to various embodiments, the processor 121 may store a thermal image captured by the intruder in the memory 123 in response to detecting an intruder trespassing into the unmanned substation without permission. These thermal images can be used as evidence in the future. According to an embodiment, the processor 121 may store the thermal image and at the same time provide the manager of the monitoring server 120 with information indicating that an intruder trespassing into the unmanned substation is detected. For example, the processor 121 may output information indicating that an intruder who trespasses into an unattended substation without permission is detected through the output device 127 . For another example, the processor 121 transmits information indicating that an intruder who has trespassed into an unmanned substation without permission is detected with a preset portable terminal (eg, a portable terminal of a manager of the monitoring server 120) through the communication circuit 129. can be sent

According to various embodiments, the processor 121 may obtain information for detecting a fire in an unmanned substation from the monitoring device 110 . For example, the processor 121 may obtain a thermal image of the unmanned substation and its surroundings from the thermal imaging camera 113 disposed around the unmanned substation through the communication circuit 129 .

According to various embodiments, the processor 121 may detect a fire in an unmanned substation based on information obtained from the monitoring device 110 . For example, when a thermal image of the unmanned substation and its surroundings is obtained from the thermal imaging camera 113, the processor 121 analyzes the obtained image, so that the temperature of at least a part of the unmanned substation is the reference temperature. It is determined whether or not the temperature is abnormal, and if the temperature of at least some zones of the unmanned substation is higher than the reference temperature, a control signal for adjusting the angle of the thermal imaging camera 113 is transmitted to the thermal imaging camera 113 in order to intensively check the corresponding zone. It is possible to determine whether or not a fire has occurred in the area by transmitting and analyzing again the thermal image obtained through the thermal imaging camera 113 whose angle is adjusted. According to an embodiment, the processor 121 may determine whether a fire has occurred by performing machine learning on the thermal image using a database pre-stored in the memory 123 . According to an embodiment, the processor 121 may identify a fire occurrence path based on a temperature change of areas of an unmanned substation identified from a thermal image. According to an embodiment, the processor 121 may improve the accuracy of the machine learning algorithm by continuously learning images captured through the thermal imaging camera 113. For example, regardless of whether an intruder is detected, the processor 121 transmits information on the type of object (eg, human or animal) and intrusion type in the thermal image obtained from the thermal imaging camera 113 to the corresponding thermal image. The accuracy of the machine learning algorithm may be improved by tagging the image and performing learning through the thermal image including the tagging information. Here, the information tagged to the thermal image may be generated based on information input from a manager or automatically based on information identified by the processor 121 through a machine learning process.

According to various embodiments, the processor 121 may store a thermal image in which a fire is detected in the memory 123 in response to detecting a fire in an unmanned substation. These thermal images can be used as data to identify the fire path in the future. According to an embodiment, the processor 121 may store the thermal image and provide information indicating that a fire occurs in an unmanned substation to a manager of the monitoring server 120 at the same time. For example, the processor 121 may output information indicating that a fire occurs in an unmanned substation through the output device 127 . For another example, the processor 121 may transmit information indicating that a fire occurs in an unmanned substation to a predetermined portable terminal (eg, a portable terminal of a manager of the monitoring server 120) through the communication circuit 129. there is.

According to various embodiments, the processor 121 may parallelly perform a process for detecting an intruder entering an unattended substation and a process for detecting a fire in an unattended substation.

According to various embodiments, the memory 123 may store various data used by at least one component (eg, the processor 121) of the monitoring server 120. Data may include, for example, input data or output data for software and related instructions. The memory 123 may include volatile memory and/or non-volatile memory.

According to various embodiments, the input device 125 may receive a command or data to be used for a component (eg, the processor 121) of the monitoring server 120 from the outside of the monitoring server 120 (eg, a manager) there is. The input device 125 may include, for example, a microphone, mouse, keyboard, or digital pen (eg, a stylus pen).

According to various embodiments, the output device 127 may visually provide information to the outside of the monitoring server 120 (eg, a manager). The output device 117 may include, for example, a display, a hologram device, or a projector and a control circuit for controlling the device. According to an embodiment, the output device 127 may include a touch circuitry set to detect a touch or a sensor circuit (eg, a pressure sensor) set to measure the intensity of force generated by the touch. there is.

According to various embodiments, the output device 127 may output a sound signal to the outside of the monitoring server 120 (eg, a manager). The output device 127 may include, for example, a speaker.

According to various embodiments, the communication circuit 129 establishes a direct (eg, wired) communication channel or a wireless communication channel between the monitoring server 200 and an external electronic device (eg, the monitoring device 110), and the established communication Communication through a channel may be supported. The communication circuit 129 may include one or more communication processors that operate independently of the processor 121 (eg, an application processor) and support direct (eg, wired) communication or wireless communication. According to an embodiment, the communication circuit 129 may be a wireless communication module (eg, a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (eg, a local area network (LAN)). ) communication module, or power line communication module).

4 is a flowchart illustrating a method of detecting an intruder trespassing into an unmanned substation in a monitoring server according to various embodiments.

Referring to FIG. 4 , in operation 401, a processor (eg, processor 121 of FIG. 3 ) of a monitoring server (eg, monitoring server 120 of FIGS. 1 and 3 ) is a radar sensor (eg, radar of FIG. 1 ). sensor 111 or the radar sensor 221, 223, 225, or 227 of FIG. 2 and a thermal imaging camera (e.g., the thermal imaging camera 113 of FIG. 1 or the thermal imaging camera 211, 213, 215 of FIG. 2) , or 217)), an intruder intruding into an unmanned substation without permission may be detected (or detected) based on the information acquired through at least one of 217)). For example, the processor 121 identifies at least some of a change in position, size, and moving speed of an object located around an unmanned substation based on information obtained from the racer sensor 111, and performs machine learning on the identified information. By performing, it is possible to identify that the object detected through the radar sensor 111 is an intruder trespassing into the unmanned substation without permission. As another example, the processor 121 acquires a thermal image of an object located around an unmanned substation based on a thermal imaging camera, and performs machine learning on the obtained thermal image, so that the information contained in the thermal image is included in the thermal image. It is possible to identify an object as an intruder entering an unmanned substation without permission. As another example, the processor 121 comprehensively uses information obtained from the radar sensor 111 and the thermal imaging camera 113 and includes the information acquired from the radar sensor 111 and the thermal imaging camera 113. It is possible to identify the object as an intruder entering the unmanned substation without permission. According to an embodiment, the processor 121 may filter the identified object by considering at least one of a moving distance and a moving speed of the object. For example, when an object is detected through the radar sensor 111 or the thermal imaging camera, the processor 121 identifies at least one of a moving distance and a moving speed of the object, and determines that the identified moving distance of the object is equal to or less than the reference distance. , If the moving speed of the identified object is less than or equal to the reference speed, the object may be filtered (or ignored).

In operation 403, the processor 121 may adjust the angle of the thermal imaging camera 113 based on the moving line of the intruder in response to detecting the intruder. For example, when an intruder is detected through at least one of the radar sensor 111 and the thermal imaging camera 113, the processor 121 identifies the movement line of the detected intruder, and identifies the intruder as the thermal imaging camera 113. A control signal for adjusting an angle of the thermal imaging camera 113 based on the identified moving line may be transmitted to the thermal imaging camera 113 through the communication circuit 129. According to an embodiment, when there are a plurality of thermal imaging cameras capable of tracking an intruder, the processor 121 adjusts all angles of the plurality of thermal imaging cameras or selects one of the thermal imaging cameras closest to the intruder. Only the angle of the visual camera can be adjusted. According to an embodiment, the processor 121 may adjust magnification (eg, enlargement or reduction) as well as an angle of the thermal imaging camera 113 . For example, the processor 121 identifies a distance between the intruder and the thermal imaging camera 113 based on the location of the intruder, and sends a control signal for adjusting magnification of the thermal imaging camera 113 based on the identified distance. The generated control signal may be transmitted to the thermal imaging camera 113 together with a control signal for adjusting an angle of the thermal imaging camera 113 . According to an embodiment, while tracking an intruder through a specific thermal imaging camera among a plurality of thermal imaging cameras provided in an unmanned substation, a location where the intruder cannot be photographed through a specific thermal imaging camera (eg, behind a building or a tree) When moving to , the processor 121 may keep track of the intruder using another thermal imaging camera capable of capturing the intruder. According to an embodiment, the processor 121 may output a warning broadcast through an output device disposed around the unmanned substation in response to detection of an intruder approaching the unmanned substation. For example, the processor 121 determines at least one output device disposed close to an intruder among a plurality of output devices (eg, displays or speakers) disposed around a substation, and transmits a warning broadcast to the determined output device. can do. For another example, the processor 121 may output a warning broadcast to a plurality of output devices disposed around the substation.

In operation 405 , the processor 121 may store an image of a thermal imaging camera associated with the intruder in the memory 123 . For example, the processor 121 may track an intruder and store a captured thermal image in the memory 123 . According to an embodiment, the processor 121 stores the thermal image in the memory 123 (or before, or simultaneously with the storage) and informs the manager of the monitoring server 120 that an unauthorized intrusion into an unmanned substation occurs. It can provide information indicating that an intruder has been detected. For example, the processor 121 outputs information indicating that an intruder who has trespassed into the unattended substation without permission has been detected through the output device 127, or through the communication circuit 129, the processor 121 outputs information indicating that an intruder has been detected. Information indicating that an intruder has been detected may be transmitted.

As described above, the monitoring server 120 detects an intruder trespassing into the unattended substation and informs the administrator of the intruder, thereby preventing an accident caused by the intruder from occurring in the unattended substation. In addition, as the thermal image captured by the intruder is stored, it can be used as evidence later.

5 is a flowchart illustrating a method of detecting a fire in an unmanned substation in a monitoring server according to various embodiments of the present disclosure.

Referring to FIG. 5 , in operation 501, a processor (eg, the processor 121 of FIG. 3 ) of a monitoring server (eg, the monitoring server 120 of FIGS. 1 and 3 ) sends a thermal image camera (eg, the monitoring server 120 of FIG. 1 ). Based on the information obtained through the thermal imaging camera 113, a temperature change of at least some areas of the substation (or unmanned substation) may be identified. For example, when a thermal image is received from the thermal imaging camera 113, the processor 121 may continuously identify temperatures of unmanned substation areas by analyzing the received thermal image.

In operation 503, the processor 121 may adjust the angle of the thermal imaging camera. For example, when the processor 121 identifies that the temperature of at least some zones of the unmanned substation is higher than the reference temperature, the thermal imaging camera 113 capable of capturing the corresponding zone in order to intensively acquire thermal images of the corresponding zone A control signal for adjusting the angle of may be transmitted to the corresponding thermal imaging camera 113 through the communication circuit 129 . According to an embodiment, when there are a plurality of thermal imaging cameras 113 capable of capturing an area with a temperature higher than a reference temperature, the processor 121 adjusts the angles of all of the thermal imaging cameras or selects one of the thermal imaging cameras for imaging. You can only adjust the angle of the one thermal imaging camera that is easiest (i.e. closest to the area). According to an embodiment, the processor 121 may also adjust the magnification as well as the angle of the thermal imaging camera 113 . For example, the processor 121 identifies a distance between the intruder and the thermal imaging camera 113 based on the location of the intruder, and generates a control signal for adjusting magnification of the thermal imaging camera 113 based on the identified distance. And, the generated control signal may be transmitted to the thermal imaging camera 113 together with the control signal for adjusting the angle.

In operation 505, the processor 121 may detect a fire based on information acquired through the thermal imaging camera 113 whose angle is adjusted. For example, when a thermal image is acquired through the thermal imaging camera 113 whose angle is adjusted, the processor 121 performs machine learning on the acquired thermal image using a database pre-stored in the memory 123. By doing so, it is possible to determine whether a fire has occurred in the area captured by the thermal image.

In operation 507, the processor 121 may store a thermal image associated with the fire in the memory 123 in response to detecting the fire. For example, the processor 121 may store a thermal image in which a fire is detected in the memory 123 . According to an embodiment, the processor 121 continuously acquires and analyzes thermal images using the thermal imaging camera 113 even after detecting a fire, thereby analyzing the path of the fire and determining the path of the analyzed fire. Information can be provided to the manager of the monitoring server 120 . According to an embodiment, after the processor 121 stores the thermal image in the memory 123 (or before, or simultaneously with the storage), the manager of the monitoring server 120 causes a fire in the unmanned substation. can provide information indicating For example, the processor 121 outputs information indicating that a fire has occurred in an unmanned substation through the output device 127 or reports that a fire has occurred in an unmanned substation through a portable terminal of a manager through a communication circuit 129. information can be transmitted.

As described above, the monitoring server 120 detects the occurrence of a fire in an unmanned substation and guides the manager to prevent the fire in the unmanned substation from spreading.

The term "module" used in this document may include a unit implemented by hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit, for example. A module may be an integrally constructed component or a minimal unit of components or a portion thereof that performs one or more functions. For example, according to one embodiment, the module may be implemented in the form of an application-specific integrated circuit (ASIC).

According to various embodiments, each component (eg, module or program) of the components described above may include a singular object or a plurality of entities. According to various embodiments, one or more components or operations among the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (eg modules or programs) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by a corresponding component of the plurality of components prior to the integration. . According to various embodiments, operations performed by modules, programs, or other components are executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations are executed in a different order, omitted, or , or one or more other operations may be added.

100: unmanned substation monitoring system
110: monitoring device
111: radar sensor
113: thermal imaging camera
120: monitoring server

Claims (11)

In the monitoring server, the monitoring server,
communication circuit;
Memory;
output device; and
Based on information acquired through a radar sensor and a plurality of thermal imaging cameras connected to the communication circuit and the memory and disposed around the unmanned substation, information on an object around the unmanned substation is obtained, and the plurality of columns Obtaining a thermal image through a visual camera and performing machine learning on information on the object using a database pre-stored in the memory to identify information on an object around the unmanned substation; Based on the information on the object, a change in location, size, moving distance, and moving speed of the object are identified, an intruder trespassing into the unmanned substation without permission is detected, and an intruder intruding into the unmanned substation is detected, and an occurrence in some area is detected through the plurality of thermal imaging cameras. a processor that detects fire; including,
the processor,
If the moving distance of the object is less than or equal to the reference distance and the moving speed of the object is less than or equal to the reference speed, the object is determined to be an object unrelated to the intruder and filtered;
Based on the moving line of the intruder, a control signal for adjusting the angle of one of the thermal imaging cameras adjacent to the location of the intruder among the plurality of thermal imaging cameras is generated and a control signal for adjusting the magnification of the thermal imaging camera generated and transmitted to the thermal imaging camera through the communication circuit;
Based on the position of the intruder, a distance between the intruder and the thermal imaging camera is identified, a control signal for adjusting the magnification of the thermal imaging camera is generated based on the identified distance, and the generated control signal is converted into the thermal imaging camera. Transmitting to the thermal imaging camera together with a control signal for adjusting the angle of the camera,
While tracking an intruder through a specific thermal imaging camera among the plurality of thermal imaging cameras, when the intruder moves to an area that cannot be captured by the specific thermal imaging camera, the plurality of thermal images are obtained based on the location of the intruder captured last. Among the cameras, a thermal imaging camera capable of capturing an intruder is determined, the determined thermal imaging camera is used to continuously track the intruder, and when the intruder moves to a location where the thermal imaging camera cannot capture the intruder, the radar sensor is used. to continuously track the intruder's location,
Information on the type of object and intrusion type of the thermal image is tagged on the thermal image to perform machine learning on the thermal image including the tagging information based on a database pre-stored in the memory. By performing, detecting an intruder unauthorizedly entering the unmanned substation,
the processor,
Identifying the temperature of the unmanned substation based on a first thermal image received through the plurality of thermal imaging cameras disposed around the unmanned substation;
When it is identified that the temperature of some zones of the unmanned substation is equal to or higher than the reference temperature, a control signal for adjusting the angle of a first thermal imaging camera among the plurality of thermal imaging cameras based on the position of the partial zone is transmitted through the communication circuit. transmits to the first thermal imaging camera through
Receiving a second thermal image through the first thermal imaging camera whose angle is adjusted;
Detecting a fire occurring in the partial area by performing machine learning on the second thermal image using a database pre-stored in the memory;
Identifying a fire path based on temperature changes of areas identified from the first thermal image, analyzing the fire path, and outputting information about the fire path,
the processor,
A process for detecting an intruder entering the unmanned substation without permission and a process for detecting a fire are performed in parallel,
In response to detecting the intruder, outputting guide information indicating that an intruder is detected to the unmanned substation through the output device so that the manager of the monitoring server can recognize the intruder;
In response to detecting a fire in the unmanned substation, outputting information indicating that a fire has occurred in the unmanned substation through the output device so that a manager of the monitoring server can recognize the occurrence of a fire;
Storing an image of a thermal imaging camera associated with the intruder in the memory, and storing the second thermal image in the memory in response to detecting a fire in the unmanned substation;
The information tagged to the thermal image is generated based on information input from a manager or automatically based on information identified through a machine learning process,
The information on the object, monitoring server characterized in that it includes the location information of the object, the size information of the object, and the moving speed information of the object.
delete delete delete delete delete delete delete delete delete delete

Images