KR20240040434A - Smart disaster monitoring system of having function for preventing false alarm - Google Patents

Abstract

The present invention includes a GIS server 110 that provides geographic information, a regional characteristic generator 120 that quantifies the risk of fire occurrence and generates characteristic information, a weather server 130 that provides weather information, and individual buildings in a specific area. One or more IoT sensor units 140 that provide environmental measurement information for each management area unit of each floor, a fire environment information generator 150 that generates fire environment information for each management area unit, and one or more units that provide first image information. The video provider 160 monitors the occurrence of fire in real time, predicts the possibility of fire occurrence, calculates the fire false detection rate, and if the fire false detection rate is less than the standard value, predicts the direction and extent of spread and is adjacent to the individual building. Complex sensing analysis, including a control server 170 that propagates a fire outbreak situation to the building and provides warning information to a communicable smart terminal 200 identified in the area included in the predicted direction and range of spread. We are launching a smart disaster detection system equipped with a false detection prevention function to reduce the false detection rate of fire and prevent false detection of fire.

Description

Smart disaster detection system with false detection prevention function {SMART DISASTER MONITORING SYSTEM OF HAVING FUNCTION FOR PREVENTING FALSE ALARM}

The present invention relates to a smart disaster detection system with a false detection prevention function that reduces the false detection rate of fire and prevents false detection of fire through complex sensing analysis of the IoT sensor unit.

As is well known, disasters such as large-scale fires, gas leaks, flooding, collapses, and traffic accidents occur unexpectedly and frequently, and in order to deal with them, disaster prevention and relief organizations, for example, use buildings, underground spaces, warehouses, We are continuously developing a system that detects the occurrence of disasters in specific spaces, such as oil storage areas, forests, and transportation, and warns the surrounding area.

In particular, in factories, logistics centers, warehouses, logistics terminals, and complex buildings, smoke detectors may trigger false detections due to smoke generated during smoking or cooking rather than an actual fire situation, resulting in social costs for fire suppression. It can be wasted unnecessarily, and false detections can also be a major cause of passive fire prevention activities.

Accordingly, technology is required to reduce the false fire detection rate and prevent false fire detection through complex sensing analysis, thereby reducing unnecessary social costs in response to non-detection or false detection.

Korean Patent Publication No. 10-1439267 (Real-time smart unmanned fire control device, 2014.09.18) Korean Patent Publication No. 10-1086221 (Disaster monitoring system and disaster monitoring system operation method, 2011.11.23)

The technical task to be achieved by the idea of the present invention is to reduce the fire false detection rate through complex sensing analysis of the IoT sensor unit, prevent false fire detection, reduce unnecessary social costs due to response to non-detection or false detection, and reduce fire detection. The goal is to provide a smart disaster detection system with a false positive detection function that can intensively monitor the predicted area and respond preemptively.

In order to achieve the above-mentioned object, the embodiment of the present invention is the cadastral land and roads of a specific area divided into areas such as downtown, suburbs, residential areas, commercial areas, industrial complexes, logistics complexes, coastal areas, and mountainous areas. and a GIS server that provides geographic information of buildings and aerial photographs; A regional characteristics generation unit that uses big data to generate characteristic information by quantifying the risk of fire occurrence according to building density, population density, and traffic concentration for the specific area; A weather server that provides weather information for the specific area; Temperature sensor, humidity sensor, wind direction sensor, wind speed sensor, illuminance sensor, heat sensor, flame detection sensor, smoke detection sensor, and gas, which are arranged in management area units on each floor of individual buildings in the above-mentioned specific area and are each assigned an identification number. One or more IoT sensor units that are grouped into one or more of a detection sensor, a motion sensor, a vibration sensor, and an earth leakage sensor, and provide environmental measurement information for the management area unit; a fire environment information generation unit that collects and combines the environmental measurement information transmitted from the IoT sensor unit through a wired or wireless network to generate fire environment information for each management area; One or more image providing units arranged for each management area unit and provided with first image information, consisting of an optical camera and a thermal imaging camera, each assigned an identification number; And by receiving and analyzing the fire environment information and the first image information, monitor fire occurrence in real time, predict the possibility of fire occurrence, and calculate the fire false detection rate. If the fire false detection rate is less than the standard value, the direction of spread and spread A control server that predicts the range, spreads the fire situation to the individual building and adjacent buildings, and provides warning information to a communicable smart terminal identified in the area included in the predicted direction and range of spread. Provides a smart disaster detection system with a false positive prevention function, including:

Here, the control server calculates the fire false detection rate by comparing and analyzing the pre-stored first fire environment information when an actual fire occurs and the second fire environment information transmitted in real time from the fire environment information generator, and the heat detection unit. Any one or more measured values of each of the sensor, the flame detection sensor, the smoke detection sensor, and the gas detection sensor are greater than or equal to a reference value corresponding to the first fire environment information, and one or more measured values are greater than or equal to the reference value corresponding to the first fire environment information. If it is below the standard value corresponding to environmental information, the fire false detection rate can be calculated by assigning weight to the corresponding measured value.

In addition, if the fire false detection rate is less than the standard value, the control server can analyze the first image information to determine whether a fire has actually occurred.

Additionally, the control server can determine whether the environmental measurement information is error-free by analyzing the electrical signal characteristics during normal operation of the IoT sensor unit and the electrical signal characteristics when a failure occurs.

In addition, a plurality of drones equipped with optical cameras and thermal imaging cameras and periodically flying according to flags set in the specific area to provide second image information for the specific area; and a drone flight control unit that sets a flight path to a fire occurrence area monitored or predicted by the control server and hovers the drone to provide the second image information to the control server.

According to the present invention, the fire false detection rate is reduced through complex sensing analysis of the IoT sensor unit, and unnecessary social costs due to response to non-detection or false detection are reduced by preventing false fire detection, and by intensively monitoring the fire prediction area. It has the effect of enabling preemptive response.

Figure 1 shows a schematic configuration diagram of a smart disaster detection system equipped with a false detection prevention function according to an embodiment of the present invention.
FIG. 2 illustrates an implementation diagram of a smart disaster detection system equipped with the false detection prevention function of FIG. 1.

Hereinafter, embodiments of the present invention having the above-described features will be described in more detail with reference to the attached drawings.

A smart disaster detection system equipped with a false detection prevention function according to an embodiment of the present invention includes a GIS server 110 that provides geographic information, a regional characteristics generator 120 that generates characteristic information by quantifying the risk of fire occurrence, A weather server 130 that provides weather information, one or more IoT sensor units 140 that provide environmental measurement information for each floor management area unit of an individual building in a specific area, and a fire environment that generates fire environment information for each management area unit. An information generation unit 150, one or more image providing units 160 that provide first image information, and real-time monitoring of fire occurrence, predicting the possibility of fire occurrence, and calculating a fire false detection rate so that the fire false detection rate is below the standard value. On the other hand, the direction and extent of spread are predicted, the fire outbreak situation is propagated to each individual building and adjacent buildings, and warning information is sent to a smart terminal (200) capable of communication that is identified in the area included in the predicted direction and extent of spread. The point is to reduce the false detection rate of fire and prevent false detection of fire through complex sensing analysis, including the control server 170, which provides.

Hereinafter, with reference to FIGS. 1 and 2, the smart disaster detection system equipped with the false detection prevention function of the above-described configuration will be described in detail as follows.

First, the GIS (Geographic Information System) server 110 is integrated and controlled by the control server 170, including urban areas, suburbs, residential areas, commercial areas, industrial complexes, and logistics complexes. Geographic information on cadastral land, roads, buildings, and aerial photos of specific areas divided by coastal area and mountainous area is provided to the control server 170.

Here, the GIS server 110 sends 2D geographic information for a specific area, satellite photos provided from the artificial satellite 400, and 3D geographic information converted from the 2D geographic information to the control server 170 and the drone flight control unit 190. Each can be transmitted.

Next, the regional characteristic generation unit 120 uses big data accumulated in the past to quantify the risk of fire occurrence according to building density, population density, and traffic concentration for a specific area to generate regional characteristic information.

For example, the regional characteristics generation unit 120 uses fire-related big data accumulated in the past to analyze changes in temperature and humidity by day, week, month, and season and past fire occurrence patterns, and to determine building density, population density, and traffic concentration. By assigning weights according to the , the risk of fire occurrence can be quantified, regional characteristic information can be generated, and transmitted to the control server 170 and the drone flight control unit 190, respectively.

Here, the control server 170 can differentiate the monitoring intensity of real-time monitoring according to regional characteristic information, and the drone flight control unit 190 can differentiate the monitoring intensity by the drone 180 according to regional characteristic information.

Next, the weather server 130 provides real-time weather information and predicted weather information for a specific area to the control server 170, allowing it to monitor real-time disaster progress according to weather conditions or predict the possibility of fire, and drones. It can be provided to the flight control unit 190 to control whether the drone 180 flies, flight range, flight altitude, flight pattern, and flight speed.

Next, the IoT sensor unit 140 is composed of one or more, and is arranged in the management area unit on each floor of individual buildings such as factories, logistics centers, warehouses, logistics terminals, and complex buildings in a specific area, and is assigned an identification number to each. Among the sensors that detect disasters such as fires are temperature sensor, humidity sensor, wind direction sensor, wind speed sensor, illuminance sensor, heat sensor, flame sensor, smoke sensor, gas sensor, motion sensor, vibration sensor, and electric leak sensor. It is grouped into one or more, and environmental measurement information for the management area measured by the sensor is provided to the fire environment information generation unit 150 through a wired or wireless network.

Here, each sensor is assigned an identification number, so that the management area unit deployed by the control server 170 and the corresponding sensor can be individually identified.

In addition, embedded coding can be performed for each sensor to be converted to specifications by the fire environment information generation unit 150 and integrated and monitored by the control server 170.

In addition, the gas detection sensor detects the components and concentration of combustion gases such as CO generated when a fire occurs, and the control server 170 identifies whether an actual fire has occurred and the ignition causative material, and quickly stops the fire according to the ignition causative material. Information on fire extinguishing equipment that can be used to extinguish the fire can also be provided.

Next, the fire environment information generation unit 150 collects and combines environmental measurement information transmitted through a wired or wireless network from the IoT sensor unit 140 to generate fire environment information for each management area, and provides it to the control server 170. This ensures real-time monitoring.

Next, the image provider 160 consists of one or more optical cameras and thermal imaging cameras, which are arranged for each management area unit and are each assigned an identification number, and provide a first image of the inside and outside of the management area unit and the inside and outside of the corresponding building. Information is generated and provided to the control server 170 for monitoring.

Next, the control server 170 receives and analyzes the fire environment information from the fire environment information generator 150 and the first image information from the video provider 160, and monitors the fire in real time by management area. , predict the possibility of fire occurrence, calculate the fire false detection rate, and if the fire false detection rate is below the standard value, predict the direction and extent of spread of the fire, spread the fire occurrence situation to the individual building and adjacent buildings, and predict the spread. Warning information is provided to a smart terminal (200) capable of communication that is identified in the area included in the direction and spread range.

Here, the control server 170 includes complex sensing data of the first fire environment information at the time of an actual fire pre-stored in the fire environment information generator 150 and the second fire environment information transmitted in real time from the fire environment information generator 150. The fire false detection rate is calculated by comparing and analyzing the complex sensing data of environmental information, and any one or more of the measured values of the heat detection sensor, flame detection sensor, smoke detection sensor, and gas detection sensor corresponds to the first fire environment information. If it is more than the standard value, and one or more measured values are less than or equal to the standard value corresponding to the first fire environment information, the fire false detection rate can be calculated by assigning weight to the corresponding measured value.

In other words, each measurement value of the smoke detection sensor and heat detection sensor is above the standard value corresponding to the first fire environment information at the time of an actual fire, but each measurement value of the gas detection sensor and flame detection sensor is the first fire environment information at the time of an actual fire occurrence. If the information is below the standard value, the possibility of false detection of fire may be high, so the fire false detection rate can be calculated by assigning weight to the measured values that are below the standard value.

For example, in a factory environment, smoke usually stays in workshops and welding areas where mechanical equipment operates 24 hours a day, and the temperature may be high, so the measured values of the smoke detection sensor and heat detection sensor may be above the standard value, but a fire may not actually occur. Since this is not a situation that has occurred, the measured values of the gas detection sensor and the flame detection sensor may be below the standard value, so the possibility of false detection can be identified by comparing and analyzing the measured values of one or more sensors.

In addition, due to seasonal characteristics, there may be a possibility of false detection by heat detection sensors or temperature sensors, so the fire false detection rate can be calculated by comparing and analyzing the measured values by other sensors to lower the possibility of false detection.

Meanwhile, if the previously calculated fire false detection rate is below the reference value, the control server 170 may determine whether a fire actually occurred by analyzing the first image information transmitted from the image provider 160.

In other words, even if the fire false detection rate is below the standard value, it is possible to determine more accurately whether a fire has actually occurred by visually identifying it.

In addition, the control server 170 compares and analyzes the electrical signal characteristics during normal operation of each sensor of the IoT sensor unit 140 and the electrical signal characteristics when a failure of the sensor itself occurs, and determines whether there is an error in the environmental measurement information for each sensor. The possibility of false detection by the sensor can also be minimized.

In addition, the smoke detected by the smoke detection sensor is affected by the wind, so even if smoke is generated due to an actual fire, if strong wind flows into the management area, the measured value by the smoke detection sensor may be low. When calculating the fire false detection rate using the measured values, the influence of the measured values of the wind direction sensor and wind speed sensor can be considered, and sudden temperature changes by the temperature sensor or rapid humidity changes by the humidity sensor can also be considered.

In addition, the control server 170 may identify that an actual fire has occurred and respond to the fire situation only when the measured values of the heat sensor, flame sensor, smoke sensor, and gas sensor are all above the reference value.

Next, the drone 180 is composed of a plurality, each equipped with an optical camera and a thermal imaging camera, and flies periodically according to a preset flag set in a specific area to provide secondary image information of an aerial image or aerial image for a specific area. It is provided in real time through a wired or wireless network by the control server 170.

Next, the drone flight control unit 190 controls the flight status, flight range, flight altitude, flight pattern, and flight speed of the drone 180, and controls the fire monitored or predicted by the control server 170 using 3D geographic information. The flight path of the drone 180 to the area where a fire occurs is set to a flag and the drone 180 is hovered to provide second image information to the control server 170, so that the fire can be prevented by stationary flight over an area with a high possibility of fire occurrence. The situation can be monitored in real time by the control server 170 or intensively monitored before an actual fire occurs.

Meanwhile, the drone flight control unit 190 performs a circuit flight that sequentially follows the flags of the drone 180 for a specific area or a hovering flight at a specific flag according to the fire risk generated by the regional characteristic generation unit 120. By controlling the flight pattern, flight speed, and flight altitude, it is possible to make a circuitous flight in areas with a relatively low fire risk, and a low-speed or hovering flight in areas with a relatively high fire risk.

Here, if the fire false detection rate is below the standard value, the control server 170 may analyze the second image information transmitted in real time from the drone 180 to determine whether a fire has actually occurred.

In addition, the control server 170 analyzes the fire environment information, first image information, and second image information to predict the possibility of fire occurrence in the area according to the risk, and the drone flight control unit 190 predicts the possibility of fire occurrence in the area according to the possibility of fire occurrence. It is possible to control the surveillance pattern of preemptive surveillance or continuous surveillance by drone 180 for a specific area.

In addition, the control server 170 analyzes weather information from the weather server 130 to predict the direction and extent of spread of the fire, and installs emergency warning equipment and emergency warning equipment in the area included in the predicted direction and extent of spread. Warning information can be provided through broadcasting equipment to enable people to respond or evacuate.

In addition, the control server 170 provides warning information to the communicable smart terminal 200 identified in the area included in the previously predicted direction and spread of the fire, thereby preventing the owner of the smart terminal 200 from experiencing a disaster. You can also evacuate by bypassing the area.

In addition, the fire environment information, first image information, and second image information are transmitted and stored to the cloud server 300 to be used as big data, and the control server 170 receives fire environment information and data from the cloud server 300. First image information and second image information can be received in real time.

In addition, the control server 170 analyzes the satellite photo, fire environment information, first image information, and second image information about the fire occurrence area received from the satellite 400, and specifies the origin of the fire to provide relief vehicles or relief. It may also provide a location for concentrated equipment deployment.

In addition, the control server 170 analyzes geographical information and generates information on the shortest approach route for relief vehicles to the origin of the fire, information on storage boxes for rescue equipment in the area, and information on evacuation routes from the origin of the fire, to disaster-related organizations. It can also be provided through servers or smart terminals of residents in disaster areas.

Meanwhile, in this embodiment, although the monitoring and prediction of fire and false detection were previously exemplified, it is not limited to this, and is not limited to forest fires, oil explosions, gas explosions, flooding, flooding, floods, heat waves, heavy snow, earthquakes, landslides, and sinks. It can also be applied to monitoring, prediction, and false positive detection of disasters such as hall and tunnel collapse, beam collapse, dam collapse, track damage, and road damage.

Therefore, by constructing a smart disaster detection system equipped with the false detection prevention function as described above, the fire false detection rate is reduced through complex sensing analysis of the IoT sensor unit, and fire false detection is prevented to respond to non-detection or false detection. It is possible to reduce unnecessary social costs and respond preemptively by intensively monitoring fire prediction areas.

The embodiments described in this specification and the configurations shown in the drawings are only one of the most preferred embodiments of the present invention and do not represent the entire technical idea of the present invention, so various equivalents may be substituted for them at the time of filing the present application. It should be understood that variations and variations may exist.

110: GIS server 120: Regional characteristics generation unit
130: weather server 140: IoT sensor unit
150: Fire environment information generation unit 160: Video provision unit
170: Control server 180: Drone
190: Drone flight control unit 200: Smart terminal
300: Cloud server 400: Satellite

Claims (5)

A GIS server that provides geographic information on cadastral land, roads, buildings, and aerial photos of specific areas divided into urban areas, suburbs, residential areas, commercial areas, industrial complexes, logistics complexes, coastal areas, and mountainous areas;
A regional characteristics generation unit that uses big data to generate characteristic information by quantifying the risk of fire occurrence according to building density, population density, and traffic concentration for the specific area;
A weather server that provides weather information for the specific area;
Temperature sensor, humidity sensor, wind direction sensor, wind speed sensor, illuminance sensor, heat sensor, flame detection sensor, smoke detection sensor, and gas, which are arranged in management area units on each floor of individual buildings in the above-mentioned specific area and are each assigned an identification number. One or more IoT sensor units that are grouped into one or more of a detection sensor, a motion sensor, a vibration sensor, and an earth leakage sensor, and provide environmental measurement information for the management area unit;
a fire environment information generation unit that collects and combines the environmental measurement information transmitted from the IoT sensor unit through a wired or wireless network to generate fire environment information for each management area;
One or more image providing units arranged for each management area unit and provided with first image information, consisting of an optical camera and a thermal imaging camera, each assigned an identification number; and
The fire environment information and the first image information are received and analyzed to monitor fire occurrence in real time, predict the possibility of fire occurrence, and calculate the fire false detection rate. If the fire false detection rate is below the standard value, the direction and extent of spread are determined. A control server that predicts, propagates the fire situation to the individual building and adjacent buildings, and provides warning information to a communicable smart terminal identified in the area included in the predicted direction and range of spread. doing,
Smart disaster detection system with false positive prevention function.
According to paragraph 1,
The control server calculates the fire false detection rate by comparing and analyzing the pre-stored first fire environment information at the time of an actual fire occurrence and the second fire environment information transmitted in real time from the fire environment information generator,
Any one or more measured values of the heat detection sensor, the flame detection sensor, the smoke detection sensor, and the gas detection sensor are greater than or equal to the reference value corresponding to the first fire environment information, and one or more measured values are greater than or equal to the reference value corresponding to the first fire environment information. Characterized in calculating the fire false detection rate by assigning a weight to the measured value if it is below the standard value corresponding to the first fire environment information,
Smart disaster detection system with false positive prevention function.
According to paragraph 2,
The control server is characterized in that, if the fire false detection rate is less than a standard value, it analyzes the first image information and determines whether a fire has actually occurred.
Smart disaster detection system with false positive prevention function.
According to paragraph 1,
The control server analyzes the electrical signal characteristics during normal operation of the IoT sensor unit and the electrical signal characteristics when a failure occurs, and determines whether the environmental measurement information is error-free.
Smart disaster detection system with false positive prevention function.
According to paragraph 1,
A plurality of drones equipped with an optical camera and a thermal imaging camera and periodically flying according to a flag set in the specific area to provide second image information for the specific area; and
A drone flight control unit that sets a flight path to a fire occurrence area monitored or predicted by the control server and hovers the drone to provide the second image information to the control server. Characterized in that it further comprises a.
Smart disaster detection system with false positive prevention function.

Images