WO2021040126A1 - Intelligent wearable dangerous state determination device using complex environment measurement, and method therefor - Google Patents
Intelligent wearable dangerous state determination device using complex environment measurement, and method therefor Download PDFInfo
- Publication number
- WO2021040126A1 WO2021040126A1 PCT/KR2019/013719 KR2019013719W WO2021040126A1 WO 2021040126 A1 WO2021040126 A1 WO 2021040126A1 KR 2019013719 W KR2019013719 W KR 2019013719W WO 2021040126 A1 WO2021040126 A1 WO 2021040126A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- worker
- state
- sensor
- intelligent wearable
- hazardous
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000005259 measurement Methods 0.000 title claims abstract description 12
- 231100001261 hazardous Toxicity 0.000 claims abstract description 40
- 230000001133 acceleration Effects 0.000 claims abstract description 36
- 238000010801 machine learning Methods 0.000 claims abstract description 8
- 239000007789 gas Substances 0.000 claims description 41
- 230000007423 decrease Effects 0.000 claims description 8
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 6
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 claims description 6
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 6
- 229910002091 carbon monoxide Inorganic materials 0.000 claims description 6
- 229910000037 hydrogen sulfide Inorganic materials 0.000 claims description 6
- 239000001301 oxygen Substances 0.000 claims description 6
- 229910052760 oxygen Inorganic materials 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 6
- 239000003570 air Substances 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 208000001408 Carbon monoxide poisoning Diseases 0.000 description 1
- 206010017740 Gas poisoning Diseases 0.000 description 1
- 208000006930 Pseudomyxoma Peritonei Diseases 0.000 description 1
- 239000012080 ambient air Substances 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 231100000614 poison Toxicity 0.000 description 1
- 230000007096 poisonous effect Effects 0.000 description 1
- 229920001690 polydopamine Polymers 0.000 description 1
- 229920000306 polymethylpentene Polymers 0.000 description 1
- 239000002341 toxic gas Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0438—Sensor means for detecting
- G08B21/0446—Sensor means for detecting worn on the body to detect changes of posture, e.g. a fall, inclination, acceleration, gait
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C19/00—Gyroscopes; Turn-sensitive devices using vibrating masses; Turn-sensitive devices without moving masses; Measuring angular rate using gyroscopic effects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0027—General constructional details of gas analysers, e.g. portable test equipment concerning the detector
- G01N33/0036—General constructional details of gas analysers, e.g. portable test equipment concerning the detector specially adapted to detect a particular component
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P15/00—Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration
- G01P15/003—Kinematic accelerometers, i.e. measuring acceleration in relation to an external reference frame, e.g. Ferratis accelerometers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0438—Sensor means for detecting
- G08B21/0492—Sensor dual technology, i.e. two or more technologies collaborate to extract unsafe condition, e.g. video tracking and RFID tracking
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/12—Alarms for ensuring the safety of persons responsive to undesired emission of substances, e.g. pollution alarms
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/14—Central alarm receiver or annunciator arrangements
Definitions
- the present invention relates to an intelligent wearable risk state determination device and method using a composite environment measurement, and an intelligent wearable risk state using a composite environment measurement to measure the user's external environment and check the user's state based on the measured data. It relates to a judgment device and a method thereof.
- a portable gas meter uses a battery to supply power, so it is inconvenient to carry it at all times due to its heavy weight and size. It is a method driven by a single sensor capable of detecting one gas on one sensor chip.
- mobile terminals refer to portable electronic devices such as cell phones, portable computers, palm PCs, PDAs, electronic notebooks, digital cameras, camcorders, MP3 players, and PMPs.
- portable electronic devices such as cell phones, portable computers, palm PCs, PDAs, electronic notebooks, digital cameras, camcorders, MP3 players, and PMPs.
- the trend is becoming smaller.
- Such a mobile terminal configures various internal circuits according to a maker and a model of the mobile terminal, and is provided to enable interfacing by installing a plurality of connectors on one side of the mobile terminal housing as an interface for communicating with the outside.
- a portable gas meter has a battery, and the required power is supplied through the battery. In the case of being supplied, there is a problem in that the portable gas measuring device is inconvenient to carry due to the heavy weight and large size of the portable gas meter due to the characteristic of the structure supplying power from the battery.
- An object of the present invention is to provide an intelligent wearable danger state determination device and method using complex environment measurement to measure the user's external environment and check the user's state based on the measured data.
- an intelligent wearable danger state determination device using a complex environment measurement
- a gas sensor that is detachable and capable of measuring the concentration of gas around the work environment, and the operator's
- a sensor unit including a gyro sensor and an acceleration sensor capable of measuring the balance state and motion, and a camera for photographing the surrounding environment of the worker, and a hazardous state determination to determine whether or not there is a harmful state around the worker from the measured concentration of the gas Part
- a learning unit that generates a learning model by applying the worker's fall according to the number of floors on which the worker is located, the measured value of the gyro sensor, the acceleration sensor and the camera's photographed image attached to the worker, to a machine learning technique.
- a fall determination unit that determines whether the worker falls or not by applying the measured value of the gyro sensor, the measured value of the acceleration sensor, the pixel change value of the photographed image, and the number of floors of the worker's current location to the learning model, Includes an output unit for outputting information on a hazardous state and information on whether the worker is falling through a display, and a control unit to transmit information on a harmful state of the work environment and information on whether the worker is falling through a network to another worker or a control center. do.
- the sensor unit includes a read out integrated circuit (ROIC), and may measure at least one of oxygen, combustible gas, hydrogen sulfide, temperature, humidity, and carbon monoxide.
- ROIC read out integrated circuit
- the fall determination unit if the value measured from the gyro sensor is greater than the reference value, the value measured from the acceleration sensor is greater than the reference value, or the amount of change in the pixel value of the image captured by the camera is greater than the reference value. It can be determined that the worker simply fell.
- the fall determination unit determines that the surrounding environment before the fall of the felled worker is in a hazardous state, it may be determined that the fall is caused by the fall of the worker.
- the control unit When it is determined that the surrounding of the worker is in a hazardous state, the control unit transmits a danger alarm signal to another worker at a certain distance from the worker, and when it is determined that the worker has fallen, an alarm is generated and the other worker wears it.
- An intelligent wearable complex environment measuring device can communicate the fall of the worker.
- the control unit may distinguish whether the worker has fallen due to a simple fall or an unhealthy condition, and transmit it to the control center.
- the learning unit may learn by increasing the weight of the gyro sensor and the acceleration sensor as the number of floors of the work environment increases, and decrease the weight of the gyro sensor and the acceleration sensor as the number of floors of the work environment decreases.
- the control unit may estimate the current number of floors of the worker through a beacon signal attached to the work environment.
- a method for determining a dangerous state using an intelligent wearable dangerous state determining device it is possible to attach and detach, measure the concentration of gas around the work environment, measure the balance state and motion of the worker, Photographing the surrounding environment of the worker, determining whether there is a harmful state around the worker from the measured concentration of the gas, measured values of the gyro sensor, acceleration sensor and camera attached to the worker, and the number of floors on which the worker is located.
- Generating a learning model by applying whether the worker falls or not to a machine learning technique, the measured value of the gyro sensor, the measured value of the acceleration sensor, the pixel change value of the photographed image, and the number of floors in the current location of the worker.
- the present invention it is possible to detect whether there is harmfulness by using harmful information obtained in real time, and when a harmful state occurs, it is possible to notify a worker in real time so that they can leave a corresponding area.
- the senor module can be replaced and used, the efficiency and safety of work can be improved.
- FIG. 1 is a diagram showing the configuration of an intelligent wearable danger state determination apparatus according to an embodiment of the present invention.
- FIG. 2 is a flowchart illustrating a method of determining a dangerous state using an intelligent wearable dangerous state determining device according to an embodiment of the present invention.
- step S210 of FIG. 2 is a diagram for explaining step S210 of FIG. 2.
- FIG. 4 is a diagram illustrating an apparatus for determining an intelligent wearable danger state according to an embodiment of the present invention.
- FIG. 1 is a diagram showing the configuration of an intelligent wearable danger state determination apparatus according to an embodiment of the present invention.
- the intelligent wearable danger state determination device 100 includes a sensor unit 110, a hazardous state determination unit 120, a learning unit 130, a fall determination unit 140, an output unit 150, and a control unit ( 160).
- the sensor unit 110 is detachable, a gas sensor capable of measuring the concentration of gas around the work environment, a gyro sensor and an acceleration sensor capable of measuring the balance and motion of the worker, and the surrounding environment of the worker. It includes a camera for shooting.
- the gas sensor includes a read out integrated circuit (ROIC) and may measure at least one of oxygen, combustible gas, hydrogen sulfide, temperature/humidity, and carbon monoxide.
- ROIC read out integrated circuit
- the sensor unit 110 may change the type of gas that can be measured by changing the type of the gas sensor.
- the harmful state determination unit 120 determines whether there is a harmful state around the worker from the concentration of the gas measured by the gas sensor.
- the learning unit 130 generates a learning model by applying the measurement values of a gyro sensor, an acceleration sensor, and a camera attached to the worker, and whether the worker falls according to the number of floors on which the worker is located, to a machine learning technique.
- the machine learning technique is an artificial intelligence learning method, and can generate optimal data by analyzing big data.
- the learning unit 130 learns by increasing the weights for the gyro sensor and the acceleration sensor as the number of floors in the work environment increases, and decreases the weights for the gyro sensor and the acceleration sensor as the number of floors in the work environment decreases.
- the fall determination unit 140 determines whether the worker falls by applying the measured value of the gyro sensor, the measured value of the acceleration sensor, the pixel change value of the camera, and the number of floors of the worker's current location to the learning model.
- the fall determination unit 140 may have a value measured from a gyro sensor greater than a reference value, a value measured from an acceleration sensor greater than a reference value, or the amount of change in the pixel value of the image captured by the camera is greater than the reference value. If it is large, it is determined that the worker has simply fallen.
- a simple fall means a fall caused by a worker's failure.
- the fall determination unit 140 determines that the surrounding environment before the fall of the fallen worker is in a hazardous state, it is determined that the worker has fallen due to the hazardous state.
- the output unit 150 outputs information on a hazardous state of the work environment and information on whether a worker falls or not through the display.
- the output unit 150 outputs information on the current harmful state around the worker through the display.
- control unit 160 transmits information on the hazardous state of the work environment and information on whether the worker has fallen or not to another worker or a control center through a network.
- the control unit 160 transmits a danger alarm signal to another worker at a certain distance from the worker, and when it is determined that the worker has fallen, an alarm is generated and the other worker wears it.
- An intelligent wearable complex environment measuring device communicates the fall of the worker.
- control unit 160 distinguishes whether the worker has simply fallen or has fallen due to a hazardous condition, and transmits it to the control center.
- control unit 160 estimates the current number of floors of the worker through a beacon signal attached to the work environment.
- FIG. 2 is a flowchart illustrating a method of determining a dangerous state using an intelligent wearable dangerous state determining device according to an embodiment of the present invention.
- the sensor unit 110 measures the concentration of gas around the work environment using a detachable sensor module, measures the balance and motion of the worker using a gyro sensor and an acceleration sensor, and measures the operator's balance and motion using a camera. Take a picture of the surrounding environment (S210).
- step S210 of FIG. 2 is a diagram for explaining step S210 of FIG. 2.
- the gas sensor included in the sensor unit 110 may be implemented in the form of a plurality of sensor modules according to the type of gas to be measured.
- the gas sensor may include any one of a temperature/humidity sensor module 111a, a CO 2 sensor module 111b, or a CO sensor module 111e. At least one of gas, hydrogen sulfide, temperature/humidity, and carbon monoxide can be measured.
- a gyro sensor and an acceleration sensor included in the sensor unit 110 are used to detect a worker's balance state and motion, and a camera is used to photograph the worker's surrounding environment.
- the hazardous state determination unit 120 determines whether the work environment around the worker is in a hazardous state from the measured concentration of the gas (S220).
- the hazardous state determination unit 120 indicates that there is a hazardous state when the oxygen concentration is less than 18% or 23.5% or more, or the concentration of carbon dioxide is 1.5% or more, or the concentration of hydrogen sulfide is 10 ppm or more and the carbon monoxide concentration is 30 ppm. Judge.
- the learning unit 130 generates a learning model by applying the measurement values of the gyro sensor, acceleration sensor and camera attached to the worker, and whether the worker falls according to the number of floors on which the worker is located, to a machine learning technique. (S230).
- the learning unit 130 learns by increasing the weights for the gyro sensor and the acceleration sensor as the number of floors in the work environment increases, and decreases the weights for the gyro sensor and the acceleration sensor as the number of floors in the work environment decreases.
- the learning unit 130 sets the weight for the floor on which the worker is located to a value greater than 1 to learn.
- the learning unit 130 learns by increasing the weight differentially according to the final number of floors of the building.
- the fall determination unit 140 determines whether the worker falls by applying the measured value of the gyro sensor, the measured value of the acceleration sensor, the amount of pixel change of the camera, and the number of floors of the worker's current location to the learning model (S240).
- the fall determination unit 140 determines whether the value measured from the gyro sensor is greater than the reference value, the value measured from the acceleration sensor is greater than the reference value, or the amount of change in the pixel value of the image captured by the camera is the reference value. If it is greater than, it is judged that the worker has simply fallen.
- the fall or not determining unit 140 determines that the surrounding environment before the fall of the fallen worker is in a hazardous state, it is determined that the worker has fallen due to the hazardous state.
- the reference value is a work environment, a value that changes when the worker moves or works, and may be changed according to the worker or the attached position.
- the output unit 150 outputs information on a hazardous state of the work environment and information on whether a worker falls or not through the display (S250).
- the output unit 150 outputs information on the hazardous state of the work environment through the display so that the worker or other worker can check it.
- control unit 160 transmits information on the hazardous state of the work environment and information on whether the worker has fallen to another worker or the control center through the network (S260).
- control unit 160 transmits a danger alarm signal to another worker at a certain distance from the worker, and when it is determined that the worker has fallen, the control unit 160 causes an alarm to occur. Communicate the worker's status to other workers.
- control unit 160 determines whether a fall due to a loss or a fall due to a harmful condition is determined, and transmits it to another worker or a control center.
- the control center provides the rescuer with a list of necessary tools according to the hazardous condition.
- the control center For example, if it is determined that the person has fallen due to carbon monoxide poisoning, the control center provides tools such as an oxygen tank to the rescuer, and if it is judged that the person has fallen due to poisonous gas poisoning, the control center provides a rescuer with a tool that can remove the toxic gas. To provide.
- control unit 160 estimates the current number of floors of the worker using a beacon signal and a network signal attached to the work environment.
- control unit 160 provides the operator's condition and harmful condition to another operator using a wired or wireless network, and transmits the operator's condition and harmful condition to another operator or the control center in real time to the control center.
- the beacon is a short-range mobile communication device for forming IoT, and the controller 160 can know the exact location of the worker and the number of floors in the building using the beacon.
- FIG. 4 is a diagram illustrating an apparatus for determining an intelligent wearable danger state according to an embodiment of the present invention.
- the operator can wear the manufactured intelligent wearable danger state determination device 100 on a part of the worker's body, and the attachment position is the form of the user and the intelligent wearable danger state determination device 100 It can be changed according to.
- an air inlet portion for inhaling ambient air and an air outlet portion for discharging the inhaled air are included in order to measure harmful gas, and each position may be changed.
- each button generated on the left and right of the intelligent wearable complex environment measuring apparatus 100 may be any one of power, normal clock mode, communication mode, and gas sensor operation. Each location can be changed according to the user.
- the senor module can be replaced and used, the efficiency and safety of work can be improved.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Chemical & Material Sciences (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Gerontology & Geriatric Medicine (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Toxicology (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Combustion & Propulsion (AREA)
- Environmental & Geological Engineering (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Emergency Alarm Devices (AREA)
- Alarm Systems (AREA)
Abstract
Description
Claims (16)
- 복합환경 측정을 이용한 지능형 웨어러블 위험 상태 판단 장치에 있어서,In the intelligent wearable danger state determination device using complex environment measurement,탈부착이 가능하며, 작업 환경 주변의 가스의 농도를 측정할 수 있는 가스 센서, 작업자의 균형 상태 및 동작을 측정할 수 있는 자이로 센서 및 가속도 센서 및 상기 작업자의 주변 환경을 촬영하기 위한 카메라를 포함하는 센서부, Detachable, including a gas sensor that can measure the concentration of gas around the work environment, a gyro sensor and acceleration sensor that can measure the balance state and motion of the worker, and a camera for photographing the surrounding environment of the worker. Sensor,상기 측정된 가스의 농도로부터 작업자 주변의 유해 상태 여부를 판단하는 유해 상태 판단부,A hazardous state determination unit that determines whether or not there is a hazardous state around the worker from the measured concentration of the gas,상기 자이로 센서, 가속도 센서의 측정 값 및 카메라의 촬영 영상, 작업자가 위치한 층수에 따른 상기 작업자의 낙상 여부를 머신러닝(Machine Learning)기법에 적용하여 학습 모델을 생성하는 학습부,A learning unit that generates a learning model by applying a fall of the worker according to the number of floors on which the worker is located, the measured value of the gyro sensor and the acceleration sensor, and the image taken by the camera, to a machine learning technique,상기 자이로 센서의 측정 값, 가속도 센서의 측정 값, 촬영 영상의 픽셀 변화값 및 상기 작업자의 현재 위치 층수를 상기 학습 모델에 적용하여 상기 작업자의 낙상 여부를 판단하는 낙상 판단부,A fall determination unit that determines whether the worker falls or not by applying the measured value of the gyro sensor, the measured value of the acceleration sensor, the pixel change value of the photographed image, and the number of floors of the worker's current location to the learning model,상기 작업환경의 유해 상태 정보와 상기 작업자의 낙상 여부 정보를 디스플레이를 통하여 출력하는 출력부, 그리고 An output unit that outputs information on the hazardous state of the work environment and information on whether the worker falls through a display, and상기 작업환경의 유해 상태 정보와 상기 작업자의 낙상 여부 정보를 네트워크를 통하여 다른 작업자 또는 관제센터에 전달하도록 하는 제어부를 포함하는 지능형 웨어러블 위험 상태 판단 장치.An intelligent wearable danger state determination device comprising a control unit configured to transmit information on a hazardous state of the work environment and information on whether the worker is falling or not to another worker or a control center through a network.
- 제1항에 있어서,The method of claim 1,상기 가스 센서는,The gas sensor,판독회로(ROIC, Read Out Integrated Circuit)를 포함하고, 산소, 가연성 가스, 황하수소, 온도, 습도 및 일산화 탄소 중에서 적어도 하나를 측정할 수 있는 지능형 웨어러블 위험 상태 판단 장치.An intelligent wearable hazard condition determination device that includes a read out integrated circuit (ROIC) and can measure at least one of oxygen, combustible gas, hydrogen sulfide, temperature, humidity, and carbon monoxide.
- 제1항에 있어서,The method of claim 1,상기 낙상 판단부는,The fall determination unit,상기 자이로 센서로부터 측정되는 값이 기준 값 보다 크거나, 가속도 센서로부터 측정되는 값이 기준 값보다 크거나, 상기 카메라에 의해 촬영된 영상의 픽셀 값의 변화량이 기준 값보다 크면 상기 작업자가 단순 낙상한 것으로 판단하는 지능형 웨어러블 위험 상태 판단 장치.If the value measured from the gyro sensor is greater than the reference value, the value measured from the acceleration sensor is greater than the reference value, or the amount of change in the pixel value of the image captured by the camera is greater than the reference value, the operator simply falls. An intelligent wearable dangerous state determination device that determines that it is.
- 제3항에 있어서,The method of claim 3,상기 낙상 판단부는,The fall determination unit,상기 낙상한 작업자가 낙상하기 전의 주변 환경이 유해 상태로 판단되면, 상기 작업자는 유해 상태로 인해 낙상한 것으로 판단하는 지능형 웨어러블 위험 상태 판단 장치.An intelligent wearable danger state determination device that determines that the worker who has fallen due to a fall due to the harmful state is determined to be in a hazardous state when the surrounding environment before the fall of the fallen worker is determined to be in a hazardous state.
- 제1항에 있어서,The method of claim 1,상기 제어부는,The control unit,상기 작업자 주변이 유해 상태인 것으로 판단되면, 상기 작업자로부터 일정 거리에 있는 다른 작업자에게 위험 알람 신호를 전달하고, If it is determined that the vicinity of the worker is in a hazardous state, a danger alarm signal is transmitted to another worker at a certain distance from the worker,상기 작업자가 낙상한 것으로 판단하면, 알람이 발생시키고 다른 작업자가 착용한 지능형 웨어러블 복합환경 측정 장치로 상기 작업자의 낙상 사실을 전달하는 지능형 웨어러블 위험 상태 판단 장치.When it is determined that the worker has fallen, an alarm is generated and an intelligent wearable danger state determination device that communicates the fall of the worker to an intelligent wearable complex environment measuring device worn by another worker.
- 제5항에 있어서,The method of claim 5,상기 제어부는, The control unit,상기 작업자가 단순 낙상한 것인지, 유해 상태에 의해 낙상한 것인지를 구분하여 상기 관제센터에 전달하는 지능형 웨어러블 위험 상태 판단 장치.An intelligent wearable danger state determination device that distinguishes whether the worker has simply fallen or has fallen due to an unhealthy condition, and transmits it to the control center.
- 제1항에 있어서,The method of claim 1,상기 학습부는, The learning unit,작업 환경의 층수가 높을수록 상기 자이로 센서 및 가속도 센서에 대한 가중치를 증가시켜 학습시키고, As the number of floors in the work environment increases, the weight of the gyro sensor and the acceleration sensor is increased to learn,작업 환경의 층수가 낮을수록 상기 자이로 센서 및 가속도 센서에 대한 가중치를 감소시켜 학습시키는 지능형 웨어러블 위험 상태 판단 장치.An intelligent wearable danger state determination device that learns by reducing weights for the gyro sensor and acceleration sensor as the number of floors in the work environment decreases.
- 제7항에 있어서,The method of claim 7,상기 제어부는, The control unit,상기 작업환경에 부착된 비콘 신호를 통하여 상기 작업자의 현재 층수를 추정하는 지능형 웨어러블 위험 상태 판단 장치.An intelligent wearable danger state determination device that estimates the number of floors of the worker through a beacon signal attached to the work environment.
- 지능형 웨어러블 위험 상태 판단 장치를 이용한 위험상태 판단 방법에 있어서,In the method for determining a dangerous state using an intelligent wearable dangerous state determining device,탈부착이 가능한 가스 센서를 이용하여 작업 환경 주변의 가스의 농도를 측정하는 단계, Measuring the concentration of gas around the working environment using a detachable gas sensor,상기 측정된 가스의 농도로부터 작업자 주변의 유해 상태 여부를 판단하는 단계,Determining whether there is a harmful state around the worker from the measured concentration of the gas,자이로 센서 및 가속도 센서를 이용하여 작업자의 균형 상태 및 동작을 측정하고, 카메라를 이용하여 상기 작업자의 주변 환경을 촬영하는 단계,Measuring the balance state and motion of the worker using a gyro sensor and an acceleration sensor, and photographing the surrounding environment of the worker using a camera,상기 자이로 센서, 가속도 센서 및 카메라의 측정값, 작업자가 위치한 층수에 따른 상기 작업자의 낙상 여부를 머신러닝(Machine Learning)기법에 적용하여 학습 모델을 생성하는 단계,Generating a learning model by applying a fall of the worker according to the measured values of the gyro sensor, acceleration sensor and camera, and the number of floors on which the worker is located to a machine learning technique,상기 자이로 센서의 측정 값, 가속도 센서의 측정 값, 촬영 영상의 픽셀 변화값 및 상기 작업자의 현재 위치 층수를 상기 학습 모델에 적용하여 상기 작업자의 낙상 여부를 판단하는 단계,Determining whether or not the worker falls by applying the measured value of the gyro sensor, the measured value of the acceleration sensor, the pixel change value of the photographed image, and the number of floors of the worker's current location to the learning model,상기 작업환경의 유해 상태 정보와 상기 작업자의 낙상 여부 정보를 디스플레이를 통하여 출력하는 단계, 그리고 Outputting information on the hazardous state of the work environment and information on whether the worker falls through a display, and상기 작업환경의 유해 상태 정보와 상기 작업자의 낙상 여부 정보를 네트워크를 통하여 다른 작업자 또는 관제센터에 전달하도록 하는 단계를 포함하는 위험 상태 판단 방법.And transmitting information on the hazardous state of the work environment and information on whether the worker has fallen to another worker or a control center through a network.
- 제9항에 있어서,The method of claim 9,상기 가스 센서는,The gas sensor,판독회로(ROIC, Read Out Integrated Circuit)를 포함하고, 산소, 가연성 가스, 황하수소, 온도, 습도 및 일산화 탄소 중에서 적어도 하나를 측정할 수 있는 위험 상태 판단 방법.A method for determining a hazardous state that includes a read out integrated circuit (ROIC) and can measure at least one of oxygen, combustible gas, hydrogen sulfide, temperature, humidity, and carbon monoxide.
- 제9항에 있어서,The method of claim 9,상기 낙상 여부를 판단하는 단계는,The step of determining whether the fall or not,상기 자이로 센서로부터 측정되는 값이 기준 값 보다 크거나, 가속도 센서로부터 측정되는 값이 기준 값보다 크거나, 상기 카메라에 의해 촬영된 영상의 픽셀 값의 변화량이 기준 값보다 크면 상기 작업자가 단순 낙상한 것으로 판단하는 위험 상태 판단 방법.If the value measured from the gyro sensor is greater than the reference value, the value measured from the acceleration sensor is greater than the reference value, or the amount of change in the pixel value of the image captured by the camera is greater than the reference value, the operator simply falls. How to judge a dangerous state that is judged to be.
- 제11항에 있어서,The method of claim 11,상기 낙상 여부를 판단하는 단계는,The step of determining whether the fall or not,상기 낙상한 작업자가 낙상하기 전의 주변 환경이 유해 상태로 판단되면, 상기 작업자는 유해 상태로 인해 낙상한 것으로 판단하는 위험 상태 판단 방법.A method of determining a dangerous state of determining that the fallen worker has fallen due to the harmful state when the surrounding environment before the fall is determined to be in a hazardous state.
- 제9항에 있어서,The method of claim 9,상기 다른 작업자 또는 관제센터에 전달하도록 하는 단계는,The step of transmitting to the other operator or control center,상기 작업자 주변이 유해 상태인 것으로 판단되면, 상기 작업자로부터 일정 거리에 있는 다른 작업자에게 위험 알람 신호를 전달하고, If it is determined that the vicinity of the worker is in a hazardous state, a danger alarm signal is transmitted to another worker at a certain distance from the worker,상기 작업자가 낙상한 것으로 판단하면, 알람이 발생시키고 다른 작업자가 착용한 지능형 웨어러블 복합환경 측정 장치로 상기 작업자의 낙상 사실을 전달하는 위험 상태 판단 방법.When it is determined that the worker has fallen, an alarm is generated and a risk state determination method of transmitting the fact of the worker's fall to an intelligent wearable complex environment measuring device worn by another worker.
- 제13항에 있어서,The method of claim 13,상기 다른 작업자 또는 관제센터에 전달하도록 하는 단계는, The step of transmitting to the other operator or control center,상기 작업자가 단순 낙상한 것인지, 유해 상태에 의해 낙상한 것인지를 구분하여 상기 관제센터에 전달하는 위험 상태 판단 방법.A method for determining a dangerous state by distinguishing whether the worker has simply fallen or has fallen due to a hazardous condition, and delivers it to the control center.
- 제9항에 있어서,The method of claim 9,상기 학습 모델을 생성하는 단계는, Generating the learning model,작업 환경의 층수가 높을수록 상기 자이로 센서 및 가속도 센서에 대한 가중치를 증가시켜 학습시키고, As the number of floors in the work environment increases, the weight of the gyro sensor and the acceleration sensor is increased to learn,작업 환경의 층수가 낮을수록 상기 자이로 센서 및 가속도 센서에 대한 가중치를 감소시켜 학습시키는 위험 상태 판단 방법.As the number of floors in the work environment decreases, weights for the gyro sensor and the acceleration sensor are reduced and learned.
- 제15항에 있어서,The method of claim 15,상기 다른 작업자 또는 관제센터에 전달하도록 하는 단계는,The step of transmitting to the other operator or control center,상기 작업환경에 부착된 비콘 신호를 통하여 상기 작업자의 현재 층수를 추정하는 위험 상태 판단 방법.A method of determining a danger state for estimating the current number of floors of the worker through a beacon signal attached to the work environment.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR10-2019-0104518 | 2019-08-26 | ||
KR1020190104518A KR102123008B1 (en) | 2019-08-26 | 2019-08-26 | Apparatus for intelligent wearable hazard determination device using complex environment measurement and method thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021040126A1 true WO2021040126A1 (en) | 2021-03-04 |
Family
ID=71081652
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2019/013719 WO2021040126A1 (en) | 2019-08-26 | 2019-10-18 | Intelligent wearable dangerous state determination device using complex environment measurement, and method therefor |
Country Status (2)
Country | Link |
---|---|
KR (1) | KR102123008B1 (en) |
WO (1) | WO2021040126A1 (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112533166A (en) * | 2020-11-27 | 2021-03-19 | 上海建工集团股份有限公司 | Mobile information transmission instrument |
KR102582490B1 (en) | 2021-06-30 | 2023-09-22 | 한성대학교 산학협력단 | Apparatus and method for safety management |
CN117877198B (en) * | 2024-03-12 | 2024-05-17 | 成都蜀诚通信技术有限公司 | Safe operation and maintenance system applied to construction site |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140349707A1 (en) * | 2012-02-01 | 2014-11-27 | Young-ki Bang | Gas detection system and method using smart phone |
KR101663572B1 (en) * | 2016-03-30 | 2016-10-07 | (주)네트 | Monitoring system of working environment for ensuring safety of workers |
KR20180059356A (en) * | 2016-11-25 | 2018-06-04 | (재)한국재난안전기술원 | Integrated control system for urgent response against disaster situations including chemical hazard, and disaster response method using thereof |
KR20180097091A (en) * | 2017-02-22 | 2018-08-30 | 광주과학기술원 | Apparatus and method for estimating fall risk based on machine learning |
KR20190009481A (en) * | 2017-07-19 | 2019-01-29 | 주식회사 선경 이.엔.아이 | Realtime Process Safety Management System based worker and facility information of position and status |
-
2019
- 2019-08-26 KR KR1020190104518A patent/KR102123008B1/en active IP Right Grant
- 2019-10-18 WO PCT/KR2019/013719 patent/WO2021040126A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140349707A1 (en) * | 2012-02-01 | 2014-11-27 | Young-ki Bang | Gas detection system and method using smart phone |
KR101663572B1 (en) * | 2016-03-30 | 2016-10-07 | (주)네트 | Monitoring system of working environment for ensuring safety of workers |
KR20180059356A (en) * | 2016-11-25 | 2018-06-04 | (재)한국재난안전기술원 | Integrated control system for urgent response against disaster situations including chemical hazard, and disaster response method using thereof |
KR20180097091A (en) * | 2017-02-22 | 2018-08-30 | 광주과학기술원 | Apparatus and method for estimating fall risk based on machine learning |
KR20190009481A (en) * | 2017-07-19 | 2019-01-29 | 주식회사 선경 이.엔.아이 | Realtime Process Safety Management System based worker and facility information of position and status |
Also Published As
Publication number | Publication date |
---|---|
KR102123008B1 (en) | 2020-06-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021040126A1 (en) | Intelligent wearable dangerous state determination device using complex environment measurement, and method therefor | |
WO2019132112A1 (en) | System for monitoring abnormal states of facilities to be managed | |
WO2012005559A2 (en) | Method and portable terminal for estimating step length of pedestrian | |
WO2019143185A1 (en) | Electronic device and method of detecting status of battery thereof | |
WO2014069776A1 (en) | Head mounted display and method of outputting audio signal using the same | |
WO2014007533A1 (en) | Method and apparatus for controlling sleep mode in portable terminal | |
WO2013168920A1 (en) | Waterproof inspection device for terminal | |
WO2017099479A1 (en) | Internet-of-things system for recognizing user behavior and controlling things | |
EP3860446A1 (en) | Electronic device for obtaining blood pressure value using pulse wave velocity algorithm and method for obtaining blood pressure value | |
WO2019124816A1 (en) | On-site worker safety management system including enclosed space | |
WO2014046313A1 (en) | Method for automatically recognizing and setting attachment and device therefor | |
KR20130021060A (en) | Removable smart module for helmet | |
WO2023113058A1 (en) | Drone control method for precise landing | |
WO2014073728A1 (en) | Smart helmet having black box function and operation method therefor | |
WO2016140389A1 (en) | Wearable device and system for user monitoring | |
WO2022098181A1 (en) | System and method for battery diagnosis according to altitude using atmospheric pressure sensor | |
CN113280265A (en) | Working condition identification method and device, computer equipment and storage medium | |
WO2020190087A1 (en) | Gas detection apparatus, detection method, and operating method | |
WO2021162269A1 (en) | Wireless charging method and electronic device supporting same | |
WO2021025492A1 (en) | Headgear-type device for hazardous air quality warning and air quality improvement | |
WO2020145653A1 (en) | Electronic device and method for recommending image capturing place | |
WO2017034254A1 (en) | Fire extinguisher management apparatus and fire extinguisher | |
WO2020096311A1 (en) | Electronic device and method for identifying occurrence of hypotension | |
WO2019139409A1 (en) | Method and electronic device for correcting and generating data related to outside air on basis of movement | |
WO2021086005A1 (en) | Electronic device, and method for providing evacuation information according to occurrence of disaster by using same |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19943441 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 19943441 Country of ref document: EP Kind code of ref document: A1 |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 12/09/2022) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 19943441 Country of ref document: EP Kind code of ref document: A1 |