Fire protection method and fire protection system
A fire protection system according to an embodiment of the inventive concept includes a plurality of sensors having different address values, detecting fire occurrence, generating a fire alarm, and performing Radio Frequency (RF) communication with each other, a first server configured to perform RF communication with each of the plurality of sensors, and a second server configured to receive big data from the outside and communicate with the first server, wherein the second server includes a data collection unit configured to collect sensor data measured from each of the plurality of sensors and the big data, a data extraction unit configured to extract fire data based on information collected by the data collection unit, and a complex event processing unit configured to process complex events based on the fire data.
1 . A fire protection system comprising:
a plurality of sensors having different address values, configured to detect fire occurrence, generate a fire alarm, and perform Radio Frequency (RF) communication with each other;
a first server configured to perform RF communication with each of the plurality of sensors; and
a second server configured to receive external data from an external server and communicate with the first server,
wherein the second server comprises:
a data collection unit configured to collect sensor data measured by each of the plurality of sensors and the external data;
a data extraction unit configured to extract fire data based on information collected by the data collection unit; and
a complex event processing unit configured to process a complex event based on the fire data and to output mutually different fire evaluation criteria by space, use, and fuel type based on the fire data,
a guide unit configured to output mutually different fire occurrence probabilities by space, use, and fuel type based on the fire evaluation criteria and the information collected by the data collection unit; and
a simulation unit configured to receive the mutually different fire occurrence probabilities by space, use, and fuel type from the guide unit and simulate and output a virtual 3D plant facility model responsive to receiving the mutually different fire occurrence probabilities by space, use, and fuel type,
wherein the guide unit is further configured to output a preliminary warning message to the simulation unit when the fire occurrence probability is equal to or greater than a predetermined value, and
the simulation unit is further configured to detect a fire risk based on the virtual 3D plant facility model.
2 . The fire protection system of claim 1 , wherein the data extraction unit comprises a learning model for machine learning the information to determine whether the information corresponds to the fire data.
3 . The fire protection system of claim 1 , wherein the second server further comprises a communication unit for transmitting an abnormal symptom early detection signal to a party based on the fire data.
4 . The fire protection system of claim 1 , further comprising an image recording unit for taking an image,
wherein the data collection unit further collects the image,
wherein the second server further comprises an image analysis unit for analyzing the image.
5 . The fire protection system of claim 1 , wherein the first server further comprises a memory for storing the information.
6 . The fire protection system of claim 1 , wherein the complex event processing unit receives an event of the fire data, fuses the event to process the complex event, and classifies the fire data based on the complex event.
7 . The fire protection system of claim 1 , wherein the complex event processing unit outputs a fire evaluation criteria for each space, use, or fuel based on the fire data.
8 . The fire protection system of claim 7 , wherein the second server determines a fire situation by comparing the fire evaluation criteria and sensor data measured from each of the plurality of sensors.
9 . The fire protection system of claim 1 , wherein each of the plurality of sensors senses at least one of vibration, oil pressure, and temperature,
wherein the fire data comprises an outlier of each of vibration, hydraulic pressure, and temperature.
10 . The fire protection system of claim 9 , wherein the second server determines whether to output a preliminary warning message based on the outlier and the sensor data.
11 . The fire protection system of claim 1 , wherein the complex event processing unit processes the complex event in real time.
12 . A fire protection method comprising:
measuring sensor data by a plurality of sensors configured to sense a fire occurrence and generate a fire alarm;
collecting, by a data collection unit, external data received from an external server and the sensor data to store the collected external data and sensor data as information;
extracting, by a data extraction unit, fire data based on the information; and
processing, by a complex event processing unit, a complex event based on the fire data,
outputting, by the complex event processing unit, mutually different fire evaluation criteria by space, use, and fuel type based on the fire data;
outputting, by a guide unit, mutually different fire occurrence probabilities by space, use, and fuel type based on the fire evaluation criteria and the information;
receiving, by a simulation unit, the mutually different fire occurrence probabilities by space, use, and fuel type and outputting a virtual 3D plant facility model responsive to receiving the mutually different fire occurrence probabilities by space, use, and fuel type;
outputting, by the guide unit, a preliminary warning message when the fire occurrence probability is equal to or greater than a predetermined value; and
detecting, by the simulation unit, a fire risk based on the virtual 3D plant facility model.
13 . The fire protection method of claim 12 , further comprising outputting fire evaluation criteria by space, use, and fuel based on the complex event.
14 . The fire protection method of claim 12 , wherein the extracting of the fire data comprises:
performing machine learning on the information; and
outputting a learning model for extracting the fire data from the information.
15 . The fire protection method of claim 12 , wherein the processing of the complex event comprises:
receiving an event of the fire data and processing the complex event by fusing the event; and
classifying the fire data based on the complex event.
16 . The fire protection system of claim 1 , wherein the external data includes data related to space, use, fuel, or facility of a power plant.
17 . The fire protection system of claim 1 , wherein the data collection unit outputs information to the data extraction unit based on the collected sensor data and external data, the output information including measured values including at least one of vibration, oil pressure, sound, valve, harmful gas, heat, temperature, smoke, flame, and explosion, and the data extraction unit extracts the fire data based on the output information.
18 . The fire protection system of claim 8 , wherein the complex event includes an event in which noxious gas, heat, and smoke exceed a facility-specific criterion defined in the fire evaluation criteria.
19 . The fire protection system of claim 1 , wherein the complex event processing unit outputs fire evaluation criteria for particular facilities or equipment in a plant based on the fire data, and the second server determines a fire situation in the particular facilities or equipment by comparing the fire evaluation criteria and sensor data associated with the particular facilities or equipment.