KR-20260064243-A - FIRE PREVENTION SYSTEM USING INFRARED-BASED SENSOR AND ARTIFICIAL INTELLIGENCE MODEL

KR20260064243AKR 20260064243 AKR20260064243 AKR 20260064243AKR-20260064243-A

Abstract

A system for predicting the occurrence of a fire is provided. The system includes a sensor device for measuring the temperature of at least one target equipment within a target area, a server device for identifying the possibility of a fire based on sensing data received from the sensor device, and an alarm device for providing a danger alarm when the identified possibility of a fire exceeds a threshold. The server device can acquire sensing data regarding the temperature of each part of the target equipment through the sensor device and input the sensing data into at least one artificial intelligence model for fire prediction to identify the possibility of a fire.

Inventors

주재인
박영배
강동권

Assignees

주식회사 엠피하이테크

Dates

Publication Date: 20260507
Application Date: 20241031

Claims (9)

In a system for predicting fire occurrence, A sensor device for measuring the temperature of at least one target device within a target area; A server device that identifies the possibility of a fire based on sensing data received from the sensor device; and It includes an alarm device that provides a danger alarm when the probability of the identified fire occurring is above a threshold; and The above server device is, Sensing data regarding the temperature of each part of the target equipment is obtained through the sensor device, and A system for identifying the possibility of a fire by inputting the sensing data into at least one artificial intelligence model for fire prediction.
In paragraph 1, The sensor device above is, At least one first sensor device including an IR sensor; and at least one second sensor device including a thermal imaging camera; comprising, The above server device is, When a temperature of a certain value or higher is detected at least one point through the first sensor device, the second sensor device is controlled to capture a heat distribution image of an area including the point. A system for identifying the temperature of each part of at least one piece of equipment based on a heat distribution image captured through the second sensor device.
In paragraph 1, The above server device is, A thermal image obtained through the sensor device is input into an object recognition model to identify at least one target device included in the thermal image and each part constituting the target device, and A system that determines the likelihood of a fire by inputting the temperature of each part identified based on the above thermal image into a fire prediction model.
In paragraph 1, Time series data of a thermal image obtained through the sensor device is input into a multivariate time series model to obtain predicted values for the thermal image, and The above predicted value for the thermal image is input into an object recognition model to identify at least one target device included in the thermal image and each part constituting the target device, and A system that determines the likelihood of fire based on the temperature of each part identified based on the above-mentioned predicted value for a thermal image.
In paragraph 4, The above server device is, A system that inputs the temperature, humidity, and current of the target area and the target equipment, in addition to the time series data of the thermal image, into the multivariate time series model.
In paragraph 5, The above multivariate time series model is, A first module including a transformer-based encoder-decoder; and It includes a second module composed of an encoder, and The above server device is, First feature information is obtained by inputting time-series data of a thermal image obtained through the sensor device into the encoder of the first module, and The temperature, humidity, and current of the target area and the target equipment are input into the second module to obtain second feature information, and A system for obtaining the predicted value for a thermal image by inputting combined feature information, which is a combination of the first feature information and the second feature information, into a decoder of the first module.
In paragraph 5, The above artificial intelligence model is, A first module including a transformer-based encoder-decoder; and It includes a second module composed of an encoder, and The above server device is, First feature information is obtained by inputting time-series data of a thermal image acquired through the sensor device into the encoder of the first module, and Time series data regarding the temperature, humidity, and current of the target equipment of the above target area are input into the second module to obtain second feature information, and A system for predicting a thermal image by inputting combined feature information, which is a combination of the first feature information and the second feature information, into a decoder of the first module.
In paragraph 1, The above server device is, A system that generates a control signal for automatic control of at least one cooling equipment located within the target area and related to cooling when the probability of fire identified above is above a threshold.
In a method of operation of a system for predicting the occurrence of fire, A sensor device generates sensing data for the temperature of at least one target device within a target area; A server device identifies the possibility of a fire based on sensing data received from the sensor device; and The alarm device includes the step of providing a danger alarm when the probability of the identified fire occurring is greater than or equal to a threshold; The step of identifying the possibility of the above fire occurring is, Sensing data regarding the temperature of each part of the target equipment is obtained through the sensor device, and A method of operation of a system for identifying the possibility of a fire by inputting the sensing data into at least one artificial intelligence model for fire prediction.

Description

Fire Prevention System Using Infrared-Based Sensor and Artificial Intelligence Model The present disclosure relates to a system for predicting fire in advance, and more specifically, to a system for predicting fire by analyzing the temperature detected based on an infrared sensor based on deep learning. In conventional fire detection systems, when a fire is detected by a thermal imaging camera, information is transmitted from the fire video and fire sensors to an integrated monitoring system and an IoT-based platform for verification via a smartphone app, and a report is made using an emergency dispatch service. When a fire occurs, the integrated monitoring system analyzes the screen and saves the fire event, verifies the authenticity of the fire, and then reports it to the fire department. As such, current fire detection systems proceed with reporting based on the premise that a fire has already occurred; consequently, the fire has already taken place and property damage has occurred. FIG. 1 is a block diagram for explaining each device constituting a system according to one embodiment of the present disclosure, FIG. 2 is a block diagram for explaining the configuration of a server device according to one embodiment of the present disclosure, FIG. 3 is a block diagram illustrating the configuration of a system including various types of sensor devices according to one embodiment of the present disclosure, FIG. 4 is an algorithm for explaining the operation of a server device that activates a first sensor device including an IR sensor and a second sensor device including a thermal imaging camera according to one embodiment of the present disclosure, FIG. 5 is a diagram illustrating the operation of an electronic device according to an embodiment of the present disclosure performing fire prediction based on a thermal image using an object recognition model and a fire prediction model. FIG. 6a is a diagram illustrating the operation of an electronic device according to an embodiment of the present disclosure to perform fire prediction by generating a predicted value for a thermal image through a multivariate time series model, and FIG. 6b is a diagram illustrating the structure of a multivariate time series model according to one embodiment of the present disclosure. Before specifically describing the present disclosure, the method of description in the specification and drawings is described. First, the terms used in this specification and claims have been selected based on general terms considering their functions in the various embodiments of this disclosure. However, these terms may vary depending on the intent of those skilled in the art, legal or technical interpretations, and the emergence of new technologies. Additionally, some terms have been arbitrarily selected by the applicant. Such terms may be interpreted according to the meanings defined in this specification; in the absence of specific definitions, they may be interpreted based on the overall content of this specification and common technical knowledge in the relevant field. In addition, the same reference numbers or symbols described in each drawing attached to this specification represent parts or components that perform substantially the same function. For convenience of explanation and understanding, the same reference numbers or symbols are used to describe different embodiments. That is, even if components having the same reference number are all depicted in multiple drawings, the multiple drawings do not imply a single embodiment. Additionally, in this specification and claims, terms including ordinal numbers, such as "first," "second," etc., may be used to distinguish between components. These ordinal numbers are used to distinguish identical or similar components from one another, and the meaning of the terms should not be limited by the use of such ordinal numbers. For example, the order of use or arrangement of components combined with such ordinal numbers should not be restricted by the number. If necessary, each ordinal number may be used interchangeably. In this specification, singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, terms such as "comprising" or "consisting of" are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. In the embodiments of the present disclosure, terms such as "module," "unit," "part," etc. are used to refer to a component that performs at least one function or operation, and such component may be implemented in hardware or software, or a combination of hardware and software. Additionally, a plurality of "modules," "units," "parts," etc. may be integrated into at least one mod