Building fire-fighting monitoring system
By combining smoke sensors, aspiration smoke detectors, and anemometers in the fire protection system, dynamically adjusting data weights, and acquiring information using thermal imagers, the problem of insufficient accuracy and timeliness in smoke monitoring is solved, enabling more accurate and timely fire risk assessment and early warning.
Patent Information
- Application Number
- CN202510927876.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-07
- Publication Date
- 2025-09-16
AI Technical Summary
The existing fire protection system is not accurate and timely enough in smoke monitoring in special places with strong airflow, such as data center rooms and clean rooms, resulting in inaccurate fire risk assessment.
By combining smoke sensors and suction smoke detectors, the airflow data is monitored by an anemometer to dynamically adjust the data weight, and thermal imaging information is obtained by combining a thermal imager to achieve real-time, accurate and timely monitoring of smoke data.
It improves the accuracy and timeliness of smoke monitoring, can detect fire risks at an earlier stage, reduce misjudgments, ensure the accuracy and timeliness of fire warnings, and coordinate fire-fighting equipment for effective response.
Smart Images
Figure CN120656301A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of Internet of Things fire monitoring, and in particular to a building fire monitoring system. Background Art
[0002] The management of building fire protection is related to the safety of people's lives and property. With the rapid development of Internet of Things technology, intelligent fire protection systems have gradually become popular. They obtain real-time status data inside the building through detection sensors, judge its fire risk through analysis, and link fire protection equipment, smoke exhaust systems, broadcast systems, lighting systems and management platforms. Early detection and early warning can be achieved, and thus early fires can be effectively suppressed and the fire can be prevented from spreading.
[0003] Existing fire protection systems mainly rely on temperature sensors and smoke sensors to judge the fire risk inside buildings. The temperature sensor can detect the ambient temperature inside the building, and the smoke sensor can determine visible and invisible combustion particles. Through temperature data and particle concentration data, the fire risk inside the building can be monitored in real time. When an abnormality is detected, a timely warning is issued, thereby suppressing the occurrence and spread of fire.
[0004] The existing fire protection system can respond to fire warnings in most scenarios, but its monitoring method has certain limitations in some special places. For example, in places with strong airflow such as data center computer rooms and clean rooms, the smoke sensor will have certain errors in monitoring the real-time smoke concentration, which will lead to low accuracy of the judgment results. If an aspirating smoke detector is used, although it can greatly improve the accuracy of the judgment, its monitoring method is regular monitoring, which has poor real-time performance and cannot meet the real-time requirements. Therefore, improving the accuracy and timeliness of smoke monitoring is the fundamental problem to be solved by the present invention. Summary of the Invention
[0005] The purpose of the present invention is to provide a building fire monitoring system to solve the following technical problems: How to improve the accuracy and timeliness of smoke monitoring.
[0006] The purpose of the present invention can be achieved through the following technical solutions: A building fire monitoring system, comprising: A smoke sensor and an inhalation smoke detector, wherein the smoke sensor is used to monitor first smoke data at the building air duct in real time; the inhalation smoke detector is used to sample and monitor second smoke data at the building air duct; Thermal imager, used to obtain thermal imaging information inside the building; Anemometers are installed at the entrance and exit of building air ducts to monitor real-time airflow data; The fire monitoring unit is used to dynamically adjust the first smoke data and the second smoke data according to the real-time airflow data, obtain the smoke data, and perform risk detection on the building according to the smoke data and thermal imaging information.
[0007] Furthermore, the process of obtaining smoke data includes: Obtain the real-time airflow size change curve Af(t) within the sliding window period, and determine the real-time selection ratio of the first smoke data and the second smoke data based on the real-time airflow size change curve Af(t) ; Dividing the period according to the collection time point of the second smoke data; Through the equation Calculate and obtain the particle concentration C(t), and use the particle concentration C(t) as smoke data; in, Indicates the starting time point of the cycle in which the current time point is located. Indicates the end time of the cycle at the current time point. is the real-time particle concentration in the first smoke data, is the collected particle size concentration value of the period at the current time point in the second smoke data, .
[0008] Furthermore, the first smoke data and the second smoke data are selected in a ratio of The determination process includes: Through the equation Calculate the real-time selection coefficient X(t), and determine the corresponding real-time selection ratio according to the interval of the real-time selection coefficient X(t) value. ; Where Sw(t) is the real-time airflow velocity, St=(S1+S2) / 2, Sp=(S2-S1) / 2, S1 and S2 are airflow velocity thresholds, and S1<S2, is the discreteness reference value, is the real-time airflow velocity dispersion coefficient, and its acquisition process includes: selecting n time points at a preset interval in a fixed period before the current time point t, and using the equation Calculate the air flow velocity dispersion coefficient , i∈[1,n], represents the i-th time point.
[0009] Furthermore, the process of risk detection of buildings based on smoke data and thermal imaging information includes: Determine whether the smoke data and thermal imaging information meet the risk trigger conditions: When it is determined that one or more risk triggering conditions exist, a fire alarm will be triggered immediately; Otherwise, a potential risk assessment is conducted based on smoke data and thermal imaging information, and a fire warning is triggered based on the assessed risk.
[0010] Furthermore, the process of determining whether the smoke data meets the risk trigger conditions includes: When the real-time particulate matter concentration in the smoke data exceeds the preset threshold, it is determined that the risk trigger condition has been met; When the increase in the real-time particulate matter concentration in the smoke data per unit time exceeds the preset increment threshold, it is judged that the risk trigger condition has been met; When the smoke risk value is obtained based on the smoke data When the corresponding threshold is exceeded, it is determined that the risk trigger condition has been reached. The calculation model of the smoke risk value is: ,in, express The maximum value of C(t) during the period, express The mean value of C(t) within the period, is the adjustment coefficient, >1, Set the comparison value for the particle concentration, f(x) is a positive function, when x>0, f(x)=x, when x≤0, f(x)=0, express The overall slope of C(t) during the period, Sets the comparison value for the particle concentration slope.
[0011] Furthermore, the process of determining whether the thermal imaging information meets the risk triggering conditions includes: When the highest temperature value in the thermal imaging information exceeds the temperature threshold, it is determined that the risk trigger condition has been met; When the maximum temperature rise value per unit time in the thermal imaging information exceeds the temperature rise threshold, it is determined that the risk trigger condition has been met; When the temperature risk value obtained based on thermal imaging information When the corresponding threshold is exceeded, it is determined that the risk trigger condition has been reached. The calculation model of the temperature risk value is: , where T(t) is the real-time temperature, express The maximum value of T(t) within the time period, Set the comparison value for the temperature, The maximum value of T(t) exceeds The area value of the corresponding region is is the heat source area threshold, is the reference value of the heat source area, express The overall slope of T(t) during the period, Set the comparison value for the temperature rise.
[0012] Furthermore, the process of potential risk assessment includes: Through the equation Calculate the real-time risk value R(t). When the real-time risk value R(t) exceeds the risk threshold, it is determined that there is a potential risk. Smoke risk value The corresponding threshold, is the temperature risk value The corresponding threshold, is the weight adjustment coefficient.
[0013] Furthermore, the contents of fire warning include cutting off non-fire power supply, starting the smoke exhaust system, and starting the emergency lighting and evacuation indication system.
[0014] Beneficial effects of the present invention: (1) The present invention dynamically adjusts the weights of the first smoke data and the second smoke data through the real-time airflow data monitored by the anemometer. Therefore, when the airflow velocity is too large or too low, resulting in insufficient monitoring accuracy of the smoke sensor, the weight of the second smoke data obtained by the suction smoke detector is increased, thereby improving the accuracy of the monitoring result. When the airflow state is normal, the continuity of the monitoring result is improved by increasing the weight of the first smoke data, that is, the timeliness of the monitoring result is improved. The fire risk inside the building is judged by combining the acquired smoke data with the thermal imaging data obtained by the thermal imager, thereby improving the accuracy and timeliness of the judgment. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] The present invention will be further described below with reference to the accompanying drawings.
[0016] Figure 1 It is a logic block diagram of the building fire monitoring system of the present invention. DETAILED DESCRIPTION
[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.
[0018] In one embodiment, a building fire monitoring system is provided. Figure 1As shown, the system includes a thermal imager, an anemometer, a fire monitoring unit, a smoke sensor and an inhalation smoke detector, wherein the smoke sensor is used to monitor the first smoke data at the building air duct in real time; the inhalation smoke detector is used to sample and monitor the second smoke data at the building air duct; the thermal imager is used to obtain thermal imaging information inside the building; the anemometer is set at the inlet and outlet of the building air duct to monitor real-time airflow data; the fire monitoring unit is used to dynamically adjust the first smoke data and the second smoke data according to the real-time airflow data to obtain smoke data, and perform risk detection on the building based on the smoke data and thermal imaging information. It can be seen from the above scheme that this embodiment adopts a dual smoke detection mode, through the smoke sensor and the inhalation smoke detector The device monitors the smoke status in the building at the same time. The monitoring results of the two are not simply superimposed, but the weights of the first smoke data and the second smoke data are dynamically adjusted through the real-time airflow data monitored by the anemometer. Therefore, when the airflow velocity is too large or too low, resulting in insufficient monitoring accuracy of the smoke sensor, the weight of the second smoke data obtained by the suction smoke detector is increased, thereby improving the accuracy of the monitoring results. When the airflow status is normal, the continuity of the monitoring results is improved by increasing the weight of the first smoke data, that is, the timeliness of the monitoring results is improved. The fire risk inside the building is judged by the acquired smoke data and the thermal imaging data obtained by the comprehensive thermal imager, thereby improving the accuracy and timeliness of the judgment.
[0019] In one embodiment, a process for acquiring smoke data is provided, including: first, acquiring a real-time airflow size change curve Af(t) within a sliding window period, wherein the sliding window period refers to a period of time before a current time point, which is set according to detection data of a smoke sensor. Therefore, the real-time airflow size change curve Af(t) within the sliding window period can accurately adjust the weights of the first smoke data and the second smoke data at the current time point, and determine the real-time selection ratio of the first smoke data and the second smoke data according to the real-time airflow size change curve Af(t). , the specific process includes: through the equation The real-time selection coefficient X(t) is calculated, where Sw(t) is the real-time airflow velocity, St=(S1+S2) / 2, Sp=(S2-S1) / 2, S1 and S2 are airflow velocity thresholds, and S1<S2. S1 and S2 are selected based on the test data of the smoke sensor at different airflow velocities. That is, when the airflow velocity is lower than S1 or higher than S2, the measurement accuracy of the smoke sensor will show obvious errors. The discreteness reference value is obtained by selecting n time points at a preset interval in a fixed period before the current time point t, and using the equation Calculate and obtain, i∈[1,n], represents the i-th time point. Therefore, when the airflow fluctuation state is too large, the real-time selection coefficient X(t) value will also increase. The real-time airflow velocity dispersion coefficient is selected and set according to the test data results. Therefore, the selection weight of the first smoke data and the second smoke data can be determined according to the value of the real-time selection coefficient X(t). The larger the value of the real-time selection coefficient X(t), the higher the selection weight of the second smoke data. Conversely, the higher the selection weight of the first smoke data. Therefore, different intervals are divided according to the numerical range of the real-time selection coefficient X(t), and appropriate selection ratios are set for different intervals. , and satisfies Therefore, the corresponding real-time selection ratio can be determined according to the interval of the real-time selection coefficient X(t) value. ; Then, the period is divided according to the collection time point of the second smoke data. It should be noted that the suction smoke detector is tested regularly according to the set time interval, so the period division is actually determined according to the set data, through the equation Calculate the particle concentration C(t), where: Indicates the starting time point of the cycle in which the current time point is located. Indicates the end time of the cycle at the current time point. is the real-time particle concentration in the first smoke data, is the collected particle size concentration value of the second smoke data at the current time point in the period. It should be noted that, because there is only one set of second smoke data in each divided period, the value of each divided period is It is a fixed value. Therefore, through the process of obtaining the particle matter concentration C(t), the first smoke data and the second smoke data can be dynamically integrated to obtain a more accurate particle matter concentration C(t) as smoke data, thereby improving the accuracy and timeliness of building risk detection.
[0020] In addition, the process of performing risk detection on a building based on smoke data and thermal imaging information includes: determining whether the smoke data and thermal imaging information meet risk trigger conditions respectively; when it is determined that one or more risk trigger conditions are met, a fire alarm is immediately triggered; otherwise, a potential risk assessment is performed based on the smoke data and thermal imaging information, and a fire alarm is triggered based on the assessed risk. The process of determining whether the smoke data meets the risk trigger condition includes: comparing the real-time particle concentration in the smoke data with a preset threshold value, which is set based on empirical data. When the real-time particle concentration in the smoke data exceeds the preset threshold value, it indicates that the smoke concentration in the current building exceeds the normal level, and therefore it is determined that the risk trigger condition is met. At the same time, this embodiment also compares the increment of the real-time particle concentration in the smoke data per unit time with a preset increment threshold value, which is set based on empirical data. Therefore, when the increment of the real-time particle concentration in the smoke data per unit time exceeds the preset increment threshold value, it indicates that the increase in the particle concentration in the current building exceeds the normal fluctuation range, and therefore it is determined that the risk trigger condition is met. In addition, this embodiment also determines the smoke risk value based on the change data of the particle concentration. , compare it with the corresponding threshold, when the smoke risk value obtained based on the smoke data When the corresponding threshold is exceeded, the current smoke risk is judged to be high, and the risk trigger condition is determined to be met. The calculation model of the smoke risk value is: ,in, express The maximum value of C(t) during the period, express The mean value of C(t) within the period, is the adjustment coefficient, >1, the data is set according to the test data. Set the comparison value for the particle concentration, f(x) is a positive function, when x>0, f(x)=x, when x≤0, f(x)=0, express The overall slope of C(t) during the period, Set the comparison value for the particle concentration slope. In the above parameters, the particle concentration setting comparison value and particle concentration slope setting comparison value All settings are selected based on empirical data. It should be noted that the above-mentioned set comparison value is different from the preset threshold. The preset threshold represents the critical safety state of smoke, and the set comparison value represents the average state in the empirical data. Therefore, the set comparison value is smaller than the preset threshold. Therefore, through the calculation process and comparison process of the smoke risk value, the potential safety risks reflected by the smoke data can be further judged, thereby improving the accuracy and sensitivity of the judgment results.
[0021] In the above scheme, the content of the fire warning can be adaptively selected according to the layout of building facilities, including cutting off non-fire power supplies, starting the smoke exhaust system, starting the emergency lighting and evacuation indication system, etc. By linking with the above systems, fire risks can be managed more promptly and the timeliness of response can be improved.
[0022] In addition, the process of determining whether the thermal imaging information meets the risk trigger condition includes: first, comparing the maximum temperature value in the thermal imaging information with the temperature threshold value, the temperature threshold value is set according to empirical data, and it reflects the critical safety state, so when the maximum temperature value in the thermal imaging information exceeds the temperature threshold value, it is determined that the risk trigger condition is met; at the same time, the present embodiment also compares the maximum temperature rise value per unit time in the thermal imaging information with the temperature rise threshold value, the temperature rise threshold value is set according to empirical data, and it reflects the critical safety state of temperature rise, so when the maximum temperature rise value per unit time in the thermal imaging information exceeds the temperature rise threshold value, it is determined that the risk trigger condition is met; in addition, the present embodiment obtains a temperature risk value based on the thermal imaging information , the temperature risk value obtained from thermal imaging information Compare with the corresponding threshold, the corresponding threshold is obtained by fitting the test data, so when the temperature risk value obtained based on the thermal imaging information When the corresponding threshold is exceeded, it is determined that the risk trigger condition has been reached. The calculation model of the temperature risk value is: , where T(t) is the real-time temperature, express The maximum value of T(t) within the time period, Set the comparison value for the temperature, The maximum value of T(t) exceeds The area value of the corresponding region is is the heat source area threshold, is the reference value of the heat source area, express The overall slope of T(t) during the period, The temperature set comparison value is the temperature rise comparison value, wherein the temperature set comparison value and the temperature set comparison value are selected and set according to the empirical data, and the temperature set comparison value is different from the temperature threshold, the temperature rise set comparison value is different from the temperature rise threshold, the set comparison value temperature critical state, the set comparison value represents the average state in the empirical data, so the set comparison value is less than the threshold, in addition, the heat source area threshold and heat source area reference value According to the area distribution of temperature anomaly areas in the empirical data, when the heat source area exceeds , indicating that there is a safety hazard, by comparing the difference with the heat source area reference value By comparing and then judging the degree of risk, the calculation process and comparison process of the temperature risk value can further judge the potential safety risks reflected by the temperature data, thereby improving the accuracy and sensitivity of the judgment results.
[0023] In one embodiment, a process for potential risk assessment based on smoke data and thermal imaging information is provided, including: Calculate the real-time risk value R(t), where: Smoke risk value The corresponding threshold, is the temperature risk value The corresponding threshold, It is the weight adjustment coefficient, which is set according to the test data fitting. Therefore, the real-time risk value R(t) can judge the potential risk by comprehensively considering the temperature status and smoke status, and compare it with the risk threshold. The risk threshold is set according to the simulation data fitting. Therefore, when the real-time risk value R(t) exceeds the risk threshold, it is judged that there is a potential risk. Through the process of potential risk assessment, the potential safety risks in the building can be judged, and according to the judgment results, they can be checked in advance, thereby improving the timeliness of fire prevention.
[0024] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.
Claims
1. A building fire monitoring system, characterized in that: The system comprises: A smoke sensor and an inhalation smoke detector, wherein the smoke sensor is used to monitor first smoke data at the building air duct in real time; the inhalation smoke detector is used to sample and monitor second smoke data at the building air duct; Thermal imager, used to obtain thermal imaging information inside the building; Anemometers are installed at the entrance and exit of building air ducts to monitor real-time airflow data; The fire monitoring unit is used to dynamically adjust the first smoke data and the second smoke data according to the real-time airflow data, obtain the smoke data, and perform risk detection on the building according to the smoke data and thermal imaging information.
2. A building fire monitoring system according to claim 1, characterized in that: The process of obtaining smoke data includes: Obtain the real-time airflow size change curve Af(t) within the sliding window period, and determine the real-time selection ratio of the first smoke data and the second smoke data based on the real-time airflow size change curve Af(t) ; Dividing the period according to the collection time point of the second smoke data; Through the equation Calculate and obtain the particle concentration C(t), and use the particle concentration C(t) as smoke data; in, Indicates the starting time point of the cycle in which the current time point is located. Indicates the end time of the cycle at the current time point. is the real-time particle concentration in the first smoke data, is the collected particle size concentration value of the period at the current time point in the second smoke data, .
3. A building fire monitoring system according to claim 2, characterized in that: The selection ratio of the first smoke data and the second smoke data The determination process includes: Through the equation Calculate the real-time selection coefficient X(t), and determine the corresponding real-time selection ratio according to the interval of the real-time selection coefficient X(t) value. ; Where Sw(t) is the real-time airflow velocity, St=(S1+S2) / 2, Sp=(S2-S1) / 2, S1 and S2 are airflow velocity thresholds, and S1<S2, is the discreteness reference value, is the real-time airflow velocity dispersion coefficient, and its acquisition process includes: selecting n time points at a preset interval in a fixed period before the current time point t, and using the equation Calculate the air flow velocity dispersion coefficient , i∈[1,n], represents the i-th time point.
4. A building fire monitoring system according to claim 2, characterized in that: The process of building risk detection based on smoke data and thermal imaging information includes: Determine whether the smoke data and thermal imaging information meet the risk trigger conditions: When it is determined that one or more risk triggering conditions exist, a fire alarm will be triggered immediately; Otherwise, a potential risk assessment is conducted based on smoke data and thermal imaging information, and a fire warning is triggered based on the assessed risk.
5. A building fire monitoring system according to claim 4, characterized in that: The process of determining whether smoke data meets risk trigger conditions includes: When the real-time particulate matter concentration in the smoke data exceeds the preset threshold, it is determined that the risk trigger condition has been met; When the increase in the real-time particulate matter concentration in the smoke data per unit time exceeds the preset increment threshold, it is judged that the risk trigger condition has been met; When the smoke risk value is obtained based on the smoke data When the corresponding threshold is exceeded, it is determined that the risk trigger condition has been reached. The calculation model of the smoke risk value is: ,in, express The maximum value of C(t) during the period, express The mean value of C(t) within the period, is the adjustment coefficient, >1, Set the comparison value for the particle concentration, f(x) is a positive function, when x>0, f(x)=x, when x≤0, f(x)=0, express The overall slope of C(t) during the period, Sets the comparison value for the particle concentration slope.
6. A building fire monitoring system according to claim 5, characterized in that: The process of determining whether thermal imaging information meets risk trigger conditions includes: When the highest temperature value in the thermal imaging information exceeds the temperature threshold, it is determined that the risk trigger condition has been met; When the maximum temperature rise value per unit time in the thermal imaging information exceeds the temperature rise threshold, it is determined that the risk trigger condition has been met; When the temperature risk value obtained based on thermal imaging information When the corresponding threshold is exceeded, it is determined that the risk trigger condition has been reached. The calculation model of the temperature risk value is: , where T(t) is the real-time temperature, express The maximum value of T(t) within the time period, Set the comparison value for the temperature, The maximum value of T(t) exceeds The area value of the corresponding region is is the heat source area threshold, is the reference value of the heat source area, express The overall slope of T(t) during the period, Set the comparison value for the temperature rise.
7. A building fire monitoring system according to claim 6, characterized in that: The process of potential risk assessment includes: Through the equation Calculate the real-time risk value R(t). When the real-time risk value R(t) exceeds the risk threshold, it is determined that there is a potential risk. Smoke risk value The corresponding threshold, is the temperature risk value The corresponding threshold, is the weight adjustment coefficient.
8. A building fire monitoring system according to claim 4, characterized in that: The contents of fire warning include cutting off non-fire power supply, starting smoke exhaust system, and starting emergency lighting and evacuation indication system.