CN119832679A - Intelligent remote fire control monitoring system based on big data of Internet of things - Google Patents
Intelligent remote fire control monitoring system based on big data of Internet of things Download PDFInfo
- Publication number
- CN119832679A CN119832679A CN202510068422.0A CN202510068422A CN119832679A CN 119832679 A CN119832679 A CN 119832679A CN 202510068422 A CN202510068422 A CN 202510068422A CN 119832679 A CN119832679 A CN 119832679A
- Authority
- CN
- China
- Prior art keywords
- temperature
- early warning
- fire
- data
- threshold value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Fire Alarms (AREA)
Abstract
The invention discloses an intelligent remote fire control monitoring system based on big data of the Internet of things, which comprises a data acquisition layer and a platform layer, wherein the data acquisition layer acquires data through a sensor and then transmits the acquired data to the platform layer, the intelligent remote fire control monitoring system relates to the technical field of fire control monitoring, and in an early warning temperature threshold dynamic generation module, a low temperature range, a medium temperature range and a high temperature range are divided through analyzing annual temperature data of a region where a building is located, and an initial temperature threshold for finding potential fire risks and triggering early warning and an initial temperature change rate threshold for triggering early warning through combining temperature sensor ageing factors, humidity and temperature difference conditions are dynamically adjusted to replace an original static threshold, so that the probability of triggering false alarm is reduced.
Description
Technical Field
The invention relates to the technical field of fire control monitoring, in particular to an intelligent remote fire control monitoring system based on big data of the Internet of things.
Background
An intelligent fire safety monitoring system is a system that utilizes advanced technology and equipment to monitor, prevent and treat fires and other safety risks. These systems typically incorporate various sensors, monitoring devices, data analysis algorithms, and communication techniques to improve the efficiency and accuracy of fire detection, early warning, and handling, and are intended to provide a faster, more reliable response to protect people's lives and properties.
However, most of traditional fire safety monitoring systems are static detection systems, data detection is carried out on users by means of a monitoring sampling mode and an alarm mode which are preset by manufacturers, and when abnormal data are detected, an alarm is triggered, but in daily life, due to the fact that the temperature difference and the humidity difference of a monitored building at different periods are different, and the temperature measurement deviation of a temperature sensor is increased along with the increase of the service time, the monitoring system depending on the static data is easy to trigger false alarm.
Disclosure of Invention
In order to solve the technical problems in the background technology, the invention provides an intelligent remote fire control monitoring system based on big data of the Internet of things.
The invention provides an intelligent remote fire control monitoring system based on big data of the Internet of things, which comprises the following components:
A data acquisition layer and a platform layer, wherein:
The data acquisition layer is used for acquiring data through the sensor and then transmitting the acquired data to the platform layer;
The platform layer comprises:
the data processing module is used for cleaning and converting data;
the data storage module is used for storing the data subjected to data cleaning and data conversion;
The early warning temperature threshold dynamic generation module is used for generating an early warning temperature dynamic threshold by adopting a dynamic threshold for the temperature threshold which discovers potential fire risks and triggers early warning;
The early warning and alarm generation module is used for generating an early warning grade and an alarm grade through data analysis according to the early warning temperature dynamic threshold value generated by the early warning temperature threshold value dynamic generation module;
And the fire prediction model generation module is used for constructing a fire prediction model according to the early warning temperature dynamic threshold value generated by the early warning temperature threshold value dynamic generation module and by combining historical data analysis.
Preferably, in the data acquisition layer, the sensor comprises a smoke sensor, a temperature sensor, a flame detector, a combustible gas detector and a fire water system pressure sensor.
Preferably, in the early warning temperature threshold dynamic generation module, a temperature threshold which finds a potential fire risk and triggers early warning is generated by adopting a dynamic threshold method, as follows:
When a building is subjected to remote fire control monitoring, acquiring temperature data of the building in the area of the past year, setting the temperature data of the building in the past year as temperature data of n years, calculating to obtain average air temperature of each day according to the temperature data of n years, adding the average air temperature data of the same day in the past year, and dividing by n to obtain historical average air temperature of each day;
arranging the historical average air temperature data according to a date sequence to form a complete annual average air temperature data set;
Setting two temperature values as M1 and M2 respectively, wherein M1 is less than M2;
checking the daily historical average air temperature in the annual average air temperature dataset in sequence;
Recording the date as the starting date of the low temperature range when the historical average air temperature is lower than M1, continuously checking the subsequent date, and taking the last date as the ending date of the low temperature range when the historical average air temperature is higher than M1;
Recording the date when the historical average air temperature is larger than M1 as the starting date of the medium temperature range, continuously checking the subsequent date, and once the date when the historical average air temperature is smaller than M1 or larger than M2 is encountered, determining the last date as the ending date of the medium temperature range;
Recording the date when the historical average air temperature is higher than M2 as the starting date of the high temperature range, continuously checking the subsequent date, and taking the last date as the ending date of the high temperature range when the date when the average air temperature is lower than M2;
Obtaining a third initial temperature threshold value K1 of the temperature sensor, which is used for finding potential fire risks and triggering early warning, and setting an initial temperature change rate threshold value V1 of temperature change triggering early warning;
When the current date is in a low temperature range, the initial temperature threshold value which finds potential fire risks and triggers early warning is reduced by Y times of K1, and the initial temperature change rate threshold value which triggers early warning is reduced by Y times of V1;
when the current date is in the medium temperature range, the values of K1 and V1 are unchanged;
when the current date is in a high temperature range, the initial temperature threshold value which is found out to be at risk of potential fire and triggers early warning is increased by X times of K1, and the initial temperature change rate threshold value which is triggered by temperature change and triggers early warning is increased by X times of V1.
Preferably, the third initial temperature threshold value K1 of the temperature sensor, which finds a potential fire risk and triggers an early warning, is obtained by:
acquiring a second initial temperature threshold value K0 of the temperature sensor, wherein the second initial temperature threshold value is used for finding potential fire risks and triggering early warning;
When the humidity value measured by the humidity sensor is larger than a set threshold value, finding potential fire risk and triggering an initial temperature threshold value K0 of early warning to rise to Z times of K0, wherein Z is smaller than X;
in the same day, when the temperature difference measured by the temperature sensor is larger than a set threshold value, the initial temperature threshold value K0 which finds potential fire risks and triggers early warning is increased to Z times of K0, and Z is smaller than X;
When the condition one or the condition two is satisfied, k1=zk0;
k1=z (ZK 0) when both the condition one and the condition two are satisfied;
when neither condition one nor condition two is satisfied, k1=k0.
Preferably, the second initial temperature threshold value K0 for acquiring the potential fire risk found by the temperature sensor and triggering the early warning is obtained by the following steps:
Setting a first initial temperature threshold value of the temperature sensor, which is used for finding potential fire risks and triggering early warning, as K;
Starting timing from the time when the temperature sensor is put into use, and recording the using time t as aging time;
Obtaining the measurement deviation generated by the temperature sensor in the unit time of the initial use stage by obtaining the technical specification of the temperature sensor Representing the temperature measurement deviation caused by aging per unit time;
Calculating measurement deviation of temperature sensor due to aging The formula is:;
In the formula, k is an ageing coefficient, a theoretical relation model of the ageing coefficient and each ageing factor is established by adopting a theoretical analysis method by taking temperature, humidity, use time and use frequency as ageing factors, and the actual environmental parameters are substituted into the theoretical model to obtain the ageing coefficient k by calculation;
K0=k+ 。
Preferably, in the fire prediction model generation module, the fire prediction model is constructed as follows:
Acquiring historical fire accident data, historical daily monitoring data and early warning temperature dynamic threshold values, adopting a random forest classification algorithm to construct a fire prediction model for predicting the occurrence probability of fire, and sending out an alarm when the predicted occurrence probability of fire is larger than a set threshold value.
Preferably, in the early warning and alarm generation module, the generation of the early warning level and the alarm level is as follows:
when the temperature reaches a temperature threshold value for finding potential fire risks and triggering early warning, primary fire early warning is carried out;
when the temperature reaches a temperature threshold for finding potential fire risks and triggering early warning, and the temperature change rate reaches a temperature change rate threshold, carrying out secondary fire early warning;
When the temperature reaches a temperature threshold at which a potential fire risk is found and an early warning is triggered:
if the smoke concentration is in a continuously rising state within Q minutes and exceeds Wppm, carrying out three-stage fire early warning;
If the concentration of the combustible gas reaches 10% -15% of the explosion lower limit, performing three-level fire early warning;
when the temperature reaches a temperature threshold for finding a potential fire risk and triggering early warning, and the temperature change rate reaches a temperature change rate threshold:
If the smoke concentration rising rate exceeds 0.25Wppm per minute and lasts for more than 3 minutes, primary fire alarming is carried out;
if the smoke concentration reaches Wppm or more within 1 minute, performing primary fire alarm;
if the concentration of the combustible gas reaches 20% -30% of the explosion lower limit, performing primary fire alarm;
When the temperature reaches a temperature threshold at which a potential fire risk is found and an early warning is triggered:
If the smoke concentration exceeds 2Wppm, carrying out secondary fire alarm;
If the flame detector detects a flame signal, performing secondary fire alarm;
and if the concentration of the combustible gas reaches more than 50% of the explosion lower limit, performing secondary fire alarm.
An intelligent remote fire control monitoring method based on big data of the Internet of things is characterized by comprising the following steps:
s1, acquiring environmental data in a building through a sensor in a data acquisition layer, and then transmitting the acquired data to a platform layer;
S2, in the platform layer, the data processing module receives data from the data acquisition layer, performs data cleaning on the data, eliminates error values, abnormal values and repeated values, performs data conversion, and then stores the cleaned and converted data by the data storage module;
S3, a pre-warning temperature threshold dynamic generation module calculates daily average air temperature according to the temperature data of the building in the region of the past n years, and arranges the daily average air temperature into a data set, a temperature region is divided, and a pre-warning threshold K1 and a temperature change rate threshold V1 of a potential fire risk found by a temperature sensor are dynamically adjusted by combining humidity, temperature difference and sensor aging factors;
S4, generating corresponding primary fire early warning, secondary fire early warning and tertiary fire early warning and primary fire and secondary fire early warning by the early warning and alarm generation module according to the early warning temperature dynamic threshold value through data analysis and combining smoke concentration, combustible gas concentration and flame signal factors;
s5, the fire prediction model generation module fuses historical fire accident data and daily monitoring data by means of an early warning temperature dynamic threshold value, builds a model by using a random forest classification algorithm, and gives an alarm when the predicted fire occurrence probability exceeds a set threshold value.
The intelligent remote fire control monitoring system based on the big data of the Internet of things has the following beneficial technical effects:
1. In the early warning temperature threshold value dynamic generation module, the low temperature, medium temperature and high temperature ranges are divided through analyzing the annual temperature data of the region where the building is located, and the initial temperature threshold value for finding potential fire risks and triggering early warning and the initial temperature change rate threshold value for triggering early warning through combining the temperature sensor aging factors, humidity and temperature difference conditions are dynamically adjusted to replace the original static threshold value, so that the probability of triggering false alarm is reduced.
2. For the aging problem of the temperature sensor, the aging coefficient k is introduced, a theoretical relation model is built, the measurement deviation generated by aging is calculated, the condition that the fire disaster is not missed or false-reported due to the aging of the sensor in the whole life cycle of the temperature sensor is ensured, meanwhile, the influence of humidity and temperature difference environment factors on temperature measurement is also considered, an early warning temperature dynamic threshold value is formed, and in the same day, when the temperature difference measured by the temperature sensor is larger than a set threshold value, the threshold value of the early warning temperature can be flexibly adjusted according to the temperature difference change, the early fire disaster discovery probability is improved, and the stability and the reliability of the system are improved.
3. The early warning and alarm generation module generates corresponding primary, secondary and tertiary fire warning and primary and secondary fire alarms according to the early warning temperature dynamic threshold value and by combining smoke concentration, combustible gas concentration and flame signal factors, comprehensively considers the smoke concentration, the combustible gas concentration, the flame signal and the early warning temperature dynamic threshold value, can more comprehensively capture fire signs, verifies the possibility of fire occurrence from multiple angles, greatly enhances the reliability of early warning and alarm, and reduces the misjudgment risk.
4. The fire prediction model generation module fuses historical fire accident data and daily monitoring data by means of an early warning temperature dynamic threshold value, builds a model by using a random forest classification algorithm, gives an alarm when the predicted fire occurrence probability exceeds a set threshold value, builds a fire prediction model by means of the early warning temperature dynamic threshold value, and can accurately capture fire risks under various environments due to the fact that the early warning temperature dynamic threshold value can be adjusted according to different environment conditions, so that the pre-judging accuracy is improved.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
FIG. 1 is a schematic block diagram of a system of the present invention;
fig. 2 is a flow chart of the method of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar symbols indicate like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for explaining the present invention and are not to be construed as limiting the present invention.
The intelligent remote fire control monitored control system based on thing networking big data as shown in fig. 1 includes:
the data acquisition layer acquires data through the sensor and then transmits the acquired data to the platform layer;
the sensor comprises a smoke sensor, a temperature sensor, a flame detector, a combustible gas detector and a fire water system pressure sensor;
A platform layer, the platform layer comprising:
the data processing module is used for cleaning and converting data;
the data storage module is used for storing the data subjected to data cleaning and data conversion;
The early warning temperature threshold dynamic generation module is used for generating an early warning temperature dynamic threshold by adopting a dynamic threshold for the temperature threshold which discovers potential fire risks and triggers early warning;
The early warning and alarm generation module is used for generating an early warning grade and an alarm grade through data analysis according to the early warning temperature dynamic threshold value generated by the early warning temperature threshold value dynamic generation module;
The fire prediction model generation module is used for constructing a fire prediction model according to the early warning temperature dynamic threshold value generated by the early warning temperature threshold value dynamic generation module and by combining historical data analysis;
In the early warning temperature threshold value dynamic generation module, a temperature threshold value which discovers potential fire risk and triggers early warning is generated by adopting a dynamic threshold value method, and the method is as follows:
when remotely fire monitoring a building,
Acquiring temperature data of the building in the past year, setting the temperature data of the past year as temperature data of n years, calculating average air temperature of each day according to the temperature data of n years, adding the average air temperature data of the same day in the past year, and dividing by n to obtain the historical average air temperature of each day;
arranging the historical average air temperature data according to a date sequence to form a complete annual average air temperature data set;
Setting two temperature values as M1 and M2 respectively, wherein M1 is less than M2;
In an alternative embodiment, the values of M1 and M2 are obtained based on a clustering analysis method according to the annual average air temperature data set;
checking the daily historical average air temperature in the annual average air temperature dataset in sequence;
Recording the date as the starting date of the low temperature range when the historical average air temperature is lower than M1, continuously checking the subsequent date, and taking the last date as the ending date of the low temperature range when the historical average air temperature is higher than M1;
Recording the date when the historical average air temperature is larger than M1 as the starting date of the medium temperature range, continuously checking the subsequent date, and once the date when the historical average air temperature is smaller than M1 or larger than M2 is encountered, determining the last date as the ending date of the medium temperature range;
Recording the date when the historical average air temperature is higher than M2 as the starting date of the high temperature range, continuously checking the subsequent date, and taking the last date as the ending date of the high temperature range when the date when the average air temperature is lower than M2;
Obtaining a third initial temperature threshold value K1 of the temperature sensor, which is used for finding potential fire risks and triggering early warning, and setting an initial temperature change rate threshold value V1 of temperature change triggering early warning;
When the current date is in a low temperature range, the initial temperature threshold value which finds potential fire risks and triggers early warning is reduced by Y times of K1, and the initial temperature change rate threshold value which triggers early warning is reduced by Y times of V1;
In an alternative embodiment, 0.8.ltoreq.Y <1;
The initial temperature change rate threshold of the temperature change triggering early warning is reduced to be Y times of V1 because the normal rising process of the indoor temperature of the building is relatively stable under the low-temperature environment, the temperature change caused by fire disaster is more abrupt, and the reduction of V1 is helpful for capturing the abnormal change more sharply and early warning the fire disaster in advance. Meanwhile, the lower V1 value also considers the characteristic that the temperature difference between the indoor and the outdoor of a building is large in a low-temperature environment, and the heat spreading is possible to be faster when a fire disaster occurs, so that abnormal rise of the temperature can be detected at the initial stage of the fire disaster.
When the current date is in the medium temperature range, the values of K1 and V1 are unchanged;
When the current date is in a high temperature range, the initial temperature threshold value which finds potential fire risks and triggers early warning rises to be X times of K1, and the initial temperature change rate threshold value which triggers early warning is raised to be X times of V1;
In an alternative embodiment of the present invention, 1<X is less than or equal to 1.5;
This is because the increase of V1 in a high temperature environment reduces false alarms due to normal environmental temperature changes, and the high temperature environment may accelerate combustion speed in case of fire in the high temperature environment, but the temperature change rate due to the initial fire needs to be distinguished from the normal slow change. By improving V1, the device can better adapt to the characteristics of high-temperature environment and avoid excessive false alarm conditions while ensuring that the device is sensitive to rapid temperature change caused by fire.
The third initial temperature threshold value K1 of the temperature sensor, which is used for finding the potential fire risk and triggering the early warning, is obtained by the following steps:
acquiring a second initial temperature threshold value K0 of the temperature sensor, wherein the second initial temperature threshold value is used for finding potential fire risks and triggering early warning;
When the humidity value measured by the humidity sensor is larger than a set threshold value, finding potential fire risk and triggering an initial temperature threshold value K0 of early warning to rise to Z times of K0, wherein Z is smaller than X;
in the same day, when the temperature difference measured by the temperature sensor is larger than a set threshold value, the initial temperature threshold value K0 which finds potential fire risks and triggers early warning is increased to Z times of K0, and Z is smaller than X;
In an alternative embodiment of the present invention, 1<Z is less than or equal to 1.1;
the temperature difference refers to the difference between the lowest temperature measured by the temperature sensor and the current temperature;
When the condition one or the condition two is satisfied, k1=zk0;
k1=z (ZK 0) when both the condition one and the condition two are satisfied;
when neither condition one nor condition two is satisfied, k1=k0;
The second initial temperature threshold value K0 for acquiring the potential fire risk found by the temperature sensor and triggering early warning is obtained by the following steps:
Setting a first initial temperature threshold value of the temperature sensor, which is used for finding potential fire risks and triggering early warning, as K;
Starting timing from the time when the temperature sensor is put into use, and recording the using time t as aging time;
Obtaining the measurement deviation generated by the temperature sensor in the unit time of the initial use stage by obtaining the technical specification of the temperature sensor Representing the temperature measurement deviation caused by aging per unit time;
Calculating measurement deviation of temperature sensor due to aging The formula is:;
In the formula, k is an ageing coefficient, a theoretical relation model of the ageing coefficient and each ageing factor is established by adopting a theoretical analysis method by taking temperature, humidity, use time and use frequency as ageing factors, and the actual environmental parameters are substituted into the theoretical model to obtain the ageing coefficient k by calculation;
K0=k+ 。
For the aging problem of the temperature sensor, the aging coefficient k is introduced, a theoretical relation model is built, the measurement deviation generated by aging is calculated, the condition that the fire disaster is not missed or false-reported due to the aging of the sensor in the whole life cycle of the temperature sensor is ensured, meanwhile, the influence of humidity and temperature difference environment factors on temperature measurement is also considered, an early warning temperature dynamic threshold value is formed, and in the same day, when the temperature difference measured by the temperature sensor is larger than a set threshold value, the threshold value of the early warning temperature can be flexibly adjusted according to the temperature difference change, the early fire disaster discovery probability is improved, and the stability and the reliability of the system are improved.
In the early warning temperature threshold value dynamic generation module, the low temperature, medium temperature and high temperature ranges are divided through analyzing the annual temperature data of the region where the building is located, and the initial temperature threshold value for finding potential fire risks and triggering early warning and the initial temperature change rate threshold value for triggering early warning through combining the temperature sensor aging factors, humidity and temperature difference conditions are dynamically adjusted to replace the original static threshold value, so that the probability of triggering false alarm is reduced.
In the early warning and alarm generation module, the generation of the early warning grade and the alarm grade is as follows:
when the temperature reaches a temperature threshold value for finding potential fire risks and triggering early warning, primary fire early warning is carried out;
when the temperature reaches a temperature threshold for finding potential fire risks and triggering early warning, and the temperature change rate reaches a temperature change rate threshold, carrying out secondary fire early warning;
When the temperature reaches a temperature threshold at which a potential fire risk is found and an early warning is triggered:
if the smoke concentration is in a continuously rising state within Q minutes and exceeds Wppm, carrying out three-level fire early warning, prompting that smoldering conditions possibly occur and further paying attention to the smoldering conditions;
in an alternative embodiment, Q has a value in the range of [3,5];
In an alternative embodiment, q=5;
If the concentration of the combustible gas reaches 10% -15% of the explosion lower limit, performing three-level fire early warning;
when the temperature reaches a temperature threshold for finding a potential fire risk and triggering early warning, and the temperature change rate reaches a temperature change rate threshold:
If the smoke concentration rising rate exceeds 0.25Wppm per minute and lasts for more than 3 minutes, primary fire alarming is carried out;
if the smoke concentration reaches Wppm or more within 1 minute, performing primary fire alarm;
at this time, an alarm system of the local area can be started to inform relevant personnel to check on site.
If the concentration of the combustible gas reaches 20% -30% of the explosion lower limit, a first-stage fire alarm is carried out, and at the moment, the ventilation emergency equipment can be ready to be started.
When the temperature reaches a temperature threshold at which a potential fire risk is found and an early warning is triggered:
If the smoke concentration exceeds 2Wppm, carrying out secondary fire alarm;
If the flame detector detects a flame signal, performing secondary fire alarm;
At the moment, the comprehensive alarm can be triggered, the linkage fire-fighting water system automatically sprays water to extinguish fire, and simultaneously, the fire department is notified.
If the concentration of the combustible gas reaches more than 50% of the explosion lower limit, carrying out secondary fire alarm;
At this time, no matter the state of other sensors, the high fire risk is directly judged, and the measures of emergency cutting off of the air source and evacuating people are adopted.
The fire disaster prediction model constructed by the rule-based method can fully utilize various sensor information, flexibly judge fire disaster risks according to actual conditions, and provide powerful support for fire fighting early warning and emergency response.
The early warning and alarm generation module generates corresponding primary, secondary and tertiary fire warning and primary and secondary fire alarms according to the early warning temperature dynamic threshold value and by combining smoke concentration, combustible gas concentration and flame signal factors, comprehensively considers the smoke concentration, the combustible gas concentration, the flame signal and the early warning temperature dynamic threshold value, can more comprehensively capture fire signs, verifies the possibility of fire occurrence from multiple angles, greatly enhances the reliability of early warning and alarm, and reduces the misjudgment risk.
In the fire prediction model generation module, a fire prediction model is constructed as follows:
Acquiring historical fire accident data, historical daily monitoring data and early warning temperature dynamic threshold values, adopting a random forest classification algorithm to construct a fire prediction model for predicting the occurrence probability of fire, and sending out an alarm when the predicted occurrence probability of fire is larger than a set threshold value.
The fire prediction model generation module fuses historical fire accident data and daily monitoring data by means of an early warning temperature dynamic threshold value, builds a model by using a random forest classification algorithm, gives an alarm when the predicted fire occurrence probability exceeds a set threshold value, builds a fire prediction model by means of the early warning temperature dynamic threshold value, and can accurately capture fire risks under various environments due to the fact that the early warning temperature dynamic threshold value can be adjusted according to different environment conditions, so that the pre-judging accuracy is improved.
The intelligent remote fire control monitoring method based on the big data of the Internet of things shown in fig. 2 comprises the following steps:
s1, acquiring environmental data in a building through a sensor in a data acquisition layer, wherein a smoke sensor is used for monitoring smoke concentration in air, a temperature sensor is used for measuring environmental temperature, a flame detector is used for capturing flame signals, a flammable gas detector is used for detecting the leakage condition of the flammable gas, a fire water system pressure sensor is used for monitoring fire water pressure, and then the acquired data are transmitted to a platform layer;
S2, in the platform layer, the data processing module receives data from the data acquisition layer, performs data cleaning on the data, eliminates error values, abnormal values and repeated values, performs data conversion, unifies and standardizes data in different formats and units, and then the data storage module stores the cleaned and converted data;
S3, a pre-warning temperature threshold dynamic generation module calculates daily average air temperature according to the temperature data of the building in the region of the past n years, and arranges the daily average air temperature into a data set, a temperature region is divided, and a pre-warning threshold K1 and a temperature change rate threshold V1 of a potential fire risk found by a temperature sensor are dynamically adjusted by combining humidity, temperature difference and sensor aging factors;
S4, generating corresponding primary fire early warning, secondary fire early warning and tertiary fire early warning and primary fire and secondary fire early warning by the early warning and alarm generation module according to the early warning temperature dynamic threshold value through data analysis and combining smoke concentration, combustible gas concentration and flame signal factors;
s5, the fire prediction model generation module fuses historical fire accident data and daily monitoring data by means of an early warning temperature dynamic threshold value, builds a model by using a random forest classification algorithm, and gives an alarm when the predicted fire occurrence probability exceeds a set threshold value.
An intelligent remote fire control monitoring method based on big data of the Internet of things further comprises the following steps:
The time sequence analysis is adopted to predict the running state change trend of the fire-fighting equipment, so that maintenance and overhaul are planned in advance, and the equipment failure rate is reduced;
the convolutional neural network in deep learning is adopted to carry out intelligent analysis on the monitoring video image, flame and smoke identification is assisted, the fire alarm accuracy is improved, and scientific and accurate decision reference is provided for fire control management;
When the random forest classification algorithm builds a fire prediction model, historical data are sampled in a layered mode, so that the proportion of fire accident data of different types and daily monitoring data in a sample is similar to that of actual conditions, and the generalization capability of the model is improved.
And all that is not described in detail in this specification is well known to those skilled in the art.
In the embodiments provided in the present invention, it should be understood that the disclosed system or method may be implemented in other manners. For example, the above-described embodiments of the invention are merely illustrative, and for example, the division of modules is merely a logical function division, and other manners of division may be implemented in practice.
The modules illustrated as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, may be located in one place, or may be distributed over a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module. The integrated modules may be implemented in hardware or in hardware plus software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the essential characteristics thereof.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, shall cover the same or different embodiments according to the technical solution and the inventive concept of the present invention.
Claims (8)
1. Intelligent remote fire control monitored control system based on thing networking big data, its characterized in that includes:
A data acquisition layer and a platform layer, wherein:
The data acquisition layer is used for acquiring data through the sensor and then transmitting the acquired data to the platform layer;
The platform layer comprises:
the data processing module is used for cleaning and converting data;
the data storage module is used for storing the data subjected to data cleaning and data conversion;
The early warning temperature threshold dynamic generation module is used for generating an early warning temperature dynamic threshold by adopting a dynamic threshold for the temperature threshold which discovers potential fire risks and triggers early warning;
The early warning and alarm generation module is used for generating an early warning grade and an alarm grade through data analysis according to the early warning temperature dynamic threshold value generated by the early warning temperature threshold value dynamic generation module;
And the fire prediction model generation module is used for constructing a fire prediction model according to the early warning temperature dynamic threshold value generated by the early warning temperature threshold value dynamic generation module and by combining historical data analysis.
2. The intelligent remote fire control monitoring system based on the big data of the Internet of things, as set forth in claim 1, wherein the sensors in the data acquisition layer comprise a smoke sensor, a temperature sensor, a flame detector, a flammable gas detector and a fire control water system pressure sensor.
3. The intelligent remote fire control monitoring system based on internet of things big data according to claim 1, wherein in the early warning temperature threshold dynamic generation module, a temperature threshold which finds potential fire risk and triggers early warning is generated by adopting a dynamic threshold method, and the method is as follows:
When a building is subjected to remote fire control monitoring, acquiring temperature data of the building in the area of the past year, setting the temperature data of the building in the past year as temperature data of n years, calculating to obtain average air temperature of each day according to the temperature data of n years, adding the average air temperature data of the same day in the past year, and dividing by n to obtain historical average air temperature of each day;
arranging the historical average air temperature data according to a date sequence to form a complete annual average air temperature data set;
Setting two temperature values as M1 and M2 respectively, wherein M1 is less than M2;
checking the daily historical average air temperature in the annual average air temperature dataset in sequence;
Recording the date as the starting date of the low temperature range when the historical average air temperature is lower than M1, continuously checking the subsequent date, and taking the last date as the ending date of the low temperature range when the historical average air temperature is higher than M1;
Recording the date when the historical average air temperature is larger than M1 as the starting date of the medium temperature range, continuously checking the subsequent date, and once the date when the historical average air temperature is smaller than M1 or larger than M2 is encountered, determining the last date as the ending date of the medium temperature range;
Recording the date when the historical average air temperature is higher than M2 as the starting date of the high temperature range, continuously checking the subsequent date, and taking the last date as the ending date of the high temperature range when the date when the average air temperature is lower than M2;
Obtaining a third initial temperature threshold value K1 of the temperature sensor, which is used for finding potential fire risks and triggering early warning, and setting an initial temperature change rate threshold value V1 of temperature change triggering early warning;
When the current date is in a low temperature range, the initial temperature threshold value which finds potential fire risks and triggers early warning is reduced by Y times of K1, and the initial temperature change rate threshold value which triggers early warning is reduced by Y times of V1;
when the current date is in the medium temperature range, the values of K1 and V1 are unchanged;
when the current date is in a high temperature range, the initial temperature threshold value which is found out to be at risk of potential fire and triggers early warning is increased by X times of K1, and the initial temperature change rate threshold value which is triggered by temperature change and triggers early warning is increased by X times of V1.
4. The intelligent remote fire control monitoring system based on internet of things big data according to claim 3, wherein the third initial temperature threshold value of the temperature sensor for finding potential fire risk and triggering early warning is K1, which is obtained by:
acquiring a second initial temperature threshold value K0 of the temperature sensor, wherein the second initial temperature threshold value is used for finding potential fire risks and triggering early warning;
When the humidity value measured by the humidity sensor is larger than a set threshold value, finding potential fire risk and triggering an initial temperature threshold value K0 of early warning to rise to Z times of K0, wherein Z is smaller than X;
in the same day, when the temperature difference measured by the temperature sensor is larger than a set threshold value, the initial temperature threshold value K0 which finds potential fire risks and triggers early warning is increased to Z times of K0, and Z is smaller than X;
When the condition one or the condition two is satisfied, k1=zk0;
k1=z (ZK 0) when both the condition one and the condition two are satisfied;
when neither condition one nor condition two is satisfied, k1=k0.
5. The intelligent remote fire control monitoring system based on internet of things big data according to claim 4, wherein the second initial temperature threshold value for acquiring the potential fire risk found by the temperature sensor and triggering the early warning is K0 is obtained by:
Setting a first initial temperature threshold value of the temperature sensor, which is used for finding potential fire risks and triggering early warning, as K;
Starting timing from the time when the temperature sensor is put into use, and recording the using time t as aging time;
Obtaining the measurement deviation generated by the temperature sensor in the unit time of the initial use stage by obtaining the technical specification of the temperature sensor Representing the temperature measurement deviation caused by aging per unit time;
Calculating measurement deviation of temperature sensor due to aging The formula is:;
In the formula, k is an ageing coefficient, a theoretical relation model of the ageing coefficient and each ageing factor is established by adopting a theoretical analysis method by taking temperature, humidity, use time and use frequency as ageing factors, and the actual environmental parameters are substituted into the theoretical model to obtain the ageing coefficient k by calculation;
K0=k+ 。
6. The intelligent remote fire control monitoring system based on internet of things big data according to claim 1, wherein in the fire prediction model generation module, a fire prediction model is constructed as follows:
Acquiring historical fire accident data, historical daily monitoring data and early warning temperature dynamic threshold values, adopting a random forest classification algorithm to construct a fire prediction model for predicting the occurrence probability of fire, and sending out an alarm when the predicted occurrence probability of fire is larger than a set threshold value.
7. The intelligent remote fire control monitoring system based on internet of things big data according to claim 1 or 6, wherein in the early warning and alarm generation module, the generation of the early warning level and the alarm level is as follows:
when the temperature reaches a temperature threshold value for finding potential fire risks and triggering early warning, primary fire early warning is carried out;
when the temperature reaches a temperature threshold for finding potential fire risks and triggering early warning, and the temperature change rate reaches a temperature change rate threshold, carrying out secondary fire early warning;
When the temperature reaches a temperature threshold at which a potential fire risk is found and an early warning is triggered:
if the smoke concentration is in a continuously rising state within Q minutes and exceeds Wppm, carrying out three-stage fire early warning;
If the concentration of the combustible gas reaches 10% -15% of the explosion lower limit, performing three-level fire early warning;
when the temperature reaches a temperature threshold for finding a potential fire risk and triggering early warning, and the temperature change rate reaches a temperature change rate threshold:
If the smoke concentration rising rate exceeds 0.25Wppm per minute and lasts for more than 3 minutes, primary fire alarming is carried out;
if the smoke concentration reaches Wppm or more within 1 minute, performing primary fire alarm;
if the concentration of the combustible gas reaches 20% -30% of the explosion lower limit, performing primary fire alarm;
When the temperature reaches a temperature threshold at which a potential fire risk is found and an early warning is triggered:
If the smoke concentration exceeds 2Wppm, carrying out secondary fire alarm;
If the flame detector detects a flame signal, performing secondary fire alarm;
and if the concentration of the combustible gas reaches more than 50% of the explosion lower limit, performing secondary fire alarm.
8. An intelligent remote fire control monitoring method based on big data of the internet of things according to any one of claims 1-7, comprising the steps of:
s1, acquiring environmental data in a building through a sensor in a data acquisition layer, and then transmitting the acquired data to a platform layer;
S2, in the platform layer, the data processing module receives data from the data acquisition layer, performs data cleaning on the data, eliminates error values, abnormal values and repeated values, performs data conversion, and then stores the cleaned and converted data by the data storage module;
S3, a pre-warning temperature threshold dynamic generation module calculates daily average air temperature according to the temperature data of the building in the region of the past n years, and arranges the daily average air temperature into a data set, a temperature region is divided, and a pre-warning threshold K1 and a temperature change rate threshold V1 of a potential fire risk found by a temperature sensor are dynamically adjusted by combining humidity, temperature difference and sensor aging factors;
S4, generating corresponding primary fire early warning, secondary fire early warning and tertiary fire early warning and primary fire and secondary fire early warning by the early warning and alarm generation module according to the early warning temperature dynamic threshold value through data analysis and combining smoke concentration, combustible gas concentration and flame signal factors;
s5, the fire prediction model generation module fuses historical fire accident data and daily monitoring data by means of an early warning temperature dynamic threshold value, builds a model by using a random forest classification algorithm, and gives an alarm when the predicted fire occurrence probability exceeds a set threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510068422.0A CN119832679A (en) | 2025-01-16 | 2025-01-16 | Intelligent remote fire control monitoring system based on big data of Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510068422.0A CN119832679A (en) | 2025-01-16 | 2025-01-16 | Intelligent remote fire control monitoring system based on big data of Internet of things |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119832679A true CN119832679A (en) | 2025-04-15 |
Family
ID=95292383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510068422.0A Pending CN119832679A (en) | 2025-01-16 | 2025-01-16 | Intelligent remote fire control monitoring system based on big data of Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119832679A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120279684A (en) * | 2025-06-09 | 2025-07-08 | 贵州省气象台 | Low-temperature overcast and rainy weather monitoring and early warning method and system based on Internet of things |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030174056A1 (en) * | 2002-03-12 | 2003-09-18 | Harshaw Bob F. | System for verifying detection of a fire event condition |
| CN202711405U (en) * | 2012-08-01 | 2013-01-30 | 兰州商学院 | Multipoint grading fire intelligent monitoring alarm system |
| CN108074367A (en) * | 2016-11-17 | 2018-05-25 | 上海防灾救灾研究所 | A kind of editable formula based on external memory chip, the fire-alarm and its method of threshold value |
| JP2019096196A (en) * | 2017-11-27 | 2019-06-20 | ホーチキ株式会社 | Fire alarm |
| CN112801457A (en) * | 2020-12-31 | 2021-05-14 | 杭州拓深科技有限公司 | Fire-fighting linkage method and system based on regional fire risk assessment |
| US20210372858A1 (en) * | 2020-05-29 | 2021-12-02 | Rolls-Royce Corporation | Thermocouple pre-aging and temperature drift compensation |
| CN114023033A (en) * | 2021-10-13 | 2022-02-08 | 国网甘肃省电力公司综合服务中心 | A smart fire management system |
| CN114093112A (en) * | 2022-01-18 | 2022-02-25 | 南京光蓝物联网科技有限公司 | Forest fire multi-defense line real-time monitoring system based on distributed optical fiber sensing technology |
| CN116978178A (en) * | 2023-08-02 | 2023-10-31 | 安徽职业技术学院 | Distributed intelligent fireproof disaster prevention early warning system |
| CN119181198A (en) * | 2024-10-11 | 2024-12-24 | 山东赢云智能科技有限公司 | Fire visualization active early warning and monitoring system and method based on infrared temperature measurement technology |
-
2025
- 2025-01-16 CN CN202510068422.0A patent/CN119832679A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030174056A1 (en) * | 2002-03-12 | 2003-09-18 | Harshaw Bob F. | System for verifying detection of a fire event condition |
| CN202711405U (en) * | 2012-08-01 | 2013-01-30 | 兰州商学院 | Multipoint grading fire intelligent monitoring alarm system |
| CN108074367A (en) * | 2016-11-17 | 2018-05-25 | 上海防灾救灾研究所 | A kind of editable formula based on external memory chip, the fire-alarm and its method of threshold value |
| JP2019096196A (en) * | 2017-11-27 | 2019-06-20 | ホーチキ株式会社 | Fire alarm |
| US20210372858A1 (en) * | 2020-05-29 | 2021-12-02 | Rolls-Royce Corporation | Thermocouple pre-aging and temperature drift compensation |
| CN112801457A (en) * | 2020-12-31 | 2021-05-14 | 杭州拓深科技有限公司 | Fire-fighting linkage method and system based on regional fire risk assessment |
| CN114023033A (en) * | 2021-10-13 | 2022-02-08 | 国网甘肃省电力公司综合服务中心 | A smart fire management system |
| CN114093112A (en) * | 2022-01-18 | 2022-02-25 | 南京光蓝物联网科技有限公司 | Forest fire multi-defense line real-time monitoring system based on distributed optical fiber sensing technology |
| CN116978178A (en) * | 2023-08-02 | 2023-10-31 | 安徽职业技术学院 | Distributed intelligent fireproof disaster prevention early warning system |
| CN119181198A (en) * | 2024-10-11 | 2024-12-24 | 山东赢云智能科技有限公司 | Fire visualization active early warning and monitoring system and method based on infrared temperature measurement technology |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120279684A (en) * | 2025-06-09 | 2025-07-08 | 贵州省气象台 | Low-temperature overcast and rainy weather monitoring and early warning method and system based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12374206B2 (en) | Fire detection system | |
| US20240418548A1 (en) | Sensor fusion for fire detection & air quality monitoring | |
| CN109443440A (en) | Tunnel Integrated Monitoring System | |
| CN119832679A (en) | Intelligent remote fire control monitoring system based on big data of Internet of things | |
| JP2013504102A (en) | Fire and combustible gas notification system and method | |
| CN209821986U (en) | Fire monitoring system | |
| CN110120143A (en) | A kind of inflammable and explosive region smog intelligent monitor system of Petrochemical Enterprises | |
| KR20230120168A (en) | Waste battery thermal runaway prevention system using ai prediction model and sensor monitoring | |
| CN118038620B (en) | Intelligent fire safety monitoring system and method | |
| CN111047815A (en) | Method and system for identifying false alarm of fire-fighting detector based on self-learning model | |
| CN119206980A (en) | A fire real-time monitoring alarm system and method | |
| KR100977562B1 (en) | Fire Sensor Symptom Determination System Based on Temperature Sensor | |
| CN119207060A (en) | A remote intelligent monitoring system and method for urban housing safety | |
| JP2025036614A (en) | Fire Detection Systems | |
| CN118982893A (en) | Smart city fire monitoring and early warning method and system based on the Internet of Things | |
| KR20100026418A (en) | Fire abnormality-symptom distinction system using temperature sensor and humidity sensor | |
| CN114360194B (en) | Multi-point monitoring visual array type fire alarm system | |
| CN108230627B (en) | Combustible gas monitoring system for oil depot | |
| CN107016814A (en) | A kind of fire disaster intelligently early warning system | |
| CN113709422A (en) | Piping lane safety alarm system | |
| CN119251993A (en) | Indoor gas leakage treatment system and treatment method | |
| CN118314674A (en) | Early warning method for fire disaster | |
| JP6602035B2 (en) | Detection device | |
| Upadhyaya et al. | Advancing Safety: IoT-Based Multi Sensor System for Real-Time Multiple Hazards Detection and Alarming | |
| CN116418830A (en) | A computer room environment monitoring system and method based on the Internet of Things |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |