CN119026810B - Intelligent data management system for building fire safety monitoring - Google Patents
Intelligent data management system for building fire safety monitoring Download PDFInfo
- Publication number
- CN119026810B CN119026810B CN202411479469.8A CN202411479469A CN119026810B CN 119026810 B CN119026810 B CN 119026810B CN 202411479469 A CN202411479469 A CN 202411479469A CN 119026810 B CN119026810 B CN 119026810B
- Authority
- CN
- China
- Prior art keywords
- data
- temperature
- temperature sensor
- temperature data
- fluctuation
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Computer Security & Cryptography (AREA)
- Game Theory and Decision Science (AREA)
- Fire Alarms (AREA)
- Alarm Systems (AREA)
Abstract
本申请涉及数据处理领域，具体涉及用于建筑消防安全监测的智能数据管理系统，所述系统包括：数据采集模块，用于采集每个温度传感器所有时刻的温度数据；空间特征分析模块，用于通过分析相邻位置温度传感器采集数据的变化趋势、以及温度数据随空间距离的变化特征确定温度数据的位置空间特征值；监测数据处理模块，用于基于每个温度传感器在每个数据采集时刻的位置空间特征值以及温度数据完成对温度数据的智能管理。本申请通过分析建筑内可燃物阴燃现象造成的温度数据波动特征以及位置空间距离对温度数据差异的影响完成数据分类，提高对监测数据的处理精度，实现对监测数据的智能处理。
The present application relates to the field of data processing, and specifically to an intelligent data management system for building fire safety monitoring, the system comprising: a data acquisition module for collecting temperature data of each temperature sensor at all times; a spatial feature analysis module for determining the positional spatial feature value of temperature data by analyzing the change trend of the data collected by the temperature sensors at adjacent positions, and the change characteristics of the temperature data with the spatial distance; a monitoring data processing module for completing the intelligent management of temperature data based on the positional spatial feature value and temperature data of each temperature sensor at each data collection moment. The present application completes data classification by analyzing the temperature data fluctuation characteristics caused by the smoldering phenomenon of combustibles in the building and the influence of the positional spatial distance on the temperature data difference, thereby improving the processing accuracy of the monitoring data and realizing the intelligent processing of the monitoring data.
Description
Technical Field
The application relates to the technical field of data processing, in particular to an intelligent data management system for building fire safety monitoring.
Background
The building fire safety monitoring is to dynamically monitor and periodically detect a plurality of links in a building fire system so as to ensure the fire safety of a building. The fire disaster ultra-early detection is one of important detection tasks for checking fire disaster hidden dangers in a building, finding potential fire safety hazards and improving the fire safety level of the building.
The very early stage of a fire is the smoldering stage of the fire, and the most important feature of this stage is the change of temperature in the building. At present, various intelligent monitoring devices such as dust detectors, smoke alarms, temperature and humidity sensors and the like are generally utilized to be deployed inside a building, so that all-weather monitoring of fire is realized. The temperature sensor is used for controlling the surroundings of combustible materials in the building, data are collected through the temperature sensor, and then the data are analyzed, so that early monitoring of building fire is achieved. However, all-weather monitoring causes a large amount of data to be generated by the sensor, so that effective data management is needed, and effective data are screened out.
For fire monitoring, abnormal data in the monitoring process is effective data with potential safety hazards, and belongs to data with higher importance, so that the abnormal data and the normal data in the monitoring process need to be accurately segmented. The current segmentation of the sensor monitoring data often ignores the influence of the sensor installation environment on the data value by a global threshold segmentation method, so that the efficiency of data management in the monitoring process is low, and effective data support cannot be provided for fire management.
Disclosure of Invention
The application provides an intelligent data management system for building fire safety monitoring, which aims to solve the existing problems.
The application provides an intelligent data management system for building fire safety monitoring, which comprises:
the data acquisition module is used for acquiring temperature data of each temperature sensor at all moments;
The spatial feature analysis module is used for determining a position spatial feature value of the temperature data by analyzing the change trend of the acquired data of the temperature sensors at adjacent positions and the change feature of the temperature data along with the spatial distance, and specifically comprises the following steps:
(1) Acquiring abnormal points of temperature data, dividing the temperature data into a plurality of local data sequences by taking each abnormal point as a dividing point, and determining a characteristic array of the abnormal points according to all temperature values, values of the abnormal points and the quantity of the temperature data in the local data sequences;
(2) Setting a plurality of radiuses by taking one temperature sensor as the center, sequencing the temperature of the temperature sensor and the temperature difference of all the temperature sensors in the radiuses from small to large, and then performing first-order difference to obtain a correction sequence;
(3) At each acquisition time, correcting the fluctuation reliability of each temperature data according to the difference forward fusion fluctuation reliability of the correction coefficient and the maximum value of the correction coefficient to obtain a position space characteristic value of each data acquisition time;
The monitoring data processing module acquires associated characteristic values according to the mean value and variance of temperatures of all abnormal points before each acquisition time, the minimum time interval value of adjacent abnormal points and the position space characteristic value of the acquisition time, and classifies all the associated characteristic values into different dangerous level classes to finish intelligent management of temperature data.
Preferably, the determining the fluctuation reliability of each temperature data based on the difference of the temperature data between the temperature sensors includes:
Determining a fluctuation coefficient of each temperature data acquired by each temperature sensor based on differences of feature arrays among abnormal points in the temperature data acquired by different temperature sensors;
The fluctuation credibility of each temperature data is determined based on the overall fluctuation degree of the temperature data of each temperature sensor before each data acquisition time and the fluctuation coefficient.
Preferably, the method for acquiring the fluctuation coefficient of each temperature data includes:
detecting abnormal points in temperature data acquired by each temperature sensor by using an RRCF algorithm, and acquiring a feature array of each abnormal point;
Calculating the ratio of the DTW distance between the feature arrays of any one of the abnormal points in the same sequence before each moment of each temperature sensor and the position distance of the two temperature sensors;
And taking the accumulated result of the ratio at all abnormal points of all temperature sensors in the building before each moment as the fluctuation coefficient of each temperature data acquired by each sensor.
Preferably, the method for acquiring the fluctuation credibility of each temperature data comprises the following steps:
Calculating the difference value between the average value of all abnormal points before the corresponding acquisition time of each temperature data acquired by each temperature sensor and the average value of all temperature data before the corresponding acquisition time;
and taking the normalized result of the product of the difference value and the fluctuation coefficient of each temperature data as the fluctuation credibility of each temperature data.
Preferably, the method for acquiring the feature array includes:
Detecting abnormal points in temperature data acquired by each temperature sensor by using an RRCF algorithm;
dividing all temperature data into a plurality of local data sequences by taking each abnormal point as a dividing point, calculating variances of all temperature data in one adjacent local data sequence before each abnormal point as the fluctuation radius of each abnormal point, and taking an array formed by the numerical value of each abnormal point, the quantity of the temperature data before each abnormal point and the fluctuation radius of each abnormal point as the characteristic array of each abnormal point.
Preferably, the method for obtaining the correction coefficient of each temperature sensor at each data acquisition time includes:
and taking the ratio of the element quantity smaller than 0 in the correction sequence of each temperature sensor at each data acquisition time to the element quantity in the correction sequence as a correction coefficient of each temperature sensor at each data acquisition time.
Preferably, the method for acquiring the correction sequence includes:
For any one data acquisition moment, taking the position of each temperature sensor as the center of a sphere, acquiring the temperature data of all the temperature sensors on the sphere at each data acquisition moment according to the radius r, and calculating the average value of the temperature data of all the temperature sensors on the sphere at each data acquisition moment;
And sequentially acquiring single distance differences of each temperature sensor at each data acquisition time under different radiuses, sequencing all the single distance differences according to the sequence from the smaller radius to the larger radius, and taking a first-order differential sequence of sequencing results as a correction sequence of each temperature sensor at each data acquisition time.
Preferably, the method for acquiring the position space characteristic value at each data acquisition time comprises the following steps:
Calculating the ratio of the correction coefficient of each temperature sensor at each data acquisition time to the maximum value of the correction coefficients of each temperature sensor at all data acquisition times;
and taking the product of the ratio and the fluctuation reliability of the temperature data acquired by each temperature sensor at each data acquisition time as a position space characteristic value at each data acquisition time.
Preferably, the method for intelligently managing the temperature data based on the position space characteristic value of each temperature sensor at each data acquisition time and the temperature data comprises the following steps:
Determining the correlation characteristic value of the acquired temperature data and the fire super-early sign at each data acquisition time of each temperature sensor based on the abnormal point of each temperature sensor before each data acquisition time and the position space characteristic value of each temperature sensor at each data acquisition time;
acquiring the associated characteristic values of temperature data and fire disaster ultra-early symptoms acquired at all data acquisition moments of each temperature sensor, and dividing all the associated characteristic values into a plurality of cluster clusters by using a data clustering algorithm;
And respectively calculating the average value of all the associated characteristic values in each cluster as the label value of each cluster, arranging the label values of all the clusters in sequence from large to small, and respectively marking the clusters as a first monitoring risk level, a second monitoring risk level and a K-th monitoring risk level based on the arrangement result, wherein K is the number of the clusters.
Preferably, the method for acquiring the association characteristic value includes:
In the formula, Is the correlation characteristic value of the temperature data of the c temperature sensor at the t time and the fire disaster super-early sign,、The mean value and the variance of the temperature data between all adjacent abnormal points before the time t of the c temperature sensor are respectively,Is the minimum value of the time interval between all adjacent outliers before the t-th moment of the c-th temperature sensor,Is the position space characteristic value of the c temperature sensor at the t time,Is the minimum time interval between the time t and the time corresponding to the abnormal point,Is a parameter adjusting factor.
According to the method, firstly, the fluctuation coefficient of temperature data of each temperature sensor at each data acquisition time is determined based on the characteristic that the temperature of combustible materials in a building is increased when the combustible materials are smoldering and heat is gradually diffused in the process from being close to a smoldering phenomenon area to being far away from the smoldering phenomenon area, secondly, the fluctuation reliability of the temperature data is determined by combining the data fluctuation characteristics of the smoldering phenomenon, the method has the advantages that the fluctuation characteristics of the temperature data at each data acquisition time of the temperature sensors at different positions can be determined, afterwards, the correction coefficient of the fluctuation reliability of the temperature data is determined based on the change stability of the temperature difference in the building under the premise that the analysis distance is from small to large, the influence of the data fluctuation caused by the internal interference of the temperature sensors on the smoldering phenomenon in the all-weather monitoring process is eliminated, then, the characteristic that continuous high temperature data exist between adjacent abnormal points is caused based on the smoldering phenomenon, the position space characteristic value of each temperature sensor at each data acquisition time is obtained, the temperature sensor is associated with the super-value of the data acquisition time, the early-stage fire disaster characteristic data is clustered, and finally, the fire disaster characteristic data is clustered with the early-stage fire disaster characteristic data is acquired based on the data, and the data is clustered, and the intelligent clustering is achieved, and the fire disaster characteristic is clustered on the data is clustered, and the fire characteristic is well, and the fire characteristic data is clustered and the fire condition data is well, and the fire condition data is well.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an intelligent data management system for building fire safety monitoring according to an embodiment of the present application;
FIG. 2 is a flowchart of an embodiment of the present application for implementing a position space feature value;
Fig. 3 is a flowchart of an implementation of implementing intelligent data management based on classification marking of collected data according to an embodiment of the present application.
Detailed Description
In order to further describe the technical means and effects adopted by the application to achieve the preset aim, the following detailed description is given below of the specific implementation, structure, characteristics and effects of the intelligent data management system for building fire safety monitoring according to the application in combination with the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
The following specifically describes a specific scheme of the intelligent data management system for building fire safety monitoring provided by the application with reference to the accompanying drawings.
Referring to FIG. 1, a flowchart of an intelligent data management system for building fire safety monitoring according to one embodiment of the present application is shown, where the system includes a data acquisition module, a spatial feature analysis module, and a monitoring data processing module. The specific contents of each module are as follows:
the data acquisition module is used for acquiring the temperature data of each temperature sensor at all moments.
Specifically, firstly, determining the position of the combustible in the building, wherein the combustible comprises fixed combustible and contained combustible, secondly, arranging a temperature sensor around each combustible in the building, and adopting the center of mass point of the combustible as the center of a circle around the center of mass point of the combustibleThe arrangement of the temperature sensors is performed, and the arrangement unit of the sensors is in meters in this embodiment. It should be noted that the arrangement of the temperature sensor is not fixed, and in other embodiments, a suitable arrangement may be selected by the practitioner.
Further, in this embodiment, the temperature data monitored by each time of the temperature sensors is collected at a time interval of three minutes, and all the temperature data within 12 hours are obtained, wherein the number of the temperature sensors is greater than or equal to 2. The time interval for the temperature sensor to collect the temperature data is not specifically limited, and the practitioner may be determined according to the specific situation.
Preferably, in order to avoid data loss caused by unstable transmission network in the acquisition process, the data is filled in a linear interpolation manner in this embodiment. The linear filling is a common technology in the field of data processing, and the process thereof is not repeated.
The spatial feature analysis module is configured to determine a spatial feature value of a location of temperature data by analyzing a trend of a change of data collected by a temperature sensor at an adjacent location and a change feature of the temperature data along with a spatial distance, and a specific flow is shown in fig. 2, and includes steps 201, 202, and 203:
a fluctuation reliability of each temperature data is determined based on a difference in temperature data between the temperature sensors 201.
When the smoldering phenomenon of the combustible matters occurs in the building, the temperature from the surrounding of the combustible matters to the other positions of the surrounding space is gradually reduced, so that the possibility that each temperature data is the monitoring data belonging to the fire ultra-early stage in the monitoring process is obtained by combining the temperature change characteristics of the fire ultra-early stage through the change relation between the temperature data of each temperature sensor and the temperature data of the surrounding temperature sensors.
Further, under the condition that the smoldering phenomenon of combustible matters does not occur, the temperature data of each temperature sensor in the building are not greatly different, the size of the temperature data basically fluctuates at the room temperature, but when the smoldering phenomenon of the combustible matters occurs, the heat radiation generated by fire disaster is outwards radiated from a fire source point, so that the temperature data of different temperature sensors have large difference, and the credibility of the temperature data of each temperature sensor can be obtained according to the difference of the temperature data of the temperature sensors.
On the other hand, the larger the distance between the two temperature sensors in the space position in the building is, the higher the possibility that the difference of the ambient temperatures of the two temperature sensors is larger is, for example, the size of the temperature data of the temperature sensor close to the ventilation opening is closer to the outdoor temperature than the size of the temperature data of the temperature sensor in the building, when the smoldering phenomenon of the combustible material occurs, the change degree of the collected data of the two temperature sensors also has a certain difference, namely, the fluctuation trend of the collected data of the temperature sensors at different positions is not consistent.
For any one temperature sensor, taking all temperature data acquired by each temperature sensor as input, and outputting abnormal points in all the temperature data by using a robust random forest cutting RRCF (Robust Random Cut Forest) algorithm. It should be noted that, because the temperature sensor is in an all-weather monitoring state, the temperature sensor is in a state of continuously collecting temperature data, and the RRCF algorithm is a dynamic detection mode, so that abnormal points can be accurately detected. The RRCF algorithm is a common technology in the field of data processing, and the process thereof will not be described in detail.
Further, each abnormal point is used as a mutation point of data fluctuation of temperature data, so that all the temperature data can be divided into a plurality of local data sequences by using the abnormal point as a division point, and the data fluctuation of different temperature sensors in a short period can be analyzed. Calculating variances of all temperature data in adjacent local data sequences before each abnormal point as fluctuation radius a of each abnormal point, and taking an array formed by the numerical value v of each abnormal point, the number n of the temperature data before each abnormal point and the fluctuation radius a of each abnormal point as a characteristic array of each abnormal pointFor characterizing the data characteristics that each outlier has.
And determining the fluctuation credibility of each temperature data acquired by each temperature sensor based on the characteristic array of the corresponding abnormal points among the temperature sensors and the temperature data.
First, a fluctuation coefficient of temperature data of an ith temperature sensor at a t-th time is calculated:
In the formula, Is the fluctuation coefficient of the temperature data of the ith temperature sensor at the time t, M is the number of all abnormal points of the ith temperature sensor before the time t, N is the number of the temperature sensors installed in the building,、The characteristic array of the ith abnormal point before the t moment of the ith temperature sensor and the jth temperature sensor respectively,Is the DTW distance between them,Is the Euclidean distance between the i temperature sensor and the j temperature sensor.
Secondly, determining the fluctuation credibility of the temperature data of the ith temperature sensor at the t moment by combining the overall fluctuation degree of the temperature data of the ith temperature sensor before the t moment:
In the formula, Is the fluctuation credibility of the temperature data of the ith temperature sensor at the t moment,Is a normalization function that is used to normalize the values,Is the average of all outliers of the ith temperature sensor before time t,Is the average of all temperature data of the ith temperature sensor before the t-th time.
The larger the difference of the data fluctuation abrupt change condition between the temperature data collected by the two temperature sensors, the larger the difference between the temperature data collected by the two temperature sensors is, which means that the more likely the monitoring data is under the condition of different smoldering of combustible materials, and meanwhile, the smaller the space position distance between the two temperature sensors is, the lower the probability that the data fluctuation difference between the data collected by the two temperature sensors is caused by the position difference is, namelyThe greater the value of the (i) th temperature sensor is, the greater the possibility that the (i) th temperature sensor receives the data fluctuation of the smoldering phenomenon of the combustible at the (t) th moment is, the more obvious the trend of the (i) th temperature sensor in the temperature rise at the first t moment is, the greater the temperature data of M abnormal points in front of the (i) th temperature sensor is, the more obvious the trend characteristic of data enhancement is, namelyThe greater the value of (i) the greater the degree of fluctuation of the data of the ith temperature sensor at the time t, which is subjected to the occurrence of the smoldering phenomenon of the combustible.
202, Determining a correction coefficient of fluctuation credibility of each temperature data by analyzing the variation stability degree of the temperature difference in the building on the premise of small-to-large distance.
When the smoldering phenomenon of the combustible material occurs in the building, the temperature in the local space where the combustible material is located gradually rises, and the heat energy is radiated outwards from the point where the smoldering is serious, and in the sensing range of the temperature sensor, the sensing range is the space range determined by the acquisition radius of the temperature sensor capable of acquiring the temperature data, for example, the sensing range of the temperature sensor is thatThe representative temperature sensor can acquire temperature data in a spherical region with a radius of 10 meters by taking the installation position as the center. With the increase of the distance, the difference between the temperature data of the temperature sensor far from the severe point of the smoldering phenomenon and the temperature data of the temperature sensor close to the severe point of the smoldering phenomenon is larger, so that the fluctuation reliability of the temperature data of each temperature sensor can be corrected according to the difference of the temperature data of any two temperature sensors in the sensing range and the relation between the distances between the two temperature sensors, and the internal interference of the sensors, such as the interference of local current on the data fluctuation of the temperature data, can be avoided.
Specifically, the position of the c-th temperature sensor is taken as the center of the sphere, the temperature data of all the temperature sensors on the sphere are obtained according to the radius r, and the average value of the temperature data of all the temperature sensors on the sphere at the t-th moment is calculated and recorded asCalculating the average value of the temperature data of the c-th temperature sensor at the t-th moment and the temperature data of all the temperature sensors on the spherical surfaceThe difference between the temperature sensor c and the spherical surface at the t time is expressed asSequentially obtaining corresponding differences under different radiuses, wherein the differences represent absolute values of the differences, and the radius r has the value range ofWherein T is the acquisition radius of the sensing range of the temperature sensors arranged, it should be noted that, in this embodiment, the sensing ranges of all the temperature sensors are consistent.
For each data acquisition time, sorting the differences of the temperature data on the c-th temperature sensor and the spherical surface according to the order of the radius r from small to large, and taking the first-order difference sequence of the sorting result as the correction sequence of the c-th temperature sensor at each data acquisition time. If the combustible material with the c temperature sensor being closer to the combustible material is smoldered at the t moment, the difference value should be increased along with the increase of the radius r, and elements in the correction sequence should be equal to or greater than 0, and if the temperature data collected by the c temperature sensor is interfered by the sensor, elements less than 0 may exist in the correction sequence, so that the more elements less than 0 in the correction sequence, the greater the influence of the sensor internal interference on the temperature data fluctuation, the greater the correction degree should be.
Determining a correction coefficient of each temperature sensor at each data acquisition time based on the positive and negative conditions of element values in the correction sequence of each temperature sensor at each data acquisition time:
In the formula, Is the correction coefficient of the c-th temperature sensor at the t-th moment,Is the number of elements less than 0 in the correction sequence of the c-th temperature sensor at the t-th time,Is the number of elements in the correction sequence for the c-th temperature sensor at the t-th time instant.
And 203, correcting the fluctuation reliability of each temperature data by using the correction coefficient to obtain the position space characteristic value of each data acquisition time.
In the building, the types of combustible substances are different, and the temperature rise degree is also different under the same smoldering time, so that the application corrects the fluctuation reliability based on the ratio of the correction coefficient of each temperature sensor under different data acquisition moments to the maximum value of the correction coefficient of each temperature sensor under all the acquisition moments as the degree for evaluating the fluctuation of the temperature data under different data acquisition moments, and the position space characteristic value of each data acquisition moment is obtained.
Specifically, the calculation formula of the position space characteristic value of the c-th temperature sensor at the t-th moment is as follows:
In the formula, Is the position space characteristic value of the c-th temperature sensor at the t-th moment,Is the correction coefficient of the c-th temperature sensor at the t-th moment,Is the maximum value of the correction coefficients of the c-th temperature sensor at all data acquisition moments,Is the fluctuation credibility of the temperature data of the c-th temperature sensor at the t-th moment.
Wherein, the more the number of elements smaller than 0 in the corresponding correction sequence of the c temperature sensor at the t moment, the more likely that the fluctuation of the temperature data at the t moment is generated by the internal interference of the sensor, the more the influence on the temperature data caused by the smoldering phenomenon of the combustible is, namelyThe larger the value of (2), the more reliable the fluctuation of the temperature dataThe greater the corrected degree of (c).
And the monitoring data processing module is used for completing intelligent management of the temperature data based on the position space characteristic value of each temperature sensor at each data acquisition time and the temperature data.
In the building, the smoldering phenomenon of the combustible material can not be stopped immediately after the smoldering phenomenon occurs, namely, the temperature rise caused by the smoldering phenomenon can generate continuous high-temperature data in the temperature data acquired by the temperature sensor. Therefore, in the application, the time interval of the acquisition time between any two adjacent abnormal points before each data acquisition time is counted, and if the two adjacent abnormal points are caused by a smoldering phenomenon, the temperature data between the two adjacent abnormal points are high-temperature data, and the time interval is larger. At the same time, the larger the position space characteristic value of the temperature sensor at a certain data acquisition time, the more likely the temperature data fluctuation at the time is caused by smoldering phenomenon.
Specifically, the calculation formula of the association characteristic value of the temperature data of the c temperature sensor at the t time and the fire early symptom is as follows:
In the formula, Is the correlation characteristic value of the temperature data of the c temperature sensor at the t time and the fire disaster super-early sign,、The mean value and the variance of the temperature data between all adjacent abnormal points before the time t of the c temperature sensor are respectively,Is the minimum value of the time interval between all adjacent outliers before the t-th moment of the c-th temperature sensor,Is the position space characteristic value of the c temperature sensor at the t time,Is the minimum time interval between the time t and the time corresponding to the abnormal point,Is a parameter adjusting factor for preventing denominator from being 0,The size of (2) is 0.001.
Wherein, the closer the corresponding moment of the abnormal point of the distance at the t moment of the c-th temperature sensor is, the more the possibility that the t moment is in the smoldering phase is, the larger the average value of the temperature data between all adjacent abnormal points before the t moment is, the smaller the variance is, the more likely that the temperature data between the abnormal points are continuous high-temperature data caused by the smoldering phenomenon is, and the more the possibility that the t moment is in the smoldering phase is, the larger the data fluctuation of the temperature data at the t moment is, namelyThe greater the value of (c) the more relevant the temperature data of the c-th temperature sensor at the t-th moment and the fire early sign.
Further, based on the flow, the relevant characteristic values of the temperature data and the fire disaster ultra-early symptoms at all data acquisition time of each temperature sensor are respectively obtained. And all the associated characteristic values are used as input, the associated characteristic values of all the temperature data of each temperature sensor and the fire disaster ultra-early symptoms are divided into different cluster clusters by utilizing AP (Affinity Propagation Clustering) clustering algorithm, the average value of all the associated characteristic values in each cluster is respectively calculated and used as the label value of each cluster, the label values of all the clusters are arranged in sequence from large to small, the clusters are respectively marked as a first monitoring danger level, a second monitoring danger level and up to a Kth monitoring danger level based on the arrangement result, K is the number of the clusters, and intelligent management of the temperature data is completed. The AP clustering algorithm is a common technology in the field of data processing, and a detailed description of the process is omitted.
It should be noted that, in this embodiment, only one clustering algorithm of the associated feature values, that is, an AP clustering algorithm, is provided, and in other embodiments, other data clustering algorithms may be selected on the premise that the associated feature values can be classified, including but not limited to mean clustering and fuzzy mean clustering, which is not particularly limited in the present application.
It should be noted that the foregoing embodiments are merely illustrative of the technical solutions of the present application, and not restrictive, and although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that the technical solutions described in the foregoing embodiments may be modified or some of the technical features may be replaced equivalently, and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application and are included in the protection scope of the present application.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (9)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411479469.8A CN119026810B (en) | 2024-10-23 | 2024-10-23 | Intelligent data management system for building fire safety monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411479469.8A CN119026810B (en) | 2024-10-23 | 2024-10-23 | Intelligent data management system for building fire safety monitoring |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119026810A CN119026810A (en) | 2024-11-26 |
| CN119026810B true CN119026810B (en) | 2025-02-07 |
Family
ID=93533880
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411479469.8A Active CN119026810B (en) | 2024-10-23 | 2024-10-23 | Intelligent data management system for building fire safety monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119026810B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119483723B (en) * | 2025-01-10 | 2025-07-22 | 深圳市中康北斗科技有限公司 | Oil field data transmission method and system based on Beidou satellite |
| CN119994688B (en) * | 2025-02-21 | 2025-09-23 | 大连度达安全科技有限公司 | An explosion-proof electric cabinet for new energy energy supply |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117249922A (en) * | 2023-11-17 | 2023-12-19 | 山东盈动智能科技有限公司 | Temperature calibration method and system for temperature tester |
| CN118194208A (en) * | 2024-05-16 | 2024-06-14 | 深圳市中瑞恒管理策划有限公司 | Energy-saving building safety intelligent detection system |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116358436A (en) * | 2023-04-07 | 2023-06-30 | 上海建工四建集团有限公司 | Building deformation intelligent monitoring and data processing system based on computer vision |
| CN116956200B (en) * | 2023-09-19 | 2023-11-24 | 山东辉瑞管业有限公司 | Irrigation pipe production real-time detection system based on machine learning |
| CN117294019B (en) * | 2023-10-11 | 2024-03-22 | 中铁十四局集团建筑工程有限公司 | Environment-friendly building energy consumption monitoring method and system based on Internet of things |
| CN117746602B (en) * | 2024-02-19 | 2024-05-28 | 及安盾(海南)科技有限公司 | Fire risk intelligent early warning method and system based on multi-source data fusion |
| CN118760834B (en) * | 2024-09-06 | 2024-11-15 | 天津诺德建筑材料有限公司 | Building fire safety assessment method based on big data analysis |
-
2024
- 2024-10-23 CN CN202411479469.8A patent/CN119026810B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117249922A (en) * | 2023-11-17 | 2023-12-19 | 山东盈动智能科技有限公司 | Temperature calibration method and system for temperature tester |
| CN118194208A (en) * | 2024-05-16 | 2024-06-14 | 深圳市中瑞恒管理策划有限公司 | Energy-saving building safety intelligent detection system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119026810A (en) | 2024-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN119026810B (en) | Intelligent data management system for building fire safety monitoring | |
| Chen et al. | Multi-sourced sensing and support vector machine classification for effective detection of fire hazard in early stage | |
| US7034701B1 (en) | Identification of fire signatures for shipboard multi-criteria fire detection systems | |
| US8255522B2 (en) | Event detection from attributes read by entities | |
| CN116028852B (en) | A method for detecting underground road fire based on BP neural network and D-S evidence theory | |
| CN111986436B (en) | Comprehensive flame detection method based on ultraviolet and deep neural networks | |
| CN112188531A (en) | Abnormality detection method, abnormality detection device, electronic apparatus, and computer storage medium | |
| CN104318688B (en) | A kind of multisensor fire alarm method based on data fusion | |
| US11860038B2 (en) | Method, apparatus and system for passive infrared sensor framework | |
| Abid et al. | Anomaly detection through outlier and neighborhood data in Wireless Sensor Networks | |
| WO2020111934A1 (en) | A method and system for detection of natural disaster occurrence | |
| CN116909339B (en) | Intelligent household safety early warning method and system based on artificial intelligence | |
| CN118503794B (en) | A substation equipment abnormality detection system and method based on multimodal data | |
| CN117807550B (en) | Intelligent quantitative detection method and system for building fire-fighting facilities | |
| CN119290081B (en) | Equipment running state monitoring system based on multiple sensors | |
| CN113359637A (en) | Data quality guarantee system and method based on station house operation environment and equipment operation state | |
| CN120220318A (en) | A multi-sensor collaborative monitoring method for IoT data early warning | |
| US20250118183A1 (en) | Automated system and method for fire detection | |
| KR20230134091A (en) | GCN based IoT edge gateway capable of situation classification | |
| CN118038141B (en) | Infrared, ultraviolet and image fire detection systems and methods | |
| CN120123859A (en) | A fire prediction detection adjustment optimization method and system | |
| CN118886622A (en) | Chemical storage area data processing method and system based on Internet of Things | |
| CN114137636B (en) | Regional meteorological monitoring management method and system for annular pressure sensor | |
| KR20240098825A (en) | Apparatus and method for predicting risk for using collected information of non-contact type sensing device and energy consumption information | |
| Ayrancı et al. | IoT-based fire detection: A comparative study of machine learning techniques |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20251211 Address after: 071700 Hebei Province, Baoding City, Xiongan New Area, Rongcheng County, Rongcheng Town, Aowei Road No. 130, Building 5, 2-010 (self-declared) Patentee after: Hebei Xiong'an Xingjiang Construction Technology Co.,Ltd. Country or region after: China Address before: 116000 Public Building No. 32- (1-2), Quanshui B3 District, Ganjingzi District, Dalian City, Liaoning Province Patentee before: Liaoning Tong'an Fire Safety Technology Engineering Co.,Ltd. Country or region before: China |