An electrical fire monitoring and early warning method and system

Abstract

The present application relates to the technical field of fire warning, and particularly relates to an electrical fire monitoring and warning method and system. The method includes: collecting current electrical parameter data of a monitoring object, and obtaining electrical parameter data before multiple historical fire warnings and during multiple normal states; analyzing the first necessity of each historical fire warning according to the characteristics of abnormal data in the data collected before each historical fire warning and the correlation with the fire warning; analyzing the second necessity of each historical fire warning according to the difference between any two pieces of data during each historical normal state and the correlation between the occurrence of abnormal conditions and the fire warning; calculating the disaster warning necessity at each moment within the current and a preset period before it in combination with the first and second necessities to determine the current disaster warning necessity. The present application analyzes the historical correlation changes among multiple electrical parameters, more comprehensively evaluates the fire risk, and improves the accuracy of the warning.

Description

Technical Field

[0001] This application relates to the technical field of fire warning, and specifically relates to an electrical fire monitoring and warning method and system. Background Art

[0002] Electrical fire monitoring and warning is to monitor the operating status of electrical circuits and equipment in real time through a series of technical means and equipment, so as to timely detect potential electrical fire hazards before a fire occurs and issue a warning, thereby taking corresponding measures to prevent the occurrence of fire accidents.

[0003] Existing electrical fire monitoring algorithms mainly rely on simple threshold judgments of real-time single parameters, and have problems such as low sensitivity, high false alarm rate, and inability to give early warnings. Summary of the Invention

[0004] In order to solve the above technical problems, this application provides an electrical fire monitoring and warning method and system, and the technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of this application provides an electrical fire monitoring and warning method, and the method includes the following steps:

[0006] Collect current electrical parameter data of the monitoring object, and obtain electrical parameter data before multiple historical fire warnings and under multiple normal states.

[0007] For each item of electrical parameter data, according to the proportion of abnormal data and the abnormal score in the data collected before each historical fire warning, obtain the correlation between the data collected before each historical fire warning and the fire warning; and analyze the average value of the correlations between the data collected before all historical warnings and the fire warning, and perform weighted summation on the correlations of the corresponding item of electrical parameter data before each historical fire warning to obtain the first necessity of each historical fire warning.

[0008] Based on the difference between the ratio of any two data collected at the same moment under each historical normal state and the ratio of the average values of any two data in the same historical normal state, obtain the difference between any two data under the normal state; use the number of abnormal ratios and their abnormal scores in the ratio of any two data collected at the same moment before each historical fire warning to determine the correlation between the abnormal conditions of any two data and the disaster warning before each historical fire warning; and take the average value of the correlations between the abnormal conditions of any two data and the fire warning before all historical fire warnings as the correlation between the abnormal conditions of any two data and the fire warning.

[0009] Fuse positively the differences between any two kinds of data under normal conditions, the correlation between abnormal conditions and fire warnings, and the correlation between abnormal conditions of any two kinds of data and disaster warnings before each historical fire warning to obtain the second necessity of each historical fire warning;

[0010] Calculate the necessity of disaster warning at each moment within the preset time period before and including the current moment by combining the first and second necessities to judge the current necessity of disaster warning.

[0011] Preferably, the electrical parameter data includes temperature, voltage, current and carbon dioxide concentration.

[0012] Preferably, the abnormal data is obtained by using the LOF anomaly detection algorithm for each electrical parameter data before all historical fire warnings and under all normal conditions.

[0013] Preferably, the method for obtaining the correlation between the data collected before each historical fire warning and the fire warning is: Denote the correlation between the temperature data collected before the jth historical warning and the fire warning as , ; where represents the correlation between the temperature data collected before the jth historical warning and the fire warning, norm represents the normalization function, represents the proportion of abnormal data in the temperature data collected before the jth historical fire warning, represents the number of abnormal data in the temperature data collected before the jth historical fire warning, represents the anomaly score of the ith abnormal data.

[0014] Preferably, before weighting the correlation between the data collected before all historical warnings and the fire warning for each corresponding electrical parameter data before each historical fire warning using the mean value of the correlation, perform a normalization operation on the mean value of the correlation between each electrical parameter data collected before all historical warnings and the fire warning.

[0015] Preferably, the difference between any two kinds of data under normal conditions is determined by the cumulative sum of all the differences calculated under all historical normal conditions.

[0016] Preferably, the method for obtaining the correlation between abnormal conditions of any two kinds of data and disaster warnings before each historical fire warning is: Denote the correlation between abnormal conditions of temperature data and current data before the ath historical fire warning and the disaster warning as ;

[0017]

[0018] Where m represents the number of historical fire warnings obtained, and norm represents the normalization function. represents the number of abnormal ratios in the ratio of temperature to current data before the a-th historical fire warning, and g represents the number of collection times for each historical collection. represents the abnormal score corresponding to the ratio of temperature to current data when the abnormal ratio appears for the b-th time.

[0019] Preferably, the necessity of disaster warning at each moment within the current and the preset period before it is determined by the sum of the first necessity and the second necessity at each moment within the current and the preset period before it.

[0020] Preferably, the method for judging the necessity of the current disaster warning is as follows:

[0021] Perform threshold segmentation on all the disaster warning necessities obtained within the current and the preset period before it. When the current disaster warning necessity is greater than the segmentation threshold, a fire warning is issued.

[0022] In a second aspect, an embodiment of the present application further provides an electrical fire monitoring and warning system. The system includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the electrical fire monitoring and warning method described in any one of the above are implemented.

[0023] The present application has at least the following beneficial effects:

[0024] The advantages of the present application over the prior art are as follows: The present application can, before the electrical parameters reach the dangerous threshold, through comprehensive analysis of the historical data and real-time data of the electrical parameters, combined with the abnormal analysis of various electrical parameter data and the abnormal analysis of data correlation, not only consider the abnormality of a single electrical parameter, but also analyze the historical correlation changes between multiple electrical parameters, more comprehensively evaluate the fire risk, discover fire hazards in advance, reduce the false alarm rate, and improve the accuracy of the warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0026] Figure 1 is a flowchart of an electrical fire monitoring and warning method provided by an embodiment of the present application;

[0027] Figure 2Flowchart of a method for obtaining the necessity of current disaster warning provided by an embodiment of the present application. Detailed implementation manner

[0028] Embodiment 1

[0029] An electrical fire monitoring and warning method provided by an embodiment of the present application, specifically referring to Figure 1 , the method includes the following steps:

[0030] Step 1: Collect various current electrical parameter data of the monitoring object, and obtain the electrical parameter data before multiple historical fire warnings and under multiple normal conditions.

[0031] Install near the monitoring object devices capable of identifying electrical parameter data related to the fire of the monitoring object, including temperature, voltage, current, and carbon dioxide concentration. Among them, the temperature W, voltage D, current L, and carbon dioxide CO2 concentration C in the environment of the monitoring object are obtained through a temperature sensor, a voltage sensor, a current sensor, and a carbon dioxide concentration sensor respectively.

[0032] In this embodiment, the acquisition frequency of all data is set to collect 10 times evenly per minute, and the acquisition time is set to the current time and within 1 hour before it, which can be specifically set by the implementer.

[0033] Furthermore, obtain the electrical parameter data before multiple historical fire warnings and under multiple normal conditions, and complete the warning analysis of the current fire monitoring data by analyzing the data change characteristics in all historical data.

[0034] In this embodiment, take the electrical parameter data of the previous n hours before each historical fire warning, perform feature analysis on these parameter data, so as to obtain the tightness between the fire precursor and these data. Among them, record the number of historical fire warnings obtained as m, and record the number of data obtained under normal conditions as Q. In this embodiment, Q = 200, then m + Q groups of data are obtained correspondingly, and each group of data forms a sequence, and the length of the sequence is , each element in the sequence is a column vector composed of all item electrical parameter data at each acquisition moment, then the present application performs electrical data analysis based on these data. Among them, the length of the temperature data sequence under normal conditions is also , in this embodiment, n = 1, that is, only collect 1 hour of data.

[0035] Step 2: Analyze the first necessity of each historical fire warning according to the characteristics of abnormal data and the correlation with the fire warning in the data collected before each historical fire warning.

[0036] In this application, for each item of electrical parameter data, according to the proportion of abnormal data and the abnormal score in the data collected before each historical fire warning, the correlation between the data collected before each historical fire warning and the fire warning is obtained.

[0037] Specifically, in this embodiment, taking the temperature data as an example, m groups of temperature data collected before historical fire warnings are first obtained. The LOF anomaly detection algorithm is used to calculate the anomaly score for all the temperature data collected historically, and the data with an anomaly score greater than 1 is recorded as abnormal data. Among them, the LOF anomaly detection algorithm is a well-known technology and will not be elaborated here. In other embodiments, other suitable anomaly detection algorithms can also be used to calculate the anomaly score to obtain abnormal data.

[0038] In this embodiment, the correlation between the temperature data collected before the jth historical warning and the fire warning can be obtained according to the proportion of abnormal data and the abnormal score in the temperature data collected before the jth historical warning:

[0039]

[0040] Among them represents the correlation between the temperature data collected before the jth historical warning and the fire warning, norm represents the normalization function, represents the proportion of abnormal data in the temperature data collected before the jth historical fire warning, which is determined by the ratio of the number of abnormal data obtained by anomaly detection to the number of all temperature data collected before this fire warning; represents the number of abnormal data in the temperature data collected before the jth historical fire warning, represents the anomaly score of the i-th abnormal data. That is, when there are more abnormal temperature data and the abnormality of the temperature data is greater before the fire warning to be obtained, it indicates that the correlation between the abnormal temperature change and the fire warning is stronger. That is, when the degree of abnormal temperature change is greater, the necessity of issuing a fire warning is greater.

[0041] Similarly, the correlations between the voltage, current, and carbon dioxide concentration data collected before each historical warning and the fire warning can be obtained respectively, and they are respectively recorded as 、 and .

[0042] Furthermore, in this application, the mean value of the correlations between the data collected before all historical warnings and the fire warning is analyzed, and the correlations of the corresponding item of electrical parameter data before each historical fire warning are weighted and summed to obtain the first necessity of each historical fire warning, which is used to characterize the necessity situation of each historical fire warning.

[0043] In this embodiment, by calculating the mean value of the correlations between the temperature data collected before all historical warnings and the fire warning which is used to characterize the correlation between various electrical parameters collected historically and fire warnings.

[0044] Similarly, the correlation means of the voltage, current, and carbon dioxide concentration data collected before all historical warnings and fire warnings can be obtained respectively, and they are denoted as , and .

[0045] Before weighting the correlation between the electrical parameter data corresponding to each item and fire warnings by using the correlation means of the data collected before all historical warnings and fire warnings, a normalization operation is performed on the correlation means of each electrical parameter data collected before all historical warnings and fire warnings and fire warnings. Specifically, a probability normalization operation can be adopted, which is specifically set by the implementer.

[0046] Step 3: Analyze the second necessity of each historical fire warning according to the difference between any two data in each historical normal state and the correlation between the abnormal situation and the fire warning.

[0047] At the same time, there is also a certain correlation between the electrical parameter data when the electrical system operates smoothly. When a fire sign appears, the correlation between these data may be damaged and change. Therefore, it is also possible to monitor the correlation between the electrical parameter data, analyze the change of the correlation between these data before the fire warning, and thus obtain the relationship between the abnormal change of the correlation between these data and the fire sign.

[0048] In this application, based on the difference between the ratio of any two data collected at the same moment in each historical normal state and the ratio of the means of any two data in the same historical normal state, the difference between any two data in the normal state is obtained.

[0049] Preferably, the difference between any two data in the normal state is determined by the sum of all the differences calculated in all historical normal states.

[0050] In this embodiment, taking temperature and current as an example, the difference between these two electrical parameter data in the historical normal state is obtained. The temperature and current data collected at the same acquisition moment are analyzed, the ratio of the temperature and current data at the same acquisition moment is calculated, and it is compared with the ratio of all temperature means and all current means at the same acquisition moment in each historical normal state to perform a difference analysis, so as to obtain the difference between temperature and current in the normal state, that is, the degree of irrelevance between the changes of the two electrical parameter data under normal operation conditions. Then the difference between the corresponding temperature and current data in the normal state is calculated as follows:

[0051]

[0052] Where Q represents the number of times of data obtained in the normal state, and g represents the number of moments of each historical collection. 、 respectively represent the average temperature and the average current of all in the u-th normal state in history. That is, when the analysis is performed based on historical data, the smaller the change in the two obtained ratios, that is, the smaller the the more stable the ratio of the two types of data is under normal circumstances, that is, the stronger the correlation between the two data. Further, it can also indicate that the reliability of disaster warning based on the change of this correlation is greater. It should be noted that when the data is in the normal state and there are other reasons for the abnormal data ratio, when calculating according to the above method, the calculated correlation of its parameters is relatively low. Therefore, for some parameters that are easily disturbed by other factors in normal times, the reference of their parameters is relatively low.

[0053] Furthermore, in this application, the number of abnormal ratios and their abnormal scores in the ratios of any two types of data collected at the same moment before each historical fire warning are used to determine the correlation between the abnormal conditions of any two types of data and the disaster warning before each historical fire warning; and the average value of the correlations between the abnormal conditions of any two types of data and the disaster warning before all historical fire warnings is used as the correlation between the abnormal conditions of any two types of data and the fire warning.

[0054] In this embodiment, for the abnormal ratios in the ratios of temperature and current data collected at the same moment before all historical fire warnings, the same method as above is adopted, and the LOF anomaly detection algorithm is used to obtain the abnormal ratios and their abnormal scores among them, and the number of abnormal ratios is recorded as R.

[0055] Furthermore, the calculation method for the correlation between the abnormal conditions of temperature data and current data and the fire warning in this embodiment is as follows:

[0056]

[0057]

[0058] Where represents the correlation between the abnormal conditions of temperature data and current data and the fire warning, norm represents the normalization function, represents the correlation between the abnormal conditions of temperature data and current data and the disaster warning before the a-th historical fire warning, and m represents the number of historical fire warnings obtained. represents the number of abnormal ratios among the ratios of temperature to current data before the a-th historical fire warning, and g represents the number of collection times in each historical collection. Then represents the proportion of the number of abnormal ratios among the ratios of temperature to current data before the a-th historical fire warning. represents the abnormal score corresponding to the ratio of temperature to current data when the abnormal ratio appears for the b-th time.

[0059] It should be understood that, that is, when the ratio of temperature to current data obtained by analyzing based on the temperature to current data before the a-th historical fire warning shows a larger abnormal ratio, and the abnormal score corresponding to the obtained abnormal ratio is also larger, it indicates that the abnormality of this abnormal ratio is more likely to be a sign of a disaster, and the better the effect of using the abnormality of this abnormal ratio to predict a fire, that is, the stronger the correlation between the change of the abnormality of this abnormal ratio and the fire warning.

[0060] Similarly, obtain the correlations between the abnormal conditions of any two electrical parameter data and the fire warning, and record them as 、 、 、 and .

[0061] Then, based on the above information, the second necessity of disaster warning can be obtained. In this application, the differences between all any two data in the normal state, the correlations between the abnormal conditions and the fire warning, and the correlations between the abnormal conditions of any two data before each historical fire warning and the disaster warning are positively fused to obtain the second necessity of each historical fire warning.

[0062] It can be understood that positive fusion is a fusion method such as addition and multiplication between data. The specific positive fusion method is determined by the implementer according to the actual situation to select a suitable fusion method, and this application does not make special restrictions.

[0063] In this embodiment, taking the temperature and current data as an example, the differences between the temperature and current data in the normal state, the correlations between the abnormal conditions of the temperature data and the current data and the fire warning, and the correlations between the abnormal conditions of the temperature data and the current data before the h-th historical fire warning and the disaster warning are positively fused, and the mean value of the positive fusion results of all any two data is used as the second necessity of the h-th historical fire warning. The specific calculation method is as follows:

[0064] First, calculate the correlation weight factor, and its calculation method is to calculate the product of the correlation between the two data and the correlation between the abnormal change of the correlation between the two data and the disaster warning, that is ; Represents the correlation weight factor between temperature and current data, and norm represents the normalization function. Represents the difference between temperature and current data under normal conditions. Represents the correlation between abnormal conditions of temperature data and current data and fire warning. That is, when the correlation between the two types of data sought is stronger, and the correlation between the change in the correlation of the two types of data and disaster warning is stronger, then The larger it is, the more it indicates that the abnormal correlation of these two types of data can reflect whether a disaster requires warning. After normalizing it as the correlation weight factor reflecting the disaster warning characteristics of the pairwise correlation abnormality, the pairwise data correlation abnormality weight can be obtained.

[0065] Then the calculation method for the second necessity of each historical fire warning obtained based on the correlation between temperature and current data. In this embodiment, the second necessity of temperature and current data in the h-th historical fire warning is taken as an example: ; Represents the correlation weight factor between temperature and current data. Represents the correlation between abnormal conditions of temperature data and current data before the h-th historical fire warning and disaster warning. That is, when the correlation weight factor between the sought temperature and current data is larger, and the abnormal change in the correlation between temperature and current data in the h-th historical fire warning is larger, it indicates that the necessity of disaster warning obtained by analyzing based on temperature and current data is greater.

[0066] Use the same method to obtain the second necessity of temperature and voltage, temperature and carbon dioxide, voltage and current, voltage and carbon dioxide, current and carbon dioxide in the h-th historical fire warning respectively, and record them as 、 、 、 、 、 respectively. Sum the above six results to obtain the second necessity of the h-th historical fire warning.

[0067] Step Four: Combine the first and second necessities to calculate the disaster warning necessity at each moment within the current and previous preset time periods to judge the current disaster warning necessity.

[0068] Then, according to the data attributes and correlation analysis between data analyzed above, the historical disaster warning necessity BY for each time can be obtained: that is, by adding the first necessity of the obtained disaster warning and the second necessity of the disaster warning.

[0069] For all acquisition times within the current and the preset time period before it, the necessity of disaster warning can be obtained according to the above method. Among them, the values in the time period shorter than the length g are filled according to the average value in this time period. In this embodiment, the preset time period length for the current and before it obtained is 50, and the implementer can set it by himself according to the actual situation.

[0070] Threshold segmentation is performed on all the disaster warning necessities obtained within the current and the preset time period before it. When the current disaster warning necessity is greater than the segmentation threshold, a fire warning is issued. In this embodiment, the Otsu threshold is used for threshold segmentation, and the Otsu threshold is a well-known technology and will not be elaborated here.

[0071] In this embodiment, the abnormality of the change of each item of data is analyzed according to the data before the warning, so that the disaster signs can be detected in advance before the detection values of each item of monitoring data reach the threshold, and more time for dealing with to avoid the occurrence of disasters can be provided.

[0072] In this embodiment, the flowchart of the method for obtaining the current disaster warning necessity is as shown in the appendix Figure 2 shown.

[0073] Based on the same inventive concept as the above method, another embodiment of the present application also provides an electrical fire monitoring and warning system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of the above-mentioned electrical fire monitoring and warning method.

[0074] Those skilled in the art will easily think of other implementation schemes of the present application after considering the specification and practicing the invention here. The present application aims to cover any variations, uses or adaptations of the present application. These variations, uses or adaptations follow the general principles of the present application and include the common general knowledge or conventional technical means in the technical field not invented by the present application.

[0075] It should be understood that the present application is not limited to the precise structure already described and shown in the drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. An electrical fire monitoring and early warning method, characterized in that: The method comprises the following steps: Collect the current electrical parameter data of the monitored object, and obtain the electrical parameter data before multiple fire warnings and multiple times in normal state; For each item of electrical parameter data, the correlation between the data collected before each fire warning in history and the fire warning is obtained according to the proportion of abnormal data in the data collected before each fire warning in history and the abnormal score; and the mean of the correlation between the data collected before all historical warnings and the fire warning is analyzed, and the weighted sum of the correlation of the corresponding item of electrical parameter data before each historical fire warning is performed to obtain the first necessity of each historical fire warning; Based on the difference between the ratio of any two data collected at the same time under each normal state in history and the ratio of the mean of any two data under the normal state in history, the difference between any two data under normal state is obtained; the number of abnormal ratios and their abnormal scores in the ratio of any two data collected at the same time before each fire warning in history are used to determine the correlation between the abnormal conditions of any two data before each fire warning in history and the disaster warning; and the average value of the correlation between the abnormal conditions of any two data before all fire warnings in history and the disaster warning is used as the correlation between the abnormal conditions of any two data and the fire warning; The differences between any two data under normal conditions, the correlation between abnormal conditions and fire warnings, and the correlation between abnormal conditions and disaster warnings between any two data before each fire warning in history are forward integrated to obtain the second necessity of each fire warning in history; The necessity of disaster warning at each moment in the current and previous preset time periods is calculated in combination with the first and second necessities to determine the necessity of the current disaster warning.

2. The electrical fire monitoring and early warning method according to claim 1, characterized in that: The electrical parameter data include temperature, voltage, current and carbon dioxide concentration.

3. The electrical fire monitoring and early warning method according to claim 1, characterized in that: The abnormal data is obtained by performing a LOF abnormality detection algorithm on various electrical parameter data before all historical fire warnings and under all normal conditions.

4. The electrical fire monitoring and early warning method according to claim 1, characterized in that: The method for obtaining the correlation between the data collected before each fire warning in history and the fire warning is as follows: the correlation between the temperature data collected before the jth warning in history and the fire warning is recorded as , ;in represents the correlation between the temperature data collected before the jth warning in history and the fire warning, norm represents the normalization function, represents the proportion of abnormal data in the temperature data collected before the jth fire warning in history, represents the number of abnormal data in the temperature data collected before the jth fire warning in history, represents the anomaly score of the i-th anomaly data.

5. The electrical fire monitoring and early warning method according to claim 1, characterized in that: Before using the mean value of the correlation between the data collected before all historical warnings and the fire warning to weight the correlation of the corresponding electrical parameter data before each historical fire warning, the mean value of the correlation between each electrical parameter data collected before all historical warnings and the fire warning is normalized.

6. The electrical fire monitoring and early warning method according to claim 1, characterized in that: The difference between any two data under normal conditions is determined by the cumulative sum of all the differences calculated under all historical subnormal conditions.

7. The electrical fire monitoring and early warning method according to claim 1, characterized in that: The method for obtaining the correlation between the abnormal conditions of any two data before each fire warning in history and the disaster warning is as follows: the correlation between the abnormal conditions of the temperature data and the current data before the a-th fire warning in history and the disaster warning is recorded as ; Where m represents the number of historical fire warnings obtained, norm represents the normalization function, represents the number of abnormal ratios of the temperature to current data before the a-th fire warning in history, g represents the number of moments of each historical collection, Indicates the abnormal score corresponding to the ratio of temperature to current data when the abnormal ratio occurs for the bth time.

8. The electrical fire monitoring and early warning method according to claim 1, characterized in that: The necessity of the disaster warning at each moment in the current and previous preset time periods is determined by the sum of the first necessity and the second necessity at each moment in the current and previous preset time periods.

9. The electrical fire monitoring and early warning method according to claim 1, characterized in that: The method for judging the necessity of current disaster warning is: Threshold segmentation is performed on all disaster warning necessities obtained in the current and previous preset time periods, and a fire warning is issued when the current disaster warning necessity is greater than the segmentation threshold.

10. An electrical fire monitoring and early warning system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, an electrical fire monitoring and early warning method as described in any one of claims 1 to 9 is implemented.

Images