Fire investigation auxiliary method and system based on intelligent electric monitoring

Abstract

The invention discloses a fire investigation auxiliary method and system based on intelligent electricity monitoring, and belongs to the technical field of electrical detection, and the system specifically comprises a data collection module which comprises an intelligent electricity monitoring terminal and is used for collecting real-time monitoring data in real time, the intelligent electricity monitoring terminal comprises an electricity meter, a circuit breaker, an electrical fire monitoring detector, an intelligent socket and an electrical fire adjustment special device. The data analysis module is used for analyzing real-time monitoring data collected in a first preset time period before the fire accident occurs, performing data preprocessing and judging whether the fire accident is an electrical fire; the accident analysis module is used for further analyzing real-time monitoring data collected in a second preset time period before the fire accident when the fire accident is judged to be an electrical fire accident, and judging whether the electrical fire accident is caused by abnormal electric equipment or line insulation aging, and the second preset time period is longer than the first preset time period; according to the invention, the electrical fire can be identified through the power utilization data.

Description

Technical Field

[0001] The present invention relates to the field of electrical detection technology, and in particular to a fire investigation auxiliary method and system based on intelligent electrical monitoring. Background Art

[0002] In fire investigation, it is crucial to accurately identify the cause of the fire. Traditional fire investigation methods mainly include on-site inspection, investigation and questioning, video surveillance and physical evidence identification. However, these methods have certain limitations in practical application, especially in the identification of electrical fires.

[0003] Real-time power consumption monitoring data can reflect the electrical conditions at the time of the fire, including changes in parameters such as current, voltage, and power. These data can provide direct evidence related to electrical fires for fire investigations, helping investigators to more accurately identify the cause of the fire. At the same time, historical power consumption monitoring data can also provide reference and basis for fire investigations. By analyzing historical power consumption data, we can understand the operating status and power consumption of electrical equipment before the fire, thereby helping investigators determine whether the fire is related to electrical equipment.

[0004] By introducing real-time and historical electricity monitoring data into fire investigations, the efficiency and accuracy of fire investigations can be improved. At the same time, this can also provide more sufficient basis and credibility for the determination of responsibility for suspected electrical fire accidents. Summary of the invention

[0005] The purpose of the present invention is to provide a fire investigation auxiliary method and system based on intelligent electrical monitoring to solve the following technical problems:

[0006] Existing technologies have defects in the identification of electrical fires. By introducing real-time and historical electricity consumption monitoring data into fire investigations, the efficiency and accuracy of fire investigations can be improved.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] Fire investigation auxiliary system based on intelligent electrical monitoring, including:

[0009] The data acquisition module includes an intelligent electrical monitoring terminal for real-time acquisition of real-time monitoring data. The intelligent electrical monitoring terminal includes an electric meter, a circuit breaker, an electrical fire monitoring detector, an intelligent socket, and a dedicated electrical fire control device;

[0010] A data analysis module is used to analyze the real-time monitoring data collected within a first preset time period before the fire accident occurs, perform data preprocessing, and determine whether the fire accident is an electrical fire;

[0011] The accident analysis module, when the fire accident is determined to be an electrical fire, further analyzes the real-time monitoring data collected within a second preset time period before the fire accident to determine whether the cause of the electrical fire is abnormal electrical equipment or aging of line insulation, where the second preset time period is greater than the first preset time period.

[0012] As a further solution of the present invention: the real-time monitoring data includes the full-wave amplitude of the load current.

[0013] As a further solution of the present invention: the real-time monitoring data of the intelligent electric monitoring terminal also includes load current harmonic components, full-wave amplitude of residual current, apparent power, active power, apparent electric energy, and active electric energy.

[0014] As a further solution of the present invention: the process of preprocessing of the data acquisition module is:

[0015] The monitoring data are clustered based on the DBSCAN algorithm to obtain outliers in the monitoring data. The collected outliers are deleted, the data are filled by the interpolation algorithm, and the noise in the monitoring data is filtered by the median filter.

[0016] As a further solution of the present invention: the process of the data acquisition module determining whether it is an electrical fire is as follows:

[0017] Obtain the values ​​of all monitoring parameters and power parameters in the first preset time period before the fire accident occurs. If the full-wave amplitude of the load current is 0, it is considered that the fire accident is not an electrical fire; if the full-wave amplitude of the load current exceeds the preset interval, the fire accident is considered to be an electrical fire; if the full-wave amplitude of the load current is within the preset interval, obtain one or more of the other real-time monitoring data, and when their values ​​exceed the corresponding preset interval, the fire accident is considered to be an electrical fire.

[0018] As a further solution of the present invention: the process of further analyzing the data by the accident analysis module is as follows:

[0019] The initial time series of the real-time monitoring data collected by the data collection module within the second preset time period before the fire accident is obtained, the length of the initial time series is collected and marked as L, the sliding step of the time series is obtained and marked as S, and the shortest sample length is marked as N, so that the initial time series is split into n sub-time series, n=L / SN.

[0020] As a further solution of the present invention: the process of the accident analysis module determining the cause of the electrical fire is:

[0021] The historical power consumption current time series x and the historical leakage current time series y in the time period t0 are constructed respectively, and the Pearson correlation coefficient r of the two series is calculated according to the following formula:

[0022]

[0023] Where N is the number of points in the time series, represents the mean of the historical electricity consumption time series, It represents the mean of the historical leakage current time series. When r is greater than the preset value, it is determined that the cause of the electrical fire in the line is a hidden danger in the equipment or a hidden danger in the joint of the equipment power supply line; when r is less than the preset value, it is determined that the cause of the electrical fire in the line is a hidden danger of wiring error or a hidden danger of aging and damage of the line insulation.

[0024] As a further solution of the present invention: the accident analysis module can import the identification results of the non-invasive load decomposition algorithm. If the algorithm recognizes that the electrical appliance is started in the first preset time period before the fire occurs, it is determined that the hidden danger of the electrical equipment or the hidden danger at the power supply line connection of the equipment is the cause of the electrical fire.

[0025] The fire investigation auxiliary method based on intelligent electrical monitoring includes the following steps:

[0026] S1. Find an intelligent electrical monitoring terminal whose monitoring range overlaps with the fire accident range, wherein the intelligent electrical monitoring terminal includes an electric meter, a circuit breaker, an electrical fire monitoring detector, and a smart socket;

[0027] S2. Obtaining real-time monitoring data from the above-mentioned intelligent electricity monitoring terminal;

[0028] S3. Determine whether the fire accident is an electrical fire based on the real-time power consumption monitoring data. If so, obtain all the historical power consumption monitoring data of the above-mentioned intelligent power monitoring terminal before the fire accident occurs; otherwise, stop determining;

[0029] S4. Regularize the historical electricity consumption monitoring data, construct a time series for the historical electricity consumption monitoring data, and perform a diachronic deviation analysis on the above time series. If the difference between the real-time current amplitude within t0 before the fire accident and the historical current average is greater than a preset threshold, it is determined that the cause of the electrical fire is abnormal electrical equipment; otherwise, it is determined that the cause of the electrical fire is aging of line insulation.

[0030] Beneficial effects of the present invention:

[0031] The present invention monitors the monitoring area by automatically collecting and analyzing electricity monitoring data, and quickly locks the involved area and the corresponding monitoring terminal when a fire occurs. By neatly processing and analyzing the time series of historical and real-time detection data, as well as utilizing correlation analysis, the abnormal behavior of electrical equipment and line insulation aging problems can be effectively identified, and the cause of the fire can be determined quickly and accurately, especially distinguishing between electrical fires and non-electrical fires, thereby reducing the guesswork and manual judgment in traditional investigation methods and improving investigation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The present invention will be further described below in conjunction with the accompanying drawings.

[0033] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] See also Figure 1 As shown, the present invention is a fire investigation auxiliary method and system based on intelligent electrical monitoring, including:

[0036] Fire investigation auxiliary system based on intelligent electrical monitoring, including:

[0037] The data acquisition module includes an intelligent electrical monitoring terminal for real-time acquisition of real-time monitoring data. The intelligent electrical monitoring terminal includes an electric meter, a circuit breaker, an electrical fire monitoring detector, an intelligent socket, and a dedicated electrical fire control device;

[0038] A data analysis module is used to analyze the real-time monitoring data collected within a first preset time period before the fire accident occurs, perform data preprocessing, and determine whether the fire accident is an electrical fire;

[0039] The accident analysis module, when the fire accident is determined to be an electrical fire, further analyzes the real-time monitoring data collected within a second preset time period before the fire accident to determine whether the cause of the electrical fire is abnormal electrical equipment or aging of line insulation, where the second preset time period is greater than the first preset time period.

[0040] The present invention first counts various intelligent electrical monitoring terminals in the monitoring area. When a fire accident occurs, the real-time monitoring data of the corresponding intelligent electrical monitoring terminal in a specific time period before the fire occurs is obtained. The real-time monitoring data is preprocessed, including cluster analysis to identify outliers, delete outliers, data filling and filtering and denoising. Determine whether it is an electrical fire based on the processed real-time power consumption monitoring data. If it is an electrical fire, obtain all historical power consumption data of the monitoring point before the fire occurs. Regularize the historical power consumption data and construct a time series. Perform a diachronic deviation analysis to compare the gap between the real-time current amplitude and the historical current mean. Construct a time series and calculate the Pearson correlation coefficient between different current time series. Determine the specific cause of the electrical fire based on the size of the correlation coefficient, such as equipment hidden dangers, power supply line problems, wiring errors or line aging.

[0041] In another preferred embodiment of the present invention, the real-time monitoring data includes the full-wave amplitude of the load current.

[0042] In another preferred embodiment of the present invention, the real-time monitoring data of the intelligent electrical monitoring terminal also includes load current harmonic components, residual current full-wave amplitude, apparent power, active power, apparent electric energy, and active electric energy.

[0043] In another preferred embodiment of the present invention, the preprocessing process of the data acquisition module is:

[0044] The monitoring data are clustered based on the DBSCAN algorithm to obtain outliers in the monitoring data. The collected outliers are deleted, the data are filled by the interpolation algorithm, and the noise in the monitoring data is filtered by the median filter.

[0045] In another preferred embodiment of the present invention, the process of the data acquisition module determining whether it is an electrical fire is as follows:

[0046] Obtain the values ​​of all monitoring parameters and power parameters in the first preset time period before the fire accident occurs. If the full-wave amplitude of the load current is 0, it is considered that the fire accident is not an electrical fire; if the full-wave amplitude of the load current exceeds the preset interval, the fire accident is considered to be an electrical fire; if the full-wave amplitude of the load current is within the preset interval, obtain one or more of the other real-time monitoring data, and when their values ​​exceed the corresponding preset interval, the fire accident is considered to be an electrical fire.

[0047] In another preferred embodiment of the present invention, the process of constructing the time series by the accident analysis module is:

[0048] The initial time series of electricity consumption monitoring data is obtained, the length of the initial time series is collected and marked as L, the sliding step of the time series is obtained and marked as S, and the shortest sample length is marked as N, so that the initial time series is split into n sub-time series, n=L / SN.

[0049] In another preferred embodiment of the present invention, the process of the accident analysis module determining the cause of the electrical fire is:

[0050] The historical power consumption current time series x and the historical leakage current time series y within the first preset time period are respectively constructed, and the Pearson correlation coefficient r of the two series is calculated according to the following formula:

[0051]

[0052] Where N is the number of points in the time series, represents the mean of the historical electricity consumption time series, It represents the mean of the historical leakage current time series. When r is greater than the preset value, it is determined that the cause of the electrical fire in the line is a hidden danger in the equipment or a hidden danger in the joint of the equipment power supply line; when r is less than the preset value, it is determined that the cause of the electrical fire in the line is a hidden danger of wiring error or a hidden danger of aging and damage of the line insulation.

[0053] In another preferred embodiment of the present invention, the accident analysis module can import the identification results of the non-invasive load decomposition algorithm. If the algorithm recognizes that the electrical appliance is started in the first preset time period before the fire occurs, it is determined that the hidden danger of the electrical equipment or the hidden danger at the power supply line joint of the equipment is the cause of the electrical fire.

[0054] The fire investigation auxiliary method based on intelligent electrical monitoring includes the following steps:

[0055] S1. Find an intelligent electrical monitoring terminal whose monitoring range overlaps with the fire accident range, wherein the intelligent electrical monitoring terminal includes an electric meter, a circuit breaker, an electrical fire monitoring detector, and a smart socket;

[0056] S2. Obtaining real-time monitoring data from the above-mentioned intelligent electricity monitoring terminal;

[0057] S3. Determine whether the fire accident is an electrical fire based on the real-time power consumption monitoring data. If so, obtain all the historical power consumption monitoring data of the above-mentioned intelligent power monitoring terminal before the fire accident occurs; otherwise, stop determining;

[0058] S4. Regularize the historical electricity consumption monitoring data, construct a time series for the historical electricity consumption monitoring data, and perform a diachronic deviation analysis on the above time series. If the difference between the real-time current amplitude within t0 before the fire accident and the historical current average is greater than a preset threshold, it is determined that the cause of the electrical fire is abnormal electrical equipment; otherwise, it is determined that the cause of the electrical fire is aging of line insulation.

[0059] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. Fire investigation auxiliary system based on intelligent electrical monitoring, characterized by: include: The data acquisition module includes an intelligent electrical monitoring terminal for real-time acquisition of real-time monitoring data. The intelligent electrical monitoring terminal includes an electric meter, a circuit breaker, an electrical fire monitoring detector, an intelligent socket, and a dedicated electrical fire control device; A data analysis module is used to analyze the real-time monitoring data collected within a first preset time period before the fire accident occurs, perform data preprocessing, and determine whether the fire accident is an electrical fire; The accident analysis module, when the fire accident is determined to be an electrical fire, further analyzes the real-time monitoring data collected within a second preset time period before the fire accident to determine whether the cause of the electrical fire is abnormal electrical equipment or aging of line insulation, where the second preset time period is greater than the first preset time period.

2. The fire investigation auxiliary system based on intelligent electrical monitoring according to claim 1 is characterized in that: The real-time monitoring data includes the full-wave amplitude of the load current.

3. The fire investigation auxiliary system based on intelligent electrical monitoring according to claim 2 is characterized in that: The real-time monitoring data of the intelligent electric monitoring terminal also includes load current harmonic components, residual current full-wave amplitude, apparent power, active power, apparent electric energy, and active electric energy.

4. The fire investigation auxiliary system based on intelligent electrical monitoring according to claim 1 is characterized in that: The process of preprocessing in the data acquisition module is as follows: The monitoring data are clustered based on the DBSCAN algorithm to obtain outliers in the monitoring data. The collected outliers are deleted, the data are filled by the interpolation algorithm, and the noise in the monitoring data is filtered by the median filter.

5. The fire investigation auxiliary system based on intelligent electrical monitoring according to claim 3 is characterized in that: The process of the data acquisition module determining whether it is an electrical fire is as follows: Obtain the values ​​of all monitoring parameters and power parameters in the first preset time period before the fire accident occurs. If the full-wave amplitude of the load current is 0, it is considered that the fire accident is not an electrical fire; if the full-wave amplitude of the load current exceeds the preset interval, the fire accident is considered to be an electrical fire; if the full-wave amplitude of the load current is within the preset interval, obtain one or more of the other real-time monitoring data, and when their values ​​exceed the corresponding preset interval, the fire accident is considered to be an electrical fire.

6. The fire investigation auxiliary system based on intelligent electrical monitoring according to claim 1 is characterized in that: The process of further analyzing data by the accident analysis module is as follows: The initial time series of the real-time monitoring data collected by the data collection module within the second preset time period before the fire accident is obtained, the length of the initial time series is collected and marked as L, the sliding step of the time series is obtained and marked as S, and the shortest sample length is marked as N, so that the initial time series is split into n sub-time series, n=L / SN.

7. The fire investigation auxiliary system based on intelligent electrical monitoring according to claim 6 is characterized in that: The process of the accident analysis module determining the cause of the electrical fire is as follows: The historical power consumption current time series x and the historical leakage current time series y in the time period t0 are constructed respectively, and the Pearson correlation coefficient r of the two series is calculated according to the following formula: Where N is the number of points in the time series, represents the mean of the historical electricity consumption time series, It represents the mean of the historical leakage current time series. When r is greater than the preset value, it is determined that the cause of the electrical fire in the line is a hidden danger in the equipment or a hidden danger in the joint of the equipment power supply line; when r is less than the preset value, it is determined that the cause of the electrical fire in the line is a hidden danger of wiring error or a hidden danger of aging and damage of the line insulation.

8. The fire investigation auxiliary system based on intelligent electrical monitoring according to claim 7 is characterized in that: The accident analysis module can import the identification results of the non-intrusive load decomposition algorithm. If the algorithm recognizes that the electrical appliance is started in the first preset time period before the fire occurs, it is determined that the hidden danger of the electrical equipment or the hidden danger at the power supply line joint of the equipment is the cause of the electrical fire.

9. A fire investigation auxiliary method based on intelligent electrical monitoring, characterized in that: The following steps are involved: S1. Find an intelligent electrical monitoring terminal whose monitoring range overlaps with the fire accident range, wherein the intelligent electrical monitoring terminal includes an electric meter, a circuit breaker, an electrical fire monitoring detector, and a smart socket; S2. Obtaining real-time monitoring data from the above-mentioned intelligent electricity monitoring terminal; S3. Determine whether the fire accident is an electrical fire based on the real-time power consumption monitoring data. If so, obtain all the historical power consumption monitoring data of the above-mentioned intelligent power monitoring terminal before the fire accident occurs; otherwise, stop determining; S4. Regularize the historical electricity consumption monitoring data, construct a time series for the historical electricity consumption monitoring data, and perform a diachronic deviation analysis on the above time series. If the difference between the real-time current amplitude within t0 before the fire accident and the historical current average is greater than a preset threshold, it is determined that the cause of the electrical fire is abnormal electrical equipment; otherwise, it is determined that the cause of the electrical fire is aging of line insulation.

Images