Automatic fire early warning method and system based on multi-threshold comparison

Abstract

The invention belongs to the technical field of fire safety, and provides a multi-threshold comparison fire automatic early warning method and system, the average value, peak value and change rate of digital signals after ultraviolet intensity conversion are respectively compared with preset corresponding thresholds, and absolute values of difference values between the average value, the peak value and the change rate and the corresponding thresholds are respectively obtained; when any parameter of the average value, the peak value and the change rate is greater than a corresponding threshold value, performing weighted summation on absolute values of all the difference values to obtain a judgment value; the alarm value is comprehensively determined through the average value, the peak value and the change rate of the digital signals after ultraviolet intensity conversion, so that the phenomenon that the alarm cannot be triggered in time due to the fact that the smoke concentration change response is not sensitive enough and the peak value is not high when single signals such as the peak value are adopted for judgment is avoided; and the phenomenon of false alarm caused by over-high peak value in a short time due to solid particles and dust in the airflow is avoided, and the problems of insufficient fire alarm sensitivity and high false alarm rate are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of fire safety, and particularly relates to a multi-threshold comparison-based automatic fire warning method and system. Background Art

[0002] During the production of fiberglass products and hazardous chemicals, etc., in accordance with the relevant regulations on work safety and protection, some fire-fighting equipment needs to be installed in the workshops and factories of fiberglass products, such as automatic fire alarms and automatic fire extinguishers, etc.

[0003] Currently, the automatic fire alarms arranged in the factory area have problems such as insufficient sensitivity and high false alarm rate; for example, when using an ultraviolet alarm, it makes a judgment based on a single signal such as the peak value of the digital signal converted according to the ultraviolet intensity, and is not sensitive enough to the change in the smoke concentration in the initial stage of a fire. Especially when the smoke is diluted due to air flow, the peak value is not high, and the alarm may not be triggered in time. In an open environment, since the air flow often contains solid particles and dust from the external space, the peak value is too high in a short period, which may cause a false alarm signal to be sent when the dust concentration is high. Summary of the Invention

[0004] In order to solve the above problems, the present invention proposes a multi-threshold comparison-based automatic fire warning method and system. The present invention comprehensively determines the alarm value based on the average value, peak value, and change rate of the digital signal after converting the ultraviolet intensity, avoiding the phenomenon that when using a single signal such as the peak value for judgment, it is not sensitive enough to the change in the smoke concentration in the initial stage of a fire, and the peak value is not high enough to cause the alarm not to be triggered in time. It also avoids the phenomenon of false alarms caused by the peak value being too high in a short period due to solid particles and dust in the air flow, and solves the problems of insufficient sensitivity of fire alarms and high false alarm rate.

[0005] In order to achieve the above object, the present invention is implemented by the following technical solutions:

[0006] In a first aspect, the present invention provides a multi-threshold comparison-based automatic fire warning method, including:

[0007] Obtain the ultraviolet signal of the area to be monitored;

[0008] Convert the ultraviolet signal into a digital signal, and extract the average value, peak value, and change rate of the digital signal;

[0009] Compare the average value, peak value, and change rate with the preset corresponding thresholds respectively, and obtain the absolute values of the differences between the average value, peak value, and change rate and the corresponding thresholds respectively; when any one of the average value, peak value, and change rate is greater than the corresponding threshold, perform a weighted sum of all the absolute values of the differences to obtain a judgment value;

[0010] When the judgment value is less than the preset value, an alarm is given; otherwise, no alarm is given.

[0011] Further, convert the light intensity into a voltage signal:

[0012] I s = k·P u + I d ;

[0013] U o = R f ·I s = R f ·(k·P u + I d );

[0014] Wherein, I s is the output current of the sensor; k is the sensitivity of the sensor; P u is the ultraviolet intensity; I d is the dark current, the background noise current without light; U o is the output voltage; R f is the feedback resistance;

[0015] Quantize the voltage signal into a digital signal D through an analog-to-digital converter:

[0016]

[0017] Wherein, V r1 and V r2 are the positive and negative terminals of the reference voltage of the analog-to-digital converter; N is the number of bits of the analog-to-digital converter; convert the digital signal into the ultraviolet intensity.

[0018] Further, filter the ultraviolet signal.

[0019] Further, the average value refers to the average value of the ultraviolet signal within a preset time; the change rate refers to the ratio of the difference between the ultraviolet intensity at the current time point and the ultraviolet intensity at the previous time point to the ultraviolet intensity at the previous time point.

[0020] Further, the judgment value X is:

[0021]

[0022] Wherein, T is the average value; A is the peak value; V is the change rate; Q 1 、Q 2 and Q 3 are the corresponding preset thresholds; α, β and γ are weight coefficients.

[0023] Further, when the judgment value is less than the first preset value and greater than the second preset value, a first-level alarm is triggered; at this time, automatic fire extinguishing is not carried out, and after confirmation by the staff through video or on-site inspection, fire extinguishing measures are taken.

[0024] When the judgment value is less than or equal to the second preset value and greater than the third preset value, a second-level alarm is triggered; at this time, automatic fire extinguishing is carried out, and the automatic fire extinguisher operates, and the staff needs to arrive at the scene for confirmation.

[0025] When the judgment value is less than or equal to the third preset value, a third-level alarm is triggered; at this time, automatic fire extinguishing is carried out, and an alarm call is automatically made through intelligent devices; the first preset value is greater than the second preset value, and the second preset value is greater than the third preset value.

[0026] In a second aspect, the present invention further provides a multi-threshold comparison-based automatic fire warning system, including:

[0027] A data acquisition module, configured to: obtain ultraviolet signals in the area to be monitored;

[0028] A conversion module, configured to: convert the ultraviolet signals into digital signals, and extract the average value, peak value, and change rate of the digital signals;

[0029] A judgment value determination module, configured to: compare the average value, peak value, and change rate with the preset corresponding thresholds respectively, and obtain the absolute values of the differences between the average value, peak value, and change rate and the corresponding thresholds; when any one of the average value, peak value, and change rate is greater than the corresponding threshold, perform a weighted sum of all the absolute values of the differences to obtain a judgment value;

[0030] An early warning module, configured to: trigger an alarm when the judgment value is less than the preset value, otherwise no alarm is triggered.

[0031] In a third aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the multi-threshold comparison-based automatic fire warning method described in the first aspect are implemented.

[0032] In a fourth aspect, the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and capable of running on the processor, and when the processor executes the program, the steps of the multi-threshold comparison-based automatic fire warning method described in the first aspect are implemented.

[0033] In a fifth aspect, the present invention further provides a computer program product, the computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the multi-threshold comparison-based automatic fire warning method described in the first aspect are implemented.

[0034] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0035] In the present invention, the average value, peak value, and change rate of the digital signal after ultraviolet intensity conversion are respectively compared with the preset corresponding thresholds, and the absolute values of the differences between the average value, peak value, and change rate and the corresponding thresholds are obtained respectively; when any one of the average value, peak value, and change rate is greater than the corresponding threshold, the absolute values of all differences are weighted and summed to obtain a judgment value; when the judgment value is less than the preset value, an alarm is issued, otherwise no alarm is issued; by comprehensively determining the alarm value based on the average value, peak value, and change rate of the digital signal after ultraviolet intensity conversion, it is possible to avoid the phenomenon that when using a single signal such as the peak value for judgment, the response to the change in the smoke concentration in the initial stage of a fire is not sensitive enough, and the peak value is not high enough to trigger an alarm in a timely manner, and it is also possible to avoid the phenomenon of false alarms caused by too high a peak value in the short term due to solid particles and dust in the air flow, thus solving the problems of insufficient sensitivity of fire alarm and high false alarm rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings forming a part of this embodiment are used to provide a further understanding of this embodiment. The schematic embodiments and descriptions thereof of this embodiment are used to explain this embodiment and do not constitute an improper limitation of this embodiment.

[0037] Figure 1 It is a block diagram of the early warning system of the present invention;

[0038] Figure 2 It is a block diagram of the calculation module of the early warning system of the present invention;

[0039] Figure 3 It is a block diagram of the alarm module of the early warning system of the present invention;

[0040] Figure 4 It is a flowchart of the operation of the early warning system of the present invention;

[0041] Figure 5 It is a framework diagram of the ultraviolet flame detection process of the early warning system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0043] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present application belongs.

[0044] The main characteristics of existing fire alarm methods and systems are as follows:

[0045] Dependence on a dedicated control room and personnel: The current system must establish a dedicated control room and allocate monitoring personnel on duty around the clock. The fire alarm signal is transmitted to the control room through a wired network, but the on-duty personnel cannot directly observe the on-site situation and need to contact the on-site personnel additionally for on-site inspection and handling. Many limitations in wired transmission: The alarm signal depends on wired network transmission, which not only makes the wiring work cumbersome and costly, but is also easily affected by factors such as line damage and aging, resulting in unstable or interrupted signal transmission. Insufficient sensitivity: The system is not sensitive enough to the change in smoke concentration in the initial stage of a fire. Especially when the smoke is diluted due to air flow, it may not be able to trigger the alarm in time. This leads to a time delay from the occurrence of the fire to the transmission of the alarm signal to the control room, and the best opportunity to extinguish the initial fire may be missed. Great limitations in the installation environment: The system has relatively strict requirements for the installation environment. The monitoring probe needs to be installed above combustibles to ensure the detection range. In factories or warehouses with large spaces, the installation difficulty increases, which may affect the detection effect. High false alarm rate: This system is mainly applicable to enclosed or semi-enclosed spaces. In an open environment, since the air flow often contains solid particles and dust from the external space, it may cause the system to falsely send alarm signals when the dust concentration is relatively high.

[0046] As recorded in the background technology, problems such as insufficient sensitivity and high false alarm rate are relatively prominent. For example, when using an ultraviolet alarm, it judges based on a single signal such as the peak value of the digital signal converted according to the ultraviolet intensity. It is not sensitive enough to the change in smoke concentration in the initial stage of a fire. Especially when the smoke is diluted due to air flow, the peak value is not high and it may not be able to trigger the alarm in time. In an open environment, since the air flow often contains solid particles and dust from the external space, it causes the peak value to be too high in a short period, and it may cause the system to falsely send alarm signals when the dust concentration is relatively high.

[0047] In view of the above problems, the present invention provides a multi-threshold comparison method for automatic fire warning. After obtaining the ultraviolet signal in the area to be monitored; converting the ultraviolet signal into a digital signal, and extracting the average value, peak value and change rate of the digital signal; then, comparing the average value, peak value and change rate with the preset corresponding thresholds respectively, and obtaining the absolute values of the differences between the average value, peak value and change rate and the corresponding thresholds respectively; when any one of the average value, peak value and change rate is greater than the corresponding threshold, performing a weighted sum of all the absolute values of the differences to obtain a judgment value; finally, when the judgment value is less than the preset value, an alarm is given, otherwise no alarm is given.

[0048] By comprehensively determining the alarm value based on the average value, peak value, and change rate of the digital signal after ultraviolet intensity conversion, it avoids the phenomenon that when using a single signal such as the peak value for judgment, the response to the change in smoke concentration in the initial stage of a fire is not sensitive enough, and the peak value is not high enough to trigger the alarm in a timely manner. It also avoids the phenomenon of false alarms caused by excessive peak values in the short term due to solid particles and dust in the airflow, and solves the problems of insufficient fire alarm sensitivity and a relatively high false alarm rate.

[0049] Embodiment 1:

[0050] The present invention provides a multi-threshold comparison automatic fire warning method, including:

[0051] S1. According to the relevant regulations on the safe production and protection of fiberglass products and hazardous chemicals, etc., set ultraviolet fire alarms and automatic fire extinguishers, etc. in the workshops and / or factories of fiberglass products, etc. Among them, the ultraviolet fire alarm is at least provided with an ultraviolet sensor, a data processing and calculation device, an alarm device, etc.

[0052] Collect the ultraviolet signal in the workshop and / or factory through the data acquisition device in the ultraviolet fire alarm, such as an ultraviolet sensor.

[0053] S2. Convert the ultraviolet signal collected in step S1 into a digital signal.

[0054] Convert the light intensity into a current or voltage signal:

[0055] I s = k·P u + I d ;

[0056] U o = R f ·I s = R f ·(k·P u + I d ) ;

[0057] Among them, I s is the output current of the sensor; k is the sensitivity of the sensor; P u is the ultraviolet intensity; I d is the dark current, the background noise current without light; U o is the output voltage; R f is the feedback resistance.

[0058] Quantize the voltage signal into a digital signal D through an analog-to-digital converter:

[0059]

[0060] Among them, V r1 and Vr2 are the positive and negative terminals of the reference voltage of the analog-to-digital converter; N is the number of bits of the analog-to-digital converter. Convert the digital signal D into the ultraviolet intensity P u : If the sensor response is linear, then:

[0061] P u = a·D + b;

[0062] where, a is the slope; b is the offset term; a and b can be determined through a calibration experiment.

[0063] For a non-linear sensor, then:

[0064] P u = c 0 + c 1 D + c 2 D 2 +…+ c 2 D 2 ;

[0065] where, c 0 , c 1 ,…, c n are calibration coefficients and can be obtained through experimental calibration.

[0066] S3. Filter the data to eliminate noise and interference, and use an average filter for signal processing.

[0067] Optionally, use an average filter for signal processing; filter the data to eliminate noise and interference.

[0068] S4. Calculate the average value T, peak value A, and change rate V of the digital signal in step 3.

[0069] The average value refers to the average value of the output signal after the ultraviolet sensor operates for a period of time. Since the ultraviolet sensor will be affected by factors such as ambient temperature change, power supply voltage change, and particles in the air during operation, the output signal will fluctuate. To ensure the detection accuracy, the output signal is averaged to exclude the interference of the fluctuation factor and obtain a more accurate detection result.

[0070] The change rate refers to the ratio of the difference between the ultraviolet intensity at the current time point and the ultraviolet intensity at the previous time point to the ultraviolet intensity at the previous time point.

[0071]

[0072] where, P u , t is the ultraviolet intensity at the current time point; P u , t-1is the ultraviolet intensity at the previous time point, and the interval between the current time point and the previous time point can be preset.

[0073] S5. Compare the average value, peak value, and change rate with the preset corresponding thresholds respectively, and obtain the absolute values of the differences between the average value, peak value, and change rate and the corresponding thresholds respectively; when any one of the average value, peak value, and change rate is greater than the corresponding threshold, perform a weighted sum of all the absolute values of the differences to obtain a judgment value. The judgment value X is:

[0074]

[0075] where T is the average value; A is the peak value; V is the change rate; Q 1 、Q 2 and Q 3 are the corresponding preset thresholds; α, β, and γ are weight coefficients, which can be determined through experiments or obtained by fitting historical data, etc.

[0076] S5. When the judgment value is less than the preset value, it means that at least one of the other two parameters is close to the corresponding threshold, and at this time, an alarm is given, otherwise no alarm is given.

[0077] When the judgment value is less than the first preset value and greater than the second preset value, a first-level alarm is given; at this time, automatic fire extinguishing is not performed, the automatic fire extinguisher does not work, and the staff will perform fire extinguishing treatment after confirmation through video or on-site.

[0078] When the judgment value is less than or equal to the second preset value and greater than the third preset value, a second-level alarm is given; at this time, automatic fire extinguishing is performed, the automatic fire extinguisher works, and the staff needs to arrive at the scene for confirmation.

[0079] When the judgment value is less than or equal to the third preset value, a third-level alarm is given; at this time, automatic fire extinguishing is performed, the automatic fire extinguisher works, and an alarm call is automatically made through intelligent devices, etc.

[0080] The first preset value is greater than the second preset value, and the second preset value is greater than the third preset value.

[0081] Embodiment 2:

[0082] Such as Figure 1As shown in the figure, in order to implement and realize the method in Embodiment 1, this embodiment provides a multi-threshold comparison automatic fire warning system, including an ultraviolet sensor, a data acquisition module, a data transmission module, a data processing module, a feature extraction module, a calculation module, a data comparison module, a judgment module, an alarm module, an optimization module, a threshold setting module, a monitoring module, and a remote background terminal, etc. The ultraviolet sensor is connected to the data acquisition module, the data acquisition module is connected to the data transmission module, the data transmission module is connected to the data processing module, the data processing module is connected to the feature extraction module, the feature extraction module is connected to the calculation module, the calculation module is connected to the data comparison module, the data comparison module is connected to the judgment module, the judgment module is connected to the alarm module, the optimization module is connected to the calculation module and the threshold setting module, the threshold setting module is connected to the data comparison module, the monitoring module is connected to the judgment module, and the remote background terminal is connected to the monitoring module.

[0083] In this embodiment, the ultraviolet sensor is used to detect ultraviolet radiation, collect the ultraviolet intensity in the application scenario, and the analyzer converts the sensor signal into a digital signal and transmits it to the main control unit to convert the ultraviolet intensity into a standard electrical signal and transmit it to the data acquisition module.

[0084] Optionally, the data acquisition module regularly reads data from the ultraviolet sensor and transmits the read data to the data processing module through the data transmission module. The data processing module is used to filter the data to eliminate noise and interference, and uses an average filter for signal processing. The feature extraction module is used to extract features related to the flame from the preprocessed data and transmit the extracted features to the calculation module.

[0085] Such as Figure 2 、 Figure 3 、 Figure 4 and Figure 5As shown, optionally, the calculation module is used to calculate the average value, peak value, and change rate of the ultraviolet radiation intensity, and transmit the calculated average value, peak value, and change rate to the data comparison module. The threshold setting module is used to set the comparison thresholds for the average value, peak value, and change rate, and compare the calculated average value, peak value, and change rate with the corresponding thresholds respectively. The judgment module analyzes and judges the comparison results. If the calculated value exceeds the threshold, it is considered that there is a flame. The alarm module is used to alarm when the judgment module determines that there is a flame. The optimization module uses machine learning or deep learning technology to automatically adjust the threshold and optimize the algorithm performance of the calculation module. The monitoring module is used to monitor the site, and the remote background terminal is used for the management personnel to remotely observe the monitoring screen of the monitoring module. The calculation module includes a receiving unit, which is connected to an average value calculation unit, the average value calculation unit is connected to a peak value calculation unit, and the peak value calculation unit is connected to a change rate calculation unit. The alarm module includes a telephone alarm unit, which is connected to a WeChat alarm unit, the WeChat alarm unit is connected to a text message alarm unit, and the text message alarm unit is connected to an audible and visual alarm unit. The average value calculation unit is used to calculate the average value of the ultraviolet radiation intensity, the peak value calculation unit is used to calculate the peak value of the ultraviolet radiation intensity, and the change rate calculation unit is used to calculate the change rate of the ultraviolet radiation intensity.

[0086] In some embodiments, through the data collection of ultraviolet sensors and based on computer data AI algorithms, a fire warning device for fixed production sites is formed. For back-end development, an app mini-program and WeChat mobile warning are integrated to realize an information linkage warning device for non-fixed fire prevention units. Compared with traditional fire alarm systems, it has the functions of high sensitivity, fast response, simple installation, strong environmental adaptability, low cost, and wireless transmission. It effectively solves the drawbacks of the previous systems. When a fire breaks out, it quickly gives an audible and visual alarm to remind nearby personnel to carry out emergency disposal at the initial stage of the fire. The system can wirelessly transmit, automatically make phone calls, send WeChat messages, and send text messages to notify relevant personnel for dispatching and command. It does not require a control room and dedicated personnel to be on duty 24 hours a day, saving manpower and material resources, and the sensitivity and response degree are also correspondingly improved. It is suitable for fire monitoring and prevention in occasions with large areas, wide regions, and strong dispersion.

[0087] In some embodiments, an ultraviolet sensor has a detection area of 100 square meters, with a wide detection range; it can detect tiny fire sources, is not affected by the size of the fire and the smoke concentration, and has characteristics such as high sensitivity and high stability. When a fire breaks out, this system can quickly output an alarm signal within less than 0.5 seconds, driving on-site audible and visual alarms. When the ultraviolet sensor detects a fire signal, it will automatically call, send WeChat messages, and send text messages to the system-set personnel through the Internet of Things platform within less than 3 seconds. The fire detection system does not require a control room and dedicated personnel to be on duty 24 hours a day. Managers can view the on-site real-time monitoring images and perform remote monitoring operations on their mobile phones through the network at any time. The system is not restricted by the on-site environment, is simple to construct, easy to install, has low costs, and can be recycled.

[0088] In some embodiments, an ultraviolet (UV) flame detection algorithm is used to detect fires, mainly based on the specific radiation characteristics of flames in the ultraviolet band. Certain chemical substances in flames (such as hydrocarbons) emit ultraviolet radiation when burning. Using the ultraviolet method for detection has the characteristics of high sensitivity, stability, and reliability.

[0089] The modules corresponding to the system in this embodiment also implement the method in Embodiment 1, which will not be elaborated here.

[0090] Embodiment 3:

[0091] This embodiment provides a multi-threshold comparison-based automatic fire warning system, which is different from Embodiment 2 in that it includes an ultraviolet sensor, a data acquisition module, a data transmission module, a data processing module, a feature extraction module, a calculation module, a data comparison module, a judgment module, an alarm module, an optimization module, a threshold setting module, a monitoring module, a remote background terminal, a timing module, an emergency handling module, and a treatment plan setting module. The ultraviolet sensor is connected to the data acquisition module, the data acquisition module is connected to the data transmission module, the data transmission module is connected to the data processing module, the data processing module is connected to the feature extraction module, the feature extraction module is connected to the calculation module, the calculation module is connected to the data comparison module, the data comparison module is connected to the judgment module, the judgment module is connected to the alarm module, the optimization module is connected to the calculation module and the threshold setting module, the threshold setting module is connected to the data comparison module, the monitoring module is connected to the judgment module, the remote background terminal is connected to the monitoring module, the alarm module is connected to the timing module, the timing module is connected to the emergency handling module, and the treatment plan setting module is connected to the emergency handling module;

[0092] The ultraviolet sensor is used to detect ultraviolet radiation, collect the ultraviolet intensity in the application scenario. The analyzer converts the sensor signal into a digital signal and transmits it to the main control unit to convert the ultraviolet intensity into a standard electrical signal, which is transmitted to the data acquisition module. The data acquisition module regularly reads data from the ultraviolet sensor and transmits the read data to the data processing module through the data transmission module. The data processing module is used to filter the data to eliminate noise and interference, and uses an average filter for signal processing. The feature extraction module is used to extract features related to the flame from the preprocessed data and transmit the extracted features to the calculation module. The calculation module is used to calculate the average value, peak value, and change rate of the ultraviolet radiation intensity, and transmit the calculated average value, peak value, and change rate to the data comparison module. The threshold setting module is used to set the comparison thresholds for the average value, peak value, and change rate, and compare the calculated average value, peak value, and change rate with the corresponding thresholds respectively. The judgment module analyzes and judges the comparison results. If the calculated value exceeds the threshold, it is considered that there is a flame. The alarm module is used to alarm when the judgment module determines that there is a flame. The optimization module uses machine learning or deep learning technology to automatically adjust the threshold and optimize the algorithm performance of the calculation module. The monitoring module is used to monitor the site, and the remote background terminal is used for managers to remotely observe the monitoring screen of the monitoring module. After the alarm module alarms, the timing module starts timing. If no measures are taken for the flame within the specified time, the emergency processing module starts a preset processing plan.

[0093] Embodiment 4:

[0094] This embodiment provides a multi-threshold comparison automatic fire warning system, including:

[0095] A data acquisition module, configured to: obtain the ultraviolet signal of the area to be monitored;

[0096] A conversion module, configured to: convert the ultraviolet signal into a digital signal, and extract the average value, peak value, and change rate of the digital signal;

[0097] A judgment value determination module, configured to: compare the average value, peak value, and change rate with the preset corresponding thresholds respectively, and obtain the absolute values of the differences between the average value, peak value, and change rate and the corresponding thresholds respectively; when any one of the average value, peak value, and change rate is greater than the corresponding threshold, perform a weighted sum of all the absolute values of the differences to obtain a judgment value;

[0098] An early warning module, configured to: alarm when the judgment value is less than the preset value, otherwise do not alarm.

[0099] The working method of the system is the same as that of the multi-threshold comparison automatic fire warning method in Embodiment 1, and will not be elaborated here.

[0100] Embodiment 5:

[0101] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps of the multi-threshold comparison-based automatic fire warning method described in Embodiment 1 are implemented.

[0102] Embodiment 6:

[0103] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored on the memory and capable of running on the processor. When the processor executes the program, the steps of the multi-threshold comparison-based automatic fire warning method described in Embodiment 1 are implemented.

[0104] Embodiment 7:

[0105] This embodiment provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the multi-threshold comparison-based automatic fire warning method described in Embodiment 1 are implemented.

[0106] The above are only the preferred embodiments of this embodiment and are not used to limit this embodiment. For those skilled in the art, this embodiment can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this embodiment shall be included within the protection scope of this embodiment.

Claims

1. A multi-threshold comparison fire automatic warning method, characterized in that: include: Obtaining ultraviolet signals from the area to be monitored; Converting the ultraviolet signal into a digital signal, and extracting the average value, peak value and change rate of the digital signal; The average value, peak value and change rate are compared with the preset corresponding thresholds respectively, and the absolute values ​​of the differences between the average value, peak value and change rate and the corresponding thresholds are obtained respectively; when any parameter among the average value, peak value and change rate is greater than the corresponding threshold, the absolute values ​​of all the differences are weighted summed to obtain the judgment value; When the judgment value is less than the preset value, an alarm is triggered; otherwise, no alarm is triggered.

2. The multi-threshold comparison automatic fire warning method according to claim 1, characterized in that: Convert light intensity into voltage signal: I s =k·P u +I d ; U o =R f ·I s =R f ·(k·P u +I d ); Among them, I s is the sensor output current; k is the sensor sensitivity; P u is the intensity of ultraviolet light; I d is the dark current, the background noise current when there is no light; U o is the output voltage; R f is the feedback resistor; The voltage signal is quantized into a digital signal D through an analog-to-digital converter: Among them, V r1 and N r2 are the positive and negative ends of the analog-to-digital converter reference voltage; N is the number of bits of the analog-to-digital converter; the digital signal is converted into ultraviolet intensity.

3. The multi-threshold comparison automatic fire warning method according to claim 1, characterized in that: The ultraviolet signal is filtered.

4. The multi-threshold comparison automatic fire warning method according to claim 1, characterized in that: The average value refers to the average value of the ultraviolet signal within a preset time period; the rate of change refers to the ratio of the difference between the ultraviolet intensity at the current time point and the ultraviolet intensity at the previous time point to the ultraviolet intensity at the previous time point.

5. The multi-threshold comparison automatic fire warning method according to claim 1, characterized in that: The judgment value X is: Among them, T is the average value; A is the peak value; V is the rate of change; Q1, Q2 and Q3 are the corresponding preset thresholds; α, β and γ are weight coefficients.

6. The multi-threshold comparison automatic fire warning method according to claim 1, characterized in that: When the judgment value is less than the first preset value and greater than the second preset value, a first-level alarm is issued; at this time, automatic fire extinguishing is not performed, and the staff performs fire extinguishing after confirming through video or on-site; When the judgment value is less than or equal to the second preset value and greater than the third preset value, a secondary alarm is issued; at this time, automatic fire extinguishing is performed, the automatic fire extinguisher works, and the staff needs to arrive at the scene for confirmation; If the judgment value is less than or equal to the third preset value, a third-level alarm is issued; at this time, the fire is automatically extinguished, and the alarm number is automatically dialed through the smart device; the first preset value is greater than the second preset value, and the second preset value is greater than the third preset value.

7. A multi-threshold comparison automatic fire warning system, characterized in that: include: The data acquisition module is configured to: obtain the ultraviolet signal of the area to be monitored; A conversion module is configured to: convert the ultraviolet signal into a digital signal, and extract an average value, a peak value and a change rate of the digital signal; The judgment value determination module is configured to: compare the average value, peak value and change rate with the preset corresponding thresholds, and obtain the absolute value of the difference between the average value, peak value and change rate and the corresponding thresholds; when any parameter among the average value, peak value and change rate is greater than the corresponding threshold, the absolute values ​​of all the differences are weighted summed to obtain the judgment value; The early warning module is configured to give an alarm when the judgment value is less than a preset value, and not give an alarm otherwise.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the automatic fire warning method based on multi-threshold comparison as described in any one of claims 1 to 6 are implemented.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor executes the program, the steps of the automatic fire warning method based on multi-threshold comparison as described in any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the automatic fire warning method based on multi-threshold comparison as described in any one of claims 1 to 6 are implemented.

Images