Intelligent explosion-proof electric appliance monitoring and protecting system

Abstract

The invention relates to the technical field of electric appliance monitoring and protection systems, and discloses an intelligent explosion-proof electric appliance monitoring and protection system which comprises an electric appliance data acquisition module, an electric appliance data analysis module and a processing module. The intelligent explosion-proof electric appliance monitoring and protecting system judges whether the electric appliance is abnormal or not according to power fluctuation by combining various factors of an actual use environment, judges the ignition probability of the electric appliance according to the actual environment factors when the electric appliance is abnormal, obtains the ignition probability according to calculation, and compares the ignition probability with an alarm threshold value, so that the safety of the electric appliance is improved. And the processing module performs corresponding operation according to the different signals and gives out early warning, so that early warning or power failure or power failure alarm can be given out in time, potential safety hazards are reduced, multiple data are fused, information islands are avoided, and the safety of the system is improved. Therefore, the intelligent explosion-proof electric appliance is effectively monitored, the corresponding early warning information is sent out according to the current state of the intelligent explosion-proof electric appliance, and the safety risk is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical appliance monitoring and protection systems, in particular to an intelligent explosion-proof electrical appliance monitoring and protection system. Background Art

[0002] The intelligent explosion-proof electrical monitoring and protection system is a comprehensive safety management system designed specifically for hazardous environments. It is used to monitor the operating status of electrical equipment to prevent accidents. This system is widely used in petrochemical, coal mining, electric power and other fields that require explosion-proof safety, and helps prevent safety accidents caused by electrical equipment failures.

[0003] At present, the intelligent explosion-proof electrical appliance monitoring and protection system usually collects one or more data and compares one or more data with the corresponding threshold value to determine the current status of the intelligent explosion-proof electrical appliance. However, this system has a low degree of integration and is prone to information island phenomenon. It is impossible to effectively monitor the intelligent explosion-proof electrical appliance and issue corresponding warning information according to the current status of the intelligent explosion-proof electrical appliance, thereby increasing safety risks. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides an intelligent explosion-proof electrical appliance monitoring and protection system, which is capable of combining various factors of the actual use environment and judging whether the electrical appliance is abnormal according to power fluctuations. When an abnormality occurs, the fire probability of the electrical appliance is judged in combination with actual environmental factors, and the fire probability is calculated, and the fire probability is compared with the alarm threshold, thereby obtaining different signals, and performing corresponding operations and issuing early warnings according to different signals through a processing module, so that early warnings or power-off or power-off alarms can be issued in time to reduce safety hazards. At the same time, multiple data are integrated to avoid information islands, thereby effectively monitoring the intelligent explosion-proof electrical appliances and issuing corresponding early warning information according to the current status of the intelligent explosion-proof electrical appliances, reducing safety risks, etc., and solving the above problems.

[0006] (II) Technical solution

[0007] To achieve the above-mentioned object, the present invention provides the following technical solutions: an intelligent explosion-proof electrical appliance monitoring and protection system, comprising an electrical appliance data acquisition module, an electrical appliance data processing module, an electrical appliance data analysis module and a processing module;

[0008] The electrical appliance data acquisition module includes an electrical appliance temperature acquisition unit, an electrical appliance humidity acquisition unit, an electrical appliance power acquisition unit, and a gas concentration acquisition unit;

[0009] The electrical temperature acquisition unit is used to collect real-time temperature data Wd of the electrical appliance during operation, the electrical humidity acquisition unit is used to collect real-time humidity data Sd of the surrounding environment of the electrical appliance during operation, the electrical power acquisition unit is used to collect real-time power data Gl of the electrical appliance during operation, and the gas concentration acquisition unit is used to collect real-time carbon monoxide concentration data Nd of the surrounding environment of the electrical appliance during operation;

[0010] The electrical appliance data acquisition module forms corresponding real-time temperature data sets, real-time humidity data sets, real-time power data sets and real-time carbon monoxide concentration data sets with the collected data, and sends these data sets to the electrical appliance data processing module;

[0011] The electrical appliance data processing module calculates the power mean value based on the real-time power data set And the two adjacent power means are calculated Calculate the power fluctuation rate BD and compare it with the set power fluctuation threshold BDyz. When the power fluctuation rate BD is greater than the power fluctuation threshold BDyz, determine that the power of the electrical appliance is abnormal. When the electrical appliance data processing module determines that the power of the electrical appliance is abnormal, pre-process the data in the real-time temperature data set, the real-time humidity data set and the real-time carbon monoxide concentration data set collected at the same time as the real-time power data set, and respectively obtain the real-time temperature QWd value after cleaning, the real-time humidity value QSd after cleaning and the real-time carbon monoxide concentration QNd value after cleaning, and calculate the electrical appliance fire probability index ZB based on these values. The electrical appliance processing module converts the calculated electrical appliance fire probability index ZB into the fire probability Gl and sends it to the electrical appliance data analysis module;

[0012] The electrical appliance data analysis module compares the fire probability G1 with the alarm threshold, determines the fire probability of the electrical appliance, generates a fire warning signal or a power-off signal or a power-off alarm signal, and sends the generated fire warning signal or power-off signal or power-off alarm signal to the processing module;

[0013] When the processing module receives a fire warning signal, it issues a fire warning to the user;

[0014] When the processing module receives a power-off signal, it controls the electrical equipment to be powered off and sends a power-off report to the user;

[0015] When the processing module receives the power-off alarm signal, it controls the electrical equipment to be powered off, and sends a fire alarm signal to the user that a fire has occurred in the electrical equipment or to the user.

[0016] Preferably, the real-time temperature data set expression is: {Wd1, Wd2, ..., Wdn}, the real-time humidity data set expression is: {Sd1, Sd2, ..., Sd n}, the real-time power data set expression is: {Gl1, Gl2, ..., Gl n}, the carbon monoxide real-time concentration data set expression is: {Nd1, Nd2, ..., Nd n}, and the data quantity, collection time interval and collection cycle in each data set are the same.

[0017] Preferably, the power mean The calculation expression is as follows:

[0018]

[0019] In the formula, Where i=1 means starting the calculation from the first data in the real-time power data set, and n means calculating to the nth data in the real-time power data set. The summed result is divided by the total number of data in the real-time power data set to obtain the power mean value.

[0020] The power fluctuation rate BD is calculated as follows:

[0021]

[0022] In the formula, Indicates the power average value calculated last time, Indicates the change in the average power of two consecutive times

[0023] Preferably, the numerical calculation expression of the real-time temperature QWd after cleaning is as follows:

[0024]

[0025] In the formula, Where i=1 means starting the calculation from the first data in the real-time temperature data set, and n means calculating to the nth data in the real-time temperature data set. It means that the summed result is divided by the total number of data in the real-time temperature data set to obtain the real-time temperature QWd value after cleaning.

[0026] Preferably, the calculation expression of the real-time humidity value QSd after cleaning is as follows:

[0027]

[0028] In the formula, Where i=1 means starting the calculation from the first data in the real-time humidity data set, and n means calculating to the nth data in the real-time humidity data set. It means that the summed result is divided by the total number of data in the real-time humidity data set to obtain the real-time humidity QSd value after cleaning.

[0029] Preferably, the calculation expression of the real-time concentration Qnd of carbon monoxide after cleaning is as follows:

[0030]

[0031] In the formula, Where i=1 means starting the calculation from the first data in the carbon monoxide real-time concentration data set, and n means calculating to the nth data in the carbon monoxide real-time concentration data set. It means that the summed result is divided by the total number of data in the carbon monoxide real-time concentration data set to obtain the real-time carbon monoxide concentration QNd after cleaning.

[0032] Preferably, the calculation expression of the electrical appliance fire probability index ZB is as follows:

[0033] ZB=β+β w *QWd+β s *QSd+β N QD

[0034] In the formula, β represents the intercept term, β w represents the temperature regression coefficient, β s represents the humidity regression coefficient, β N represents the regression coefficient of carbon monoxide concentration, β, β w , β s and β N These are the corresponding parameter values ​​obtained by the electrical appliance in the experimental scenario and calculated with the linear regression model set.

[0035] Preferably, the ignition probability G1 conversion formula is as follows:

[0036]

[0037] In the formula, It means mapping the linear combination result of the regression model to the range of [0, 1] to obtain a probability value, which is the fire probability Gl, and e represents the base of the natural logarithm.

[0038] Preferably, the alarm threshold value ranges from 0 to 1;

[0039] When 0<fire probability Gl≤0.1, it is judged as low fire risk and a fire warning signal is generated;

[0040] When 0.1<fire probability Gl≤0.5, it is judged as medium fire risk and a power-off signal is generated;

[0041] When 0.5<fire probability Gl, it is judged as high fire risk and a power-off alarm signal is generated.

[0042] Compared with the prior art, the present invention provides an intelligent explosion-proof electrical appliance monitoring and protection system, which has the following beneficial effects:

[0043] The present invention combines various factors of the actual use environment and judges whether there is an abnormality in the electrical appliance according to power fluctuations. When an abnormality occurs, the fire probability of the electrical appliance is judged in combination with the actual environmental factors, and the fire probability is calculated, and the fire probability is compared with the alarm threshold, so as to obtain different signals. The processing module performs corresponding operations according to the different signals and issues an early warning, so that an early warning or a power-off or power-off alarm can be issued in time to reduce safety hazards. At the same time, multiple data are integrated to avoid information islands, so as to effectively monitor the intelligent explosion-proof electrical appliances and issue corresponding early warning information according to the current state of the intelligent explosion-proof electrical appliances, thereby reducing safety risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION

[0045] 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.

[0046] In order to avoid the phenomenon of information islands, it is impossible to effectively monitor the intelligent explosion-proof electrical appliances and issue corresponding warning information according to the current status of the intelligent explosion-proof electrical appliances, which increases the safety risk. Therefore, an intelligent explosion-proof electrical appliance monitoring and protection system is proposed. Please refer to Figure 1 The system includes an electrical appliance data acquisition module, an electrical appliance data processing module, an electrical appliance data analysis module and a processing module.

[0047] The electrical appliance data acquisition module includes an electrical appliance temperature acquisition unit, an electrical appliance humidity acquisition unit, an electrical appliance power acquisition unit, and a gas concentration acquisition unit;

[0048] The electrical temperature acquisition unit is used to collect the real-time temperature data Wd of the electrical appliance during operation, the electrical humidity acquisition unit is used to collect the real-time humidity data Sd of the surrounding environment of the electrical appliance during operation, the electrical power acquisition unit is used to collect the real-time power data Gl of the electrical appliance during operation, and the gas concentration acquisition unit is used to collect the real-time carbon monoxide concentration data Nd of the surrounding environment of the electrical appliance during operation, wherein the corresponding data sets are as follows:

[0049] The real-time temperature data set expression is: {Wd1, Wd2, ..., Wd n}, the real-time humidity data set expression is: {Sd1, Sd2, ..., Sd n}, the real-time power data set expression is: {Gl1, Gl2, ..., Gl n}, the expression of the real-time concentration data set of carbon monoxide is: {Nd1, Nd2, ..., Nd n}, and the number of data in each data set is the same, the collection time interval is the same, and the collection cycle is the same. By setting the collection time interval and collection cycle of the collection unit to be the same, and the number of data in each data set to be the same, it is possible to avoid aligning multiple different data in chronological order, reduce the calculation steps, and improve the speed of system operation.

[0050] The electrical appliance data acquisition module forms corresponding real-time temperature data sets, real-time humidity data sets, real-time power data sets and real-time carbon monoxide concentration data sets with the collected data, and sends these data sets to the electrical appliance data processing module;

[0051] The electrical data processing module calculates the power mean value based on the real-time power data set The calculation expression is as follows:

[0052]

[0053] In the formula, Where i=1 means starting the calculation from the first data in the real-time power data set, and n means calculating to the nth data in the real-time power data set. The summed result is divided by the total number of data in the real-time power data set to obtain the power mean value.

[0054] When the power mean is calculated After that, the electrical data processing module calculates the average power of two adjacent Calculate the power fluctuation rate BD, and its calculation expression is as follows:

[0055]

[0056] In the formula, Indicates the power average value calculated last time, Indicates the change in the power mean between two consecutive times;

[0057] By calculating the change in the average power of the two times before and after, when the change is a negative value, it means that the power consumption of the appliance has decreased. At this time, it means that the working state of the appliance is in a relatively safe state. When the change is a positive value, it means that the power consumption of the appliance has increased. As the power consumption increases, the heat generated by the appliance will also increase, which will lead to some safety hazards.

[0058] The electrical appliance data processing module compares the calculated power fluctuation rate BD with the power fluctuation threshold BDyz. When the power fluctuation rate BD is greater than the power fluctuation threshold BDyz, the electrical appliance power is determined to be abnormal. At this time, it can be determined that the power of the electrical appliance has abnormal fluctuations or a continuous growth trend, so it can be indicated that the electrical appliance is abnormal. When the electrical appliance data processing module determines that the electrical appliance power is abnormal, the real-time temperature data set, real-time humidity data set and carbon monoxide real-time concentration data set collected at the same time of the real-time power data set are pre-processed. It should be noted that only when the electrical appliance power is determined to be abnormal will the remaining data be calculated, thereby reducing the computing burden of the electrical appliance data processing module when the electrical appliance is normal, thereby improving the computing speed of the electrical appliance data processing module. The pre-processed data are the real-time temperature QWd value after cleaning, the real-time humidity value QSd after cleaning and the real-time carbon monoxide concentration QNd value after cleaning, and the corresponding calculation expressions are as follows:

[0059] The numerical calculation expression of the real-time temperature QWd after cleaning is as follows:

[0060]

[0061] In the formula, Where i=1 means starting the calculation from the first data in the real-time temperature data set, and n means calculating to the nth data in the real-time temperature data set. The summed result is divided by the total number of data in the real-time temperature data set to obtain the real-time temperature QWd value after cleaning;

[0062] The calculation expression of the real-time humidity value QSd after cleaning is as follows:

[0063]

[0064] In the formula, Where i=1 means starting the calculation from the first data in the real-time humidity data set, and n means calculating to the nth data in the real-time humidity data set. The summed result is divided by the total number of data in the real-time humidity data set to obtain the real-time humidity QSd value after cleaning;

[0065] The calculation expression of the real-time concentration of carbon monoxide QNd after cleaning is as follows:

[0066]

[0067] In the formula, Where i=1 means starting the calculation from the first data in the carbon monoxide real-time concentration data set, and n means calculating to the nth data in the carbon monoxide real-time concentration data set. The summed result is divided by the total number of data in the carbon monoxide real-time concentration data set to obtain the cleaned carbon monoxide real-time concentration QNd;

[0068] By calculating the mean of data in multiple data sets, individual abnormal values ​​in the data set can be eliminated, so that the data is close to the actual corresponding parameter values ​​of the appliance during operation, which helps to improve the accuracy of subsequent calculation results;

[0069] After calculating the real-time temperature QWd value after cleaning, the real-time humidity value QSd after cleaning, and the real-time carbon monoxide concentration QNd value after cleaning, the electrical appliance data processing module calculates the electrical appliance fire probability index ZB based on these values. The calculation expression is as follows:

[0070] ZB=β+β w *QWd+β s *QSd+β N QD

[0071] In the formula, β represents the intercept term, β w represents the temperature regression coefficient, β s represents the humidity regression coefficient, β N represents the regression coefficient of carbon monoxide concentration, β, β w , β s and β N These are the corresponding parameter values ​​obtained by the electrical appliances in the experimental scenarios, and are calculated with the linear regression model set. The linear regression model is an existing mature mathematical model and will not be described in detail in this article. The data generated by the experiment are used to analyze the relationship between the temperature of the electrical appliance, the humidity of the environment, and the carbon monoxide concentration in the environment to calculate the comprehensive electrical appliance ignition index.

[0072] When the electrical appliance fire probability index ZB is calculated, the electrical appliance data processing module converts the calculated electrical appliance fire probability index ZB into the fire probability Gl. The conversion formula is as follows:

[0073]

[0074] In the formula, It means mapping the linear combination result of the regression model to the range of [0, 1] to obtain a probability value, which is the fire probability Gl, and e represents the base of the natural logarithm.

[0075] The electrical appliance data processing module sends the converted fire probability Gl to the electrical appliance data analysis module. The electrical appliance data analysis module is provided with an alarm threshold whose value range is 0 to 1. The electrical appliance data analysis module compares the fire probability Gl with the alarm threshold, and determines the fire probability of the electrical appliance, and generates a fire warning signal or a power-off signal or a power-off alarm signal. The specific comparison is as follows:

[0076] When 0<fire probability Gl≤0.1, it is judged as low fire risk and a fire warning signal is generated;

[0077] When 0.1<fire probability Gl≤0.5, it is judged as medium fire risk and a power-off signal is generated;

[0078] When 0.5<fire probability Gl, it is judged as high fire risk and a power-off alarm signal is generated;

[0079] The electrical appliance data analysis module sends the generated fire warning signal or power failure signal or power failure alarm signal to the processing module, and when the processing module receives the fire warning signal, it issues a fire warning to the user;

[0080] When the processing module receives a power-off signal, it controls the electrical equipment to be powered off and sends a power-off report to the user;

[0081] When the processing module receives the power-off alarm signal, it controls the electrical equipment to be powered off, and sends a fire alarm signal to the user that a fire has occurred in the electrical equipment or to the user.

[0082] Therefore, the system can combine various factors of the actual use environment and judge whether there is any abnormality in the electrical appliance based on power fluctuations. When an abnormality occurs, the fire probability of the electrical appliance is judged in combination with the actual environmental factors, and the fire probability is calculated and compared with the alarm threshold to obtain different signals. The processing module makes corresponding operations according to different signals and issues early warnings, so that early warnings or power-off or power-off alarms can be issued in time to reduce safety hazards. At the same time, multiple data are integrated to avoid information islands, so as to effectively monitor the intelligent explosion-proof electrical appliances and issue corresponding early warning information according to the current status of the intelligent explosion-proof electrical appliances, thereby reducing safety risks.

[0083] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent explosion-proof electrical appliance monitoring and protection system, characterized in that: It includes an electrical appliance data acquisition module, an electrical appliance data processing module, an electrical appliance data analysis module and a processing module; The electrical appliance data acquisition module includes an electrical appliance temperature acquisition unit, an electrical appliance humidity acquisition unit, an electrical appliance power acquisition unit, and a gas concentration acquisition unit; The electrical temperature acquisition unit is used to collect real-time temperature data Wd of the electrical appliance during operation, the electrical humidity acquisition unit is used to collect real-time humidity data Sd of the surrounding environment of the electrical appliance during operation, the electrical power acquisition unit is used to collect real-time power data Gl of the electrical appliance during operation, and the gas concentration acquisition unit is used to collect real-time carbon monoxide concentration data Nd of the surrounding environment of the electrical appliance during operation; The electrical appliance data acquisition module forms corresponding real-time temperature data sets, real-time humidity data sets, real-time power data sets and real-time carbon monoxide concentration data sets with the collected data, and sends these data sets to the electrical appliance data processing module; The electrical appliance data processing module calculates the power mean Gl according to the real-time power data set, and calculates the power fluctuation rate BD according to the two adjacent power mean values ​​Gl obtained by calculation, and compares it with the set power fluctuation threshold BDyz. When the power fluctuation rate BD is greater than the power fluctuation threshold BDyZ, the electrical appliance power is determined to be abnormal. When the electrical appliance data processing module determines that the electrical appliance power is abnormal, the real-time temperature data set, the real-time humidity data set and the real-time carbon monoxide concentration data set collected at the same time as the real-time power data set are pre-processed to obtain the real-time temperature QWd value after cleaning, the real-time humidity value QSd after cleaning and the real-time carbon monoxide concentration QNd value after cleaning, and calculate the electrical appliance fire probability index ZB according to these values. The electrical appliance processing module converts the calculated electrical appliance fire probability index ZB into the fire probability Gl, and sends it to the electrical appliance data analysis module; The electrical appliance data analysis module compares the fire probability G1 with the alarm threshold, determines the fire probability of the electrical appliance, generates a fire warning signal or a power-off signal or a power-off alarm signal, and sends the generated fire warning signal or power-off signal or power-off alarm signal to the processing module; When the processing module receives a fire warning signal, it issues a fire warning to the user; When the processing module receives a power-off signal, it controls the electrical equipment to be powered off and sends a power-off report to the user; When the processing module receives the power-off alarm signal, it controls the electrical equipment to be powered off, and sends a fire alarm signal to the user that a fire has occurred in the electrical equipment or to the user.

2. The intelligent explosion-proof electrical appliance monitoring and protection system according to claim 1 is characterized in that: The real-time temperature data set expression is: {Wd1, Wd2, ..., Wd n }, the real-time humidity data set expression is: {Sd1, Sd2, ..., Sd n }, the real-time power data set expression is: {Gl1, Gl2, ..., Gl n }, the carbon monoxide real-time concentration data set expression is: {Nd1, Nd2, ..., Nd n }, and the data quantity, collection time interval and collection cycle in each data set are the same.

3. The intelligent explosion-proof electrical appliance monitoring and protection system according to claim 2 is characterized in that: The power mean The calculation expression is as follows: In the formula, Where i=1 means starting the calculation from the first data in the real-time power data set, and n means calculating to the nth data in the real-time power data set. The summed result is divided by the total number of data in the real-time power data set to obtain the power mean value.

4. The intelligent explosion-proof electrical appliance monitoring and protection system according to claim 3 is characterized in that: The power fluctuation rate BD is calculated as follows: In the formula, Indicates the power average value calculated last time, Indicates the change in the power mean between two consecutive times.

5. The intelligent explosion-proof electrical appliance monitoring and protection system according to claim 4 is characterized in that: The numerical calculation expression of the real-time temperature QWd after cleaning is as follows: In the formula, Where i=1 means starting the calculation from the first data in the real-time temperature data set, and n means calculating to the nth data in the real-time temperature data set. It means that the summed result is divided by the total number of data in the real-time temperature data set to obtain the real-time temperature QWd value after cleaning.

6. The intelligent explosion-proof electrical appliance monitoring and protection system according to claim 1 is characterized in that: The calculation expression of the real-time humidity value QSd after cleaning is as follows: In the formula, Where i=1 means starting the calculation from the first data in the real-time humidity data set, and n means calculating to the nth data in the real-time humidity data set. It means that the summed result is divided by the total number of data in the real-time humidity data set to obtain the real-time humidity QSd value after cleaning.

7. The intelligent explosion-proof electrical appliance monitoring and protection system according to claim 1 is characterized in that: The calculation expression of the real-time concentration QNd of carbon monoxide after cleaning is as follows: In the formula, Where i=1 means starting the calculation from the first data in the carbon monoxide real-time concentration data set, and n means calculating to the nth data in the carbon monoxide real-time concentration data set. It means that the summed result is divided by the total number of data in the carbon monoxide real-time concentration data set to obtain the real-time carbon monoxide concentration QNd after cleaning.

8. The intelligent explosion-proof electrical appliance monitoring and protection system according to claim 7 is characterized in that: The calculation expression of the electrical appliance fire probability index ZB is as follows: ZB=β+β w *QWd+b s *QSd+β N *QNd In the formula, β represents the intercept term, β w represents the temperature regression coefficient, β s represents the humidity regression coefficient, β N represents the regression coefficient of carbon monoxide concentration, β, β w , β s and β N These are the corresponding parameter values ​​obtained by the electrical appliance in the experimental scenario and calculated with the linear regression model set.

9. The intelligent explosion-proof electrical appliance monitoring and protection system according to claim 8 is characterized in that: The ignition probability G1 conversion formula is as follows: In the formula, It means mapping the linear combination result of the regression model to the range of [0, 1] to obtain a probability value, which is the fire probability Gl, and e represents the base of the natural logarithm.

10. The intelligent explosion-proof electrical appliance monitoring and protection system according to claim 9 is characterized in that: The alarm threshold value ranges from 0 to 1; When 0<fire probability Gl≤0.1, it is judged as low fire risk and a fire warning signal is generated; When 0.1<fire probability Gl≤0.5, it is judged as medium fire risk and a power-off signal is generated; When 0.5<fire probability Gl, it is judged as a high fire risk and a power-off alarm signal is generated.

Images