Intelligent fire extinguishing control method suitable for building fire fighting

Abstract

The invention discloses an intelligent fire extinguishing control method suitable for building fire fighting, and relates to the technical field of fire fighting, and the method comprises the steps: monitoring five variables including temperature, smoke particle concentration, oxygen concentration, carbon monoxide concentration and wind speed through various detectors, comparing the data with a set threshold value, collecting the number of the variables which actually exceed the threshold value, and calculating the number of the variables which actually exceed the threshold value; the early warning time length and the frequency of the early warning device are determined according to the number, so that the problems of long-time early warning caused by false alarm and interference of over-high early warning frequency to people are avoided; besides, in the actual intelligent fire extinguishing stage, the fire type is judged according to the collected images, the stage where the fire is located is judged according to the actual temperature, different fire extinguishing agents are sprayed according to different stages, fire can be extinguished rapidly, and meanwhile the cost of the high fire extinguishing agents is saved.

Description

Technical Field

[0001] The present invention relates to the technical field of fire protection, and in particular to an intelligent fire extinguishing control method suitable for building fire protection. Background Art

[0002] In recent years, with the rapid development of technologies such as the Internet of Things, big data, and artificial intelligence, their applications in various industries have continued to expand, especially in the field of fire protection, where the application of intelligent technology has become an inevitable trend. The Internet of Things technology can realize the interconnection of various fire protection equipment and sensors in buildings, and collect a large amount of fire protection-related data in real time. Big data technology can store, manage, analyze and mine massive amounts of fire protection data, extract valuable information, establish a fire risk prediction model, and discover potential fire hazards in advance. Artificial intelligence technology has brought intelligent decision-making capabilities to building fire protection. It can quickly and accurately determine the type of fire, the trend of fire development, etc., and formulate the optimal fire extinguishing control strategy based on this.

[0003] The existing intelligent fire extinguishing control methods for building fire protection generally have the following two defects: (1) In the fire warning stage, when the values ​​of certain detectors exceed the standard and cause misjudgment, the warning device will continuously emit a high-frequency warning sound. This sound not only affects people's normal work and life, but also needs to be manually turned off; (2) In the fire extinguishing stage, after identifying the type of fire, a suitable fire extinguishing agent is selected and put into use directly until the fire is over. This method does not consider the stage of the fire and selects the fire extinguishing agent in a targeted manner. This method is very likely to cause a waste of fire extinguishing agent resources and poor fire extinguishing effect. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides an intelligent fire extinguishing control method suitable for building fire protection, which solves the problem of excessive sound frequency and manual shutdown when the alarm device misjudges the fire in the fire warning stage, and the problem of waste of resources caused by not considering the selection of suitable fire extinguishing agents for different stages of the fire in the fire extinguishing stage.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0006] An intelligent fire extinguishing control method suitable for building fire protection, characterized in that the method specifically comprises the following steps:

[0007] S1, collect temperature T, smoke particle concentration S, oxygen concentration O, carbon monoxide concentration C, wind speed W in real time, compare them with the preset thresholds η1, η2, η3, η4, η5, obtain the number of variables exceeding the threshold and record the variable names;

[0008] S2. Set the warning time and frequency of the warning device according to the number of variables;

[0009] S3, comparing the variable name with the recorded variable name to determine whether an early warning is issued;

[0010] S4. During the fire extinguishing stage, the fire type is determined through the images actually collected by the camera, the fire stage is judged based on the temperature, and the best fire extinguishing agent is selected for different stages.

[0011] As a further solution of the present invention, the method for setting the actual warning time according to the number of variables in S2 is:

[0012] If the number of variables greater than the threshold is y1, then the warning time is set = the time used to collect various variables + the time used to compare the variables with the threshold, where y1∈[1,2] and is an integer;

[0013] If the number of variables that are greater than the threshold is y2, then the warning time is set to = the time used to collect various variables + the time used to compare the variables with the threshold + the time used to collect the monitoring scene images + the time used to use the images to determine whether it is the initial stage of the fire, where y2∈[3,4] and is an integer;

[0014] If the number of variables greater than the threshold is 5, the warning time is set to long.

[0015] As a further solution of the present invention, the specific requirements for setting the frequency of the early warning device according to the number of variables in S2 are:

[0016] If the number of variables that are greater than the threshold is y1, the alarm frequency is set to low;

[0017] If the number of variables that are greater than the threshold is y2, the alarm frequency is set to medium;

[0018] If the number of variables greater than the threshold is 5, the alarm frequency is set to high.

[0019] As a further solution of the present invention, features related to flames and smoke in the image are extracted. If the brightness value of the flame area is less than a threshold value v, the average gray value of the smoke area is greater than a threshold value v1, and the saturation of the smoke in HSV is less than a threshold value v2, then it is determined that the fire is in the initial stage.

[0020] As a further solution of the present invention, after it is determined through images that the fire is in the initial stage, the warning time is adjusted to be long and the frequency of the alarm is set to be high.

[0021] As a further solution of the present invention, the variable name is compared with the record in S3. If the variable name this time corresponds to the variable name that has been warned in the record, the warning is stopped, otherwise, the warning continues.

[0022] As a further solution of the present invention, the method for determining the fire type through the image actually collected by the camera in S4 is:

[0023] Preprocess the captured images, including denoising, contrast enhancement, and color correction;

[0024] Use image processing algorithms to extract key features from images, including the color, shape, and area of ​​flames, and the color and density of smoke;

[0025] The collected detector data and image features are put into the trained machine learning model to determine the type of fire.

[0026] As a further solution of the present invention, the method for determining the stage of the fire according to the temperature in S4 is:

[0027] If it is a solid material fire, the temperature is between 200℃ and 500℃, which is the smoldering stage; between 500℃ and 1000℃, which is the growth stage; between 1000℃ and 1500℃, which is the full development stage; and starting from 1500℃ and decreasing, which is the decline stage;

[0028] In the case of liquid fire, the temperature is between 200℃ and 400℃, which is the smoldering stage; between 400℃ and 1000℃, which is the growth stage; between 1000℃ and 1300℃, which is the full development stage; and starting from 1300℃ and decreasing, which is the decline stage;

[0029] If it is a fire of fusible solid materials, the temperature is between 300℃ and 500℃, which is the smoldering stage; between 500℃ and 1100℃, which is the growth stage; between 1100℃ and 1400℃, which is the full development stage; and starting from 1400℃ and decreasing, which is the decay stage;

[0030] If it is a gas fire, the temperature is between 300℃ and 600℃, which is the smoldering stage; between 600℃ and 1200℃, which is the growth stage; between 1200℃ and 1500℃, which is the full development stage; and starting from 1500℃ and decreasing, which is the decline stage;

[0031] If it is a metal fire, the temperature is between 300℃ and 500℃, which is the smoldering stage; between 500℃ and 1300℃, which is the growth stage; between 1300℃ and 2000℃, which is the full development stage; and starting from 2000℃ and decreasing, which is the decline stage;

[0032] If it is an electrical fire, the temperature is between 300℃ and 600℃, which is the smoldering stage; between 600℃ and 1300℃, which is the growth stage; between 1300℃ and 1800℃, which is the full development stage; and starting from 1800℃ and decreasing, which is the decline stage;

[0033] If the fire is a cooking fire in a cooking appliance, if the temperature is between 200℃ and 400℃, it is in the smoldering stage; if it is between 400℃ and 800℃, it is in the growth stage; if it is between 800℃ and 1200℃, it is in the full development stage; and if it starts to decrease from 1200℃, it is in the recession stage.

[0034] As a further solution of the present invention, the method of selecting a suitable fire extinguishing agent according to the different stages of different types of fires is as follows:

[0035] If it is a solid material fire, choose dry powder fire extinguishing agent in the smoldering stage, choose carbon dioxide fire extinguishing agent in the growth stage, choose water-based fire extinguishing agent in the full development stage, and choose foam fire extinguishing agent in the decay stage;

[0036] If it is a fire of liquid or meltable solid material, choose dry powder fire extinguishing agent in the smoldering stage, choose foam fire extinguishing agent in the growth stage, choose water spray fire extinguishing agent in the full development stage, and choose foam fire extinguishing agent in the decay stage;

[0037] If it is a gas fire, choose dry powder fire extinguishing agent in the smoldering stage, choose carbon dioxide fire extinguishing agent in the growth stage, choose halogenated fire extinguishing agent in the full development stage, and choose dry powder or carbon dioxide fire extinguishing agent in the decay stage;

[0038] If it is a metal fire, choose 7150 fire extinguishing agent in the smoldering stage, choose 7150 fire extinguishing agent in the growth stage, choose graphite powder fire extinguishing agent in the full development stage, and choose dry sand or graphite powder fire extinguishing agent in the decay stage;

[0039] If it is an electrical fire, choose carbon dioxide fire extinguishing agent in the smoldering stage, choose dry powder fire extinguishing agent in the growth stage, choose halogenated hydrocarbon or fine water mist fire extinguishing agent in the full development stage, and choose carbon dioxide or dry powder fire extinguishing agent in the decay stage;

[0040] If it is a cooking fire in a cooking appliance, choose dry powder fire extinguisher in the smoldering stage, choose foam fire extinguisher in the growth stage, choose water-based fire extinguisher in the full development stage, and choose dry powder fire extinguisher in the decay stage.

[0041] The present invention provides an intelligent fire extinguishing control method suitable for building fire protection, which has the following beneficial effects compared with the prior art:

[0042] 1. The present invention collects the relationship between the actual detector value and the set threshold value to obtain the number of values ​​exceeding the threshold value, and records the variable name detected by the detector. The warning time and the frequency of the alarm are set according to the number, and the variable name exceeding the threshold value each time is compared with the recorded one. If the two correspond one to one, the warning is stopped this time. This method effectively solves the sound interference caused by the false alarm of the alarm and the problem of manually turning off the alarm.

[0043] 2. After determining the fire type, the present invention judges the stage of the fire by temperature and uses different types of fire extinguishing agents for different stages, thereby achieving the best fire extinguishing effect while saving the cost of the fire extinguishing agent to the greatest extent. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0045] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. 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] like Figure 1 , an intelligent fire extinguishing control method suitable for building fire protection, comprising:

[0047] S1, collect temperature T, smoke particle concentration S, oxygen concentration O, carbon monoxide concentration C, wind speed W in real time, compare them with the preset thresholds η1, η2, η3, η4, η5, obtain the number of variables exceeding the threshold and record the variable names;

[0048] If T>η1 is found for the first time, the variable name recorded is {temperature}. If S>η2, O>η3 is found for the second time, the variable name recorded is {smoke particle concentration, oxygen concentration}. In short, the variable names that exceed the threshold value this time are put together to record some abnormal quantities this time.

[0049] S2. Set the warning time and frequency of the warning device according to the number of variables;

[0050] The method to set the actual warning time according to the number of variables is:

[0051] If the number of variables that are greater than the threshold is y1, then the warning time is set = the time used to collect various variables + the time used to compare the variables with the threshold, where y1∈[1,2] and is an integer;

[0052] If one or two variables are greater than the threshold, it can be judged that some changes in the surrounding environment have caused the detector value to become higher, which is very likely to cause misjudgment. Therefore, the warning time is set to the time of collecting various variables next time plus the time used for comparison with the threshold. This time is very short and can timely turn off the sound caused by the misjudgment of the alarm;

[0053] If the number of variables that are greater than the threshold is y2, then the warning time is set to = the time used to collect various variables + the time used to compare the variables with the threshold + the time used to collect the monitoring scene images + the time used to use the images to determine whether it is the initial stage of the fire, where y2∈[3,4] and is an integer;

[0054] In the initial stage of a fire, it is not necessary for all variables to exceed the threshold. For example, in the initial stage, O>η3, C>η4, W>η5 are satisfied, but due to the good permeability of the room and the wind at the time, T<η1, S<η2. In this case, it is necessary to collect images of the scene through surveillance cameras for judgment;

[0055] If the number of variables greater than the threshold is 5, the warning time is set to long;

[0056] The long time mentioned here specifically refers to the time from the start of the warning to the complete extinguishing of the fire;

[0057] The specific requirements for setting the frequency of the early warning device according to the number of variables are:

[0058] If the number of variables that are greater than the threshold is y1, the alarm frequency is set to low;

[0059] There are many factors that lead to misjudgment of the alarm in real life. For example, if someone is smoking next to the detector, it is very likely to cause misjudgment. Therefore, in this case, the alarm frequency should be set lower to avoid interfering with people's work and life due to misjudgment.

[0060] If the number of variables that are greater than the threshold is y2, the alarm frequency is set to medium;

[0061] Extract the features of flame and smoke in the image. If the brightness value of the flame area is less than the threshold v, the average gray value of the smoke area is greater than the threshold v1, and the saturation of the smoke in HSV is less than the threshold v2, then the fire is judged to be in the initial stage.

[0062] To convert the image from RGB color to HSV color space, for the flame area, in HSV, the flame hue range is between 0-60 and 300-360, and its brightness value will change with the change of the surrounding flame intensity. Through a large amount of actual sample data and tests, a threshold is obtained, and the flame below the threshold is judged as dim in color;

[0063] The grayscale information of the image is used to estimate the smoke density. The commonly used grayscale formula is Gray = 0.299*R + 0.587*G + 0.114*B. The average grayscale value is counted and a grayscale threshold corresponding to thin smoke is set. This threshold should be adjusted according to the actual sample. If the average grayscale value of the smoke area is greater than the threshold, it can be judged that the smoke density is low, that is, relatively thin;

[0064] Smoke usually appears in lighter colors such as grayish white in images. In HSV, its hue is close to neutral and its saturation is low. Through multiple experiments, a suitable saturation threshold is set. If the actual calculated saturation is less than the threshold, it can be judged that the smoke color is lighter.

[0065] After the fire is determined to be in the initial stage through the image, the warning time is adjusted to be long and the frequency of the alarm is set to be high;

[0066] If the number of variables that are greater than the threshold is 5, the alarm frequency is set to high;

[0067] At this stage, it has been confirmed that a fire has occurred, so the alarm should emit a high-frequency sound to remind people to take emergency shelter;

[0068] S3, comparing the variable name with the recorded variable name to determine whether an early warning is issued;

[0069] If the variable name this time corresponds to the variable name that has been warned in the record, the warning will be stopped, otherwise, the warning will continue;

[0070] For example, if there are {temperature}, {temperature, smoke particle concentration}, {temperature, oxygen concentration, carbon monoxide concentration} in the record, if the variables exceeding the threshold value this time are one-to-one corresponding to the above, such as {temperature}, {temperature, smoke particle concentration}, {temperature, oxygen concentration, carbon monoxide concentration}, no warning will be issued this time. If they are not corresponding, such as {wind speed}, {temperature, wind speed}, {temperature, oxygen concentration, wind speed}, then a warning will be issued.

[0071] S4. In the fire extinguishing stage, the fire type is determined through the images actually collected by the camera, the fire stage is judged according to the temperature, and the best fire extinguishing agent is selected for different stages;

[0072] Collect data from multiple actual fire scenes or simulated fire laboratory scenes. These data sources should cover as many different fire types as possible. Perform operations such as denoising, contrast enhancement, and color correction on the image data obtained through the imaging device.

[0073] For each set of collected data, the image processing algorithm is used to extract the key features of the image, including the color, shape, area of ​​the flame, and the color, density and other characteristic values ​​of the smoke, and the fire type corresponding to each set of data is accurately labeled, such as "Class A fire (solid fire)", "Class B fire (liquid fire)", etc.

[0074] The training set is divided into 70%-80% and the test set is divided into 20%-30%. The division is performed by random sampling to ensure that the distribution of different fire types in each data subset is as uniform as possible to avoid the problem of too large a difference in the distribution of fire types in the training set and the test set.

[0075] Since these data have complex nonlinear relationships and are classification problems, models such as support vector machines, decision trees, random forests, and Adaboost can be selected;

[0076] For the selected model, set some key training parameters. For example, if you choose a random forest model, you need to set the number of trees, the maximum depth of each tree, etc. If it is a neural network model, you need to set the number of hidden layers, the number of neurons, the learning rate, the number of iterations, etc.

[0077] Input the training data (i.e., image features) into the model to start training. The model will automatically adjust its internal parameters based on the input features and annotation information to fit the data as much as possible so that the model can better identify the characteristic patterns of different fire types.

[0078] After a certain number of training iterations, the test set is input into the trained model and the results corresponding to the fire type are output. The difference between the model prediction combination and the true indicator is measured through indicators such as accuracy, recall, and F1 to evaluate the model performance;

[0079] When the model training accuracy reaches above 90%, or the maximum number of iterations reaches 500, the model will stop training;

[0080] The method of judging the stage of fire based on temperature is:

[0081] If it is a solid material fire, the temperature is between 200℃ and 500℃, which is the smoldering stage; between 500℃ and 1000℃, which is the growth stage; between 1000℃ and 1500℃, which is the full development stage; and starting from 1500℃ and decreasing, which is the decline stage;

[0082] In the case of liquid fire, the temperature is between 200℃ and 400℃, which is the smoldering stage; between 400℃ and 1000℃, which is the growth stage; between 1000℃ and 1300℃, which is the full development stage; and starting from 1300℃ and decreasing, which is the decline stage;

[0083] If it is a fire of fusible solid materials, the temperature is between 300℃ and 500℃, which is the smoldering stage; between 500℃ and 1100℃, which is the growth stage; between 1100℃ and 1400℃, which is the full development stage; and starting from 1400℃ and decreasing, which is the decay stage;

[0084] If it is a gas fire, the temperature is between 300℃ and 600℃, which is the smoldering stage; between 600℃ and 1200℃, which is the growth stage; between 1200℃ and 1500℃, which is the full development stage; and starting from 1500℃ and decreasing, which is the decline stage;

[0085] If it is a metal fire, the temperature is between 300℃ and 500℃, which is the smoldering stage; between 500℃ and 1300℃, which is the growth stage; between 1300℃ and 2000℃, which is the full development stage; and starting from 2000℃ and decreasing, which is the decline stage;

[0086] If it is an electrical fire, the temperature is between 300℃ and 600℃, which is the smoldering stage; between 600℃ and 1300℃, which is the growth stage; between 1300℃ and 1800℃, which is the full development stage; and starting from 1800℃ and decreasing, which is the decline stage;

[0087] If the fire is caused by food in a cooking appliance, the temperature is between 200℃ and 400℃, which is the smoldering stage; between 400℃ and 800℃, which is the growth stage; between 800℃ and 1200℃, which is the full development stage; and starting from 1200℃ and decreasing, which is the decay stage;

[0088] The method of selecting the appropriate fire extinguishing agent according to the different stages of different types of fire is:

[0089] If it is a solid material fire, choose dry powder fire extinguishing agent in the smoldering stage, choose carbon dioxide fire extinguishing agent in the growth stage, choose water-based fire extinguishing agent in the full development stage, and choose foam fire extinguishing agent in the decay stage;

[0090] If it is a fire of liquid or meltable solid material, choose dry powder fire extinguishing agent in the smoldering stage, choose foam fire extinguishing agent in the growth stage, choose water spray fire extinguishing agent in the full development stage, and choose foam fire extinguishing agent in the decay stage;

[0091] If it is a gas fire, choose dry powder fire extinguishing agent in the smoldering stage, choose carbon dioxide fire extinguishing agent in the growth stage, choose halogenated fire extinguishing agent in the full development stage, and choose dry powder or carbon dioxide fire extinguishing agent in the decay stage;

[0092] If it is a metal fire, choose 7150 fire extinguishing agent in the smoldering stage, choose 7150 fire extinguishing agent in the growth stage, choose graphite powder fire extinguishing agent in the full development stage, and choose dry sand or graphite powder fire extinguishing agent in the decay stage;

[0093] If it is an electrical fire, choose carbon dioxide fire extinguishing agent in the smoldering stage, choose dry powder fire extinguishing agent in the growth stage, choose halogenated hydrocarbon or fine water mist fire extinguishing agent in the full development stage, and choose carbon dioxide or dry powder fire extinguishing agent in the decay stage;

[0094] If it is a cooking fire in a cooking appliance, choose dry powder fire extinguisher in the smoldering stage, choose foam fire extinguisher in the growth stage, choose water-based fire extinguisher in the full development stage, and choose dry powder fire extinguisher in the decay stage;

[0095] In the description of the specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0096] The above contents are merely examples and explanations of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the invention or exceed the scope defined by the claims, they shall all fall within the protection scope of the present invention.

Claims

1. An intelligent fire extinguishing control method suitable for building fire protection, characterized in that: The following steps are involved: S1, collect temperature T, smoke particle concentration S, oxygen concentration O, carbon monoxide concentration C, wind speed W in real time, compare them with the preset thresholds η1, η2, η3, η4, η5, obtain the number of variables exceeding the threshold and record the variable names; S2. Set the warning time and frequency of the warning device according to the number of variables; S3, comparing the variable name with the recorded variable name to determine whether an early warning is issued; S4. During the fire extinguishing stage, the fire type is determined through the images actually collected by the camera, the fire stage is judged based on the temperature, and the best fire extinguishing agent is selected for different stages.

2. The intelligent fire extinguishing control method for building fire protection according to claim 1, characterized in that: The method for setting the actual warning time according to the number of variables in S2 is: If the number of variables greater than the threshold is y1, then the warning time is set = the time used to collect various variables + the time used to compare the variables with the threshold, where y1∈[1,2] and is an integer; If the number of variables that are greater than the threshold is y2, then the warning time is set to = the time used to collect various variables + the time used to compare the variables with the threshold + the time used to collect the monitoring scene images + the time used to use the images to determine whether it is the initial stage of the fire, where y2∈[3,4] and is an integer; If the number of variables greater than the threshold is 5, the warning time is set to long.

3. The intelligent fire extinguishing control method for building fire protection according to claim 1, characterized in that: The specific requirements for setting the frequency of the early warning device according to the number of variables in S2 are: If the number of variables that are greater than the threshold is y1, the alarm frequency is set to low; If the number of variables that are greater than the threshold is y2, the alarm frequency is set to medium; If the number of variables greater than the threshold is 5, the alarm frequency is set to high.

4. The intelligent fire extinguishing control method for building fire protection according to claim 2, characterized in that: Extract the features of flame and smoke in the image. If the brightness value of the flame area is less than the threshold v, the average gray value of the smoke area is greater than the threshold v1, and the saturation of the smoke in HSV is less than the threshold v2, then the fire is judged to be in the initial stage.

5. The intelligent fire extinguishing control method for building fire protection according to claim 4, characterized in that: After it is determined through the image that the fire is in the initial stage, the warning time is adjusted to a long time and the alarm frequency is set to a high time.

6. The intelligent fire extinguishing control method for building fire protection according to claim 1, characterized in that: In S3, the variable name is compared with the record. If the variable name this time corresponds to the variable name that has been warned in the record, the warning is stopped; otherwise, the warning continues.

7. The intelligent fire extinguishing control method for building fire protection according to claim 1, characterized in that: The method for determining the fire type through the images actually collected by the camera in S4 is: Preprocess the captured images, including denoising, contrast enhancement, and color correction; Use image processing algorithms to extract key features from images, including the color, shape, and area of ​​flames, and the color and density of smoke; The collected detector data and image features are put into the trained machine learning model to determine the type of fire.

8. The intelligent fire extinguishing control method for building fire protection according to claim 1, characterized in that: The method for determining the stage of a fire based on temperature in S4 is: If it is a solid material fire, the temperature is between 200℃ and 500℃, which is the smoldering stage; between 500℃ and 1000℃, which is the growth stage; between 1000℃ and 1500℃, which is the full development stage; and starting from 1500℃ and decreasing, which is the decline stage; In the case of liquid fire, the temperature is between 200℃ and 400℃, which is the smoldering stage; between 400℃ and 1000℃, which is the growth stage; between 1000℃ and 1300℃, which is the full development stage; and starting from 1300℃ and decreasing, which is the decline stage; If it is a fire of fusible solid materials, the temperature is between 300℃ and 500℃, which is the smoldering stage; between 500℃ and 1100℃, which is the growth stage; between 1100℃ and 1400℃, which is the full development stage; and starting from 1400℃ and decreasing, which is the decay stage; If it is a gas fire, the temperature is between 300℃ and 600℃, which is the smoldering stage; between 600℃ and 1200℃, which is the growth stage; between 1200℃ and 1500℃, which is the full development stage; and starting from 1500℃ and decreasing, which is the decline stage; If it is a metal fire, the temperature is between 300℃ and 500℃, which is the smoldering stage; between 500℃ and 1300℃, which is the growth stage; between 1300℃ and 2000℃, which is the full development stage; and starting from 2000℃ and decreasing, which is the decline stage; If it is an electrical fire, the temperature is between 300℃ and 600℃, which is the smoldering stage; between 600℃ and 1300℃, which is the growth stage; between 1300℃ and 1800℃, which is the full development stage; and starting from 1800℃ and decreasing, which is the decline stage; If the fire is a cooking fire in a cooking appliance, if the temperature is between 200℃ and 400℃, it is in the smoldering stage; if it is between 400℃ and 800℃, it is in the growth stage; if it is between 800℃ and 1200℃, it is in the full development stage; and if it starts to decrease from 1200℃, it is in the recession stage.

9. The intelligent fire extinguishing control method applicable to building fire protection according to claim 1, characterized in that: The method of selecting the appropriate fire extinguishing agent according to the different stages of different types of fire is: If it is a solid material fire, choose dry powder fire extinguishing agent in the smoldering stage, choose carbon dioxide fire extinguishing agent in the growth stage, choose water-based fire extinguishing agent in the full development stage, and choose foam fire extinguishing agent in the decay stage; If it is a fire of liquid or meltable solid material, choose dry powder fire extinguishing agent in the smoldering stage, choose foam fire extinguishing agent in the growth stage, choose water spray fire extinguishing agent in the full development stage, and choose foam fire extinguishing agent in the decay stage; If it is a gas fire, choose dry powder fire extinguishing agent in the smoldering stage, choose carbon dioxide fire extinguishing agent in the growth stage, choose halogenated fire extinguishing agent in the full development stage, and choose dry powder or carbon dioxide fire extinguishing agent in the decay stage; If it is a metal fire, choose 7150 fire extinguishing agent in the smoldering stage, choose 7150 fire extinguishing agent in the growth stage, choose graphite powder fire extinguishing agent in the full development stage, and choose dry sand or graphite powder fire extinguishing agent in the decay stage; If it is an electrical fire, choose carbon dioxide fire extinguishing agent in the smoldering stage, choose dry powder fire extinguishing agent in the growth stage, choose halogenated hydrocarbon or fine water mist fire extinguishing agent in the full development stage, and choose carbon dioxide or dry powder fire extinguishing agent in the decay stage; If it is a cooking fire in a cooking appliance, choose dry powder fire extinguisher in the smoldering stage, choose foam fire extinguisher in the growth stage, choose water-based fire extinguisher in the full development stage, and choose dry powder fire extinguisher in the decay stage.

Images