Intelligent fire fighting system based on Internet of Things

Abstract

The invention discloses an intelligent fire-fighting system based on the Internet of Things, relates to the technical field of fire-fighting safety, and solves the technical problems that monitoring parameters of a fire-fighting monitoring system at the present stage are relatively single, and different fire-fighting rescue strategies cannot be executed according to fire threat levels at fire points. The fire analysis module is used for carrying out comprehensive analysis according to fire feature information and video information groups in a fire-fighting area, and judging whether a fire occurs and the position of a fire point when the fire occurs; through simultaneous analysis of various data, conditions of wrong sending and missed sending of alarms are reduced, and the early warning effect is improved. The fire-fighting decision-making module is used for collecting fire behavior data at the position of a fire point and the distribution condition of surrounding flammable and combustible objects for analysis, and automatically outputting a fire threat level in combination with the fire level identification module; and then based on the fire threat level, a corresponding fire rescue strategy is executed, adverse effects on production and life of a user are reduced to the maximum extent, and fire safety is improved.

Description

Technical Field

[0001] The present invention relates to the field of fire safety technology, and in particular to a smart fire fighting system based on the Internet of Things. Background Art

[0002] Urban fire protection systems are receiving more and more attention from people. At present, people's firefighting concept has changed from passive firefighting after the fire occurs to active detection and prevention using various detectors, striving to achieve early detection, early prevention and early fire extinguishing, which is also in line with the firefighting concept of prevention first.

[0003] At present, the fire monitoring system mainly monitors regional videos and fire parameters. It does not include various risk factors in the monitoring area into the monitoring range, and the monitoring parameters are relatively single. When a fire accident occurs, it is impossible to implement different fire rescue strategies according to the fire threat level at the fire point, thereby effectively improving the fire extinguishing efficiency and eliminating safety hazards. Based on the above shortcomings, the present invention proposes a smart fire protection system based on the Internet of Things. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a smart fire fighting system based on the Internet of Things.

[0005] To achieve the above-mentioned object, the first aspect of the present invention provides a smart fire protection system based on the Internet of Things, including a fire feature perception module, a video monitoring module, a server, a database, a fire analysis module, an alarm module and a fire protection decision module;

[0006] The fire characteristic sensing module is used to sense the fire characteristic information in the fire protection area and upload the fire characteristic information to the fire analysis module; the fire characteristic information includes smoke concentration information, carbon monoxide concentration information, carbon dioxide concentration information, temperature information and infrared intensity information;

[0007] The fire analysis module is used to perform a comprehensive analysis based on the fire characteristic information and the video information group in the fire area to determine whether a fire has occurred and the location of the fire point when the fire occurs; specifically, it includes:

[0008] The perceived smoke concentration information, carbon monoxide concentration information, carbon dioxide concentration information, temperature information and infrared intensity information are marked as Yi, Ni, Ei, Wi and Hi respectively;

[0009] Compare each feature information with the corresponding preset safety threshold to obtain the smoke over-alarm value Yt, carbon monoxide over-alarm value Nt, carbon dioxide over-alarm value Et, temperature over-alarm value Wt and infrared intensity over-alarm value Ht;

[0010] Using the formula The fire warning coefficient HZi is calculated, where g1, g2, and g3 are all preset coefficient factors; μ is the preset compensation coefficient;

[0011] Compare the fire warning coefficient HZi with the preset warning threshold; if the fire warning coefficient HZi is greater than the preset warning threshold, obtain the video information at the position corresponding to HZi, intercept the image at the corresponding position in the video information and compare it with the flame image group stored in the database;

[0012] If the comparison is consistent, it is determined that a fire has occurred, a fire signal is generated, and the location information of the fire point is recorded; the fire analysis module is used to send the fire signal and the corresponding location information of the fire point to the server; the server is used to drive the alarm module to sound an alarm after receiving the fire signal;

[0013] The fire fighting decision module is used to collect fire data at the fire point and the distribution of flammable and explosive materials in the surrounding area for analysis, and automatically output the fire threat level in combination with the fire level recognition module;

[0014] Then, based on the fire threat level, a corresponding fire rescue strategy is executed; the fire threat level includes level one, level two, and level three, and level one < level two < level three.

[0015] Furthermore, each feature information is compared with the corresponding preset safety threshold, specifically including:

[0016] Compare the smoke density information Yi with the preset smoke density threshold to obtain the smoke over-alarm value Yt; if the smoke over-alarm value Yt is less than 0, set the smoke over-alarm value Yt=0;

[0017] Compare the carbon monoxide concentration information Ni with the preset carbon monoxide concentration threshold to obtain the carbon monoxide exceeding warning value Nt; if the carbon monoxide exceeding warning value Nt is less than 0, then set the carbon monoxide exceeding warning value Nt=0;

[0018] Compare the carbon dioxide concentration information Ei with the preset carbon dioxide concentration threshold to obtain the carbon dioxide excess warning value Et; if the carbon dioxide excess warning value Et is less than 0, set the carbon dioxide excess warning value Et=0;

[0019] Compare the temperature information Wi with the preset temperature threshold to obtain the temperature over-alarm value Wt; if the temperature over-alarm value Wt is less than 0, set the temperature over-alarm value Wt=0;

[0020] The infrared intensity information Hi is compared with a preset infrared intensity threshold to obtain an infrared intensity exceeding warning value Ht; if the infrared intensity exceeding warning value Ht is less than 0, the infrared intensity exceeding warning value Ht=0.

[0021] Furthermore, according to the smart fire protection system based on the Internet of Things according to claim 1, the specific analysis steps of the fire protection decision module are as follows:

[0022] Collecting fire data at the fire point, the fire data including flame level and fire warning coefficient; wherein each flame image is manually annotated with the flame level;

[0023] Collect the real-time scene around the fire point, and identify it through the built-in flammable and explosive distribution recognition algorithm to obtain the spatial distribution information of flammable and explosive materials;

[0024] The fire intensity data and the spatial distribution information of flammable and explosive materials are substituted into a fire level identification module to automatically output the fire threat level; the fire level identification module is obtained by training an LSTM neural network model with historical values ​​of the fire intensity data, the spatial distribution information of flammable and explosive materials and the fire threat level.

[0025] Furthermore, based on the fire threat level, corresponding fire rescue strategies are implemented, including:

[0026] When the fire threat level is level one, the sound and light alarm will send out a warning message to inform the user that there is a fire hazard. The sprinkler and broadcasting devices will be in silent state. The nearest staff will be arranged to go to the fire point to use the fire hydrant to extinguish the fire and wait for further confirmation of the fire situation.

[0027] When the fire threat level is level 2, the sound and light alarm will send out warning information, the broadcasting device will broadcast an alarm to remind residents to evacuate urgently, and the sprinkler device will automatically aim at the fire source to automatically spray water to extinguish the fire. At the same time, staff will be arranged to go to the fire point to use the fire hydrant to extinguish the fire.

[0028] When the fire threat level is level three, the sound and light alarm will send out a warning message, the broadcasting device will broadcast an alarm to remind residents to evacuate urgently, the sprinkler device will automatically aim at the fire source to implement automatic water spraying fire extinguishing operations, and at the same time, a fire-fighting robot will be dispatched to the fire point to spray dust to extinguish the fire.

[0029] Furthermore, the fire characteristic sensing module includes a plurality of smoke sensors, a plurality of carbon monoxide sensors, a plurality of carbon dioxide sensors, a plurality of temperature sensors and a plurality of infrared sensors; wherein the smoke sensors, carbon monoxide sensors, carbon dioxide sensors, temperature sensors and infrared sensors are all provided with position marks and correspond one to one.

[0030] Furthermore, the video monitoring module is a plurality of monitoring cameras distributed in the fire protection area, which is used to obtain the video information group in the fire protection area in real time and transmit the video information group to the fire analysis module.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] 1. The fire analysis module in the present invention is used to perform a comprehensive analysis based on the fire feature information and the video information group in the fire area, and calculate the fire warning coefficient HZi; if the fire warning coefficient HZi is greater than the preset feature threshold, the video information at the corresponding position of HZi is obtained; the image at the corresponding position in the video information is intercepted and compared with the flame image group stored in the database; if the comparison is consistent, it is judged that a fire has occurred, a fire signal is generated, and the location information of the ignition point is recorded. By analyzing multiple data simultaneously, the occurrence of wrong or missed alarms is reduced, and the warning effect is improved;

[0033] 2. The fire decision module in the present invention is used to collect fire data at the fire point and the distribution of flammable and explosive materials in the surrounding area for analysis, and automatically output the fire threat level in combination with the fire level identification module; then based on the fire threat level, the corresponding fire rescue strategy is executed; it can respond to fires intelligently, minimize the adverse effects of fire rescue strategies on users' production and life, and improve fire safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 This is a system block diagram of a smart fire protection system based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0036] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0037] See also Figure 1 , the first aspect of the present invention provides an intelligent fire protection system based on the Internet of Things, including a fire feature perception module, a video monitoring module, a server, a database, a fire analysis module, an alarm module and a fire protection decision module;

[0038] The fire characteristic sensing module includes a plurality of smoke sensors, a plurality of carbon monoxide sensors, a plurality of carbon dioxide sensors, a plurality of temperature sensors and a plurality of infrared sensors, which are used to sense the fire characteristic information in the fire protection area; the fire characteristic information includes smoke concentration information, carbon monoxide concentration information, carbon dioxide concentration information, temperature information and infrared intensity information;

[0039] Several smoke sensors, several carbon monoxide sensors, several carbon dioxide sensors, several temperature sensors and several infrared sensors are distributed in the fire protection area;

[0040] Among them, the smoke sensor, carbon monoxide sensor, carbon dioxide sensor, temperature sensor and infrared sensor are all marked with positions and correspond one to one;

[0041] The video monitoring module is a number of monitoring cameras distributed in the fire protection area, which is used to obtain the video information group in the fire protection area in real time and transmit the video information group to the fire analysis module;

[0042] The fire analysis module is used to conduct a comprehensive analysis based on the fire characteristic information and the video information group in the fire area to determine whether a fire has occurred and the location of the fire point when the fire occurs; specifically, it includes:

[0043] The perceived smoke concentration information, carbon monoxide concentration information, carbon dioxide concentration information, temperature information and infrared intensity information are marked as Yi, Ni, Ei, Wi and Hi respectively; wherein i represents the i-th position identifier;

[0044] Compare each characteristic information with the corresponding preset safety threshold to obtain the over-alarm value of the corresponding characteristic information; the preset safety threshold includes a preset smoke concentration threshold, a preset carbon monoxide concentration threshold, a preset carbon dioxide concentration threshold, a preset temperature threshold and a preset infrared intensity threshold;

[0045] In this embodiment, each feature information is compared with the corresponding preset safety threshold to obtain the over-alarm value of the corresponding feature information; specifically including:

[0046] Compare the smoke density information Yi with the preset smoke density threshold to obtain the smoke over-alarm value Yt; if the smoke over-alarm value Yt is less than 0, set the smoke over-alarm value Yt=0;

[0047] Compare the carbon monoxide concentration information Ni with the preset carbon monoxide concentration threshold to obtain the carbon monoxide exceeding warning value Nt; if the carbon monoxide exceeding warning value Nt is less than 0, then set the carbon monoxide exceeding warning value Nt=0;

[0048] Compare the carbon dioxide concentration information Ei with the preset carbon dioxide concentration threshold to obtain the carbon dioxide excess warning value Et; if the carbon dioxide excess warning value Et is less than 0, set the carbon dioxide excess warning value Et=0;

[0049] Compare the temperature information Wi with the preset temperature threshold to obtain the temperature over-alarm value Wt; if the temperature over-alarm value Wt is less than 0, set the temperature over-alarm value Wt=0;

[0050] Compare the infrared intensity information Hi with the preset infrared intensity threshold to obtain the infrared intensity over-alarm value Ht; if the infrared intensity over-alarm value Ht is less than 0, set the infrared intensity over-alarm value Ht=0;

[0051] Using the formula The fire warning coefficient HZi is calculated, where g1, g2, and g3 are all preset coefficient factors; g1 takes the value of (0, 0.1], g2 takes the value of (0, 0.2], and g3 takes the value of (0.3, 0.5]; μ is the preset compensation coefficient, which takes the value of 0.005689;

[0052] Compare the fire warning coefficient HZi with the preset warning threshold; if the fire warning coefficient HZi is greater than the preset warning threshold, obtain the video information at the position corresponding to HZi, intercept the image at the corresponding position in the video information and compare it with the flame image group stored in the database;

[0053] If the comparison is consistent, it is judged that a fire has occurred, a fire signal is generated, and the location information of the fire point is recorded; each flame image is manually annotated with the flame level, and the larger the level, the larger the fire;

[0054] The fire analysis module is used to send the fire signal and the corresponding fire point location information to the server; the server is used to drive the alarm module to sound an alarm after receiving the fire signal, prompting the administrator to carry out fire rescue and personnel evacuation;

[0055] In this embodiment, in order to intelligently respond to fires and minimize the adverse effects of fire rescue strategies on user production and life, the fire decision module is used to collect fire data at the fire point and the distribution of flammable and explosive materials in the surrounding area for analysis, automatically output the fire threat level, and then execute the corresponding fire rescue strategy based on the fire threat level; the specific analysis process is as follows:

[0056] Collect fire data at the fire point, including flame level and fire warning coefficient;

[0057] Collect the real-time scene around the fire point, and identify it through the built-in flammable and explosive distribution recognition algorithm to obtain the spatial distribution information of flammable and explosive materials;

[0058] Substitute the fire data and the spatial distribution information of flammable and explosive materials into the fire level recognition module to automatically output the fire threat level; the fire level recognition module is obtained by training the LSTM neural network model with the fire data, the spatial distribution information of flammable and explosive materials and the historical values ​​of the fire threat level;

[0059] Then, based on the fire threat level, the corresponding fire rescue strategy is implemented; the fire threat levels include level 1, level 2, and level 3, and level 1 < level 2 < level 3; specifically, they include:

[0060] When the fire threat level is level one, the sound and light alarm will send out a warning message to inform the user that there is a fire hazard. The sprinkler and broadcasting devices will be in silent state. The nearest staff will be arranged to go to the fire point to use the fire hydrant to extinguish the fire and wait for further confirmation of the fire situation.

[0061] When the fire threat level is level 2, the sound and light alarm will send out warning information, the broadcasting device will broadcast an alarm to remind residents to evacuate urgently, and the sprinkler device will automatically aim at the fire source to automatically spray water to extinguish the fire. At the same time, staff will be arranged to go to the fire point to use the fire hydrant to extinguish the fire.

[0062] When the fire threat level is level three, the sound and light alarm will send out a warning message, the broadcasting device will broadcast an alarm to remind residents to evacuate urgently, the sprinkler device will automatically aim at the fire source to implement automatic water spraying fire extinguishing operations, and at the same time, a fire-fighting robot will be dispatched to the fire point to spray dust for fire extinguishing; the fire-fighting robot prevents the staff from getting into danger when extinguishing the fire due to the large fire, thereby improving fire safety.

[0063] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0064] In the description of this 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.

[0065] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A smart fire fighting system based on the Internet of Things, characterized in that: It includes fire characteristic perception module, video monitoring module, server, database, fire analysis module and fire decision module; The fire characteristic sensing module is used to sense the fire characteristic information in the fire protection area and upload the fire characteristic information to the fire analysis module; the fire characteristic information includes smoke concentration information, carbon monoxide concentration information, carbon dioxide concentration information, temperature information and infrared intensity information; The fire analysis module is used to perform a comprehensive analysis based on the fire characteristic information and the video information group in the fire area to determine whether a fire has occurred and the location of the fire point when the fire occurs; specifically, it includes: The perceived smoke concentration information, carbon monoxide concentration information, carbon dioxide concentration information, temperature information and infrared intensity information are marked as Yi, Ni, Ei, Wi and Hi respectively; Compare each feature information with the corresponding preset safety threshold to obtain the smoke over-alarm value Yt, carbon monoxide over-alarm value Nt, carbon dioxide over-alarm value Et, temperature over-alarm value Wt and infrared intensity over-alarm value Ht; Using the formula The fire warning coefficient HZi is calculated, where g1, g2, and g3 are all preset coefficient factors; μ is the preset compensation coefficient; Compare the fire warning coefficient HZi with the preset warning threshold; if the fire warning coefficient HZi is greater than the preset warning threshold, obtain the video information at the position corresponding to HZi, intercept the image at the corresponding position in the video information and compare it with the flame image group stored in the database; If the comparison is consistent, it is determined that a fire has occurred, a fire signal is generated, and the location information of the fire point is recorded; the fire analysis module is used to send the fire signal and the corresponding location information of the fire point to the server; the server is used to drive the alarm module to sound an alarm after receiving the fire signal; The fire fighting decision module is used to collect fire data at the fire point and the distribution of flammable and explosive materials in the surrounding area for analysis, and automatically output the fire threat level in combination with the fire level recognition module; Based on the fire threat level, a corresponding firefighting and rescue strategy is executed.

2. According to the Internet of Things-based smart fire protection system of claim 1, it is characterized in that: Compare each feature information with the corresponding preset safety threshold, including: Compare the smoke density information Yi with the preset smoke density threshold to obtain the smoke over-alarm value Yt; if the smoke over-alarm value Yt is less than 0, set the smoke over-alarm value Yt=0; Compare the carbon monoxide concentration information Ni with the preset carbon monoxide concentration threshold to obtain the carbon monoxide exceeding warning value Nt; if the carbon monoxide exceeding warning value Nt is less than 0, then set the carbon monoxide exceeding warning value Nt=0; Compare the carbon dioxide concentration information Ei with the preset carbon dioxide concentration threshold to obtain the carbon dioxide excess warning value Et; if the carbon dioxide excess warning value Et is less than 0, set the carbon dioxide excess warning value Et=0; Compare the temperature information Wi with the preset temperature threshold to obtain the temperature over-alarm value Wt; if the temperature over-alarm value Wt is less than 0, set the temperature over-alarm value Wt=0; The infrared intensity information Hi is compared with a preset infrared intensity threshold to obtain an infrared intensity exceeding warning value Ht; if the infrared intensity exceeding warning value Ht is less than 0, the infrared intensity exceeding warning value Ht=0.

3. According to the smart fire fighting system based on the Internet of Things as claimed in claim 1, it is characterized in that: The specific analysis steps of the fire fighting decision module are as follows: Collecting fire data at the fire point, the fire data including flame level and fire warning coefficient; wherein each flame image is manually annotated with the flame level; Collect the real-time scene around the fire point, and identify it through the built-in flammable and explosive distribution recognition algorithm to obtain the spatial distribution information of flammable and explosive materials; The fire intensity data and the spatial distribution information of flammable and explosive materials are substituted into a fire level identification module to automatically output the fire threat level; the fire level identification module is obtained by training an LSTM neural network model with historical values ​​of the fire intensity data, the spatial distribution information of flammable and explosive materials and the fire threat level.

4. According to the Internet of Things-based smart fire protection system of claim 1, it is characterized in that: Based on the fire threat level, execute corresponding firefighting and rescue strategies; Specifically include: When the fire threat level is level one, the sound and light alarm will send out a warning message to inform the user that there is a fire hazard. The sprinkler and broadcasting devices will be in silent state. The nearest staff will be arranged to go to the fire point to use the fire hydrant to extinguish the fire and wait for further confirmation of the fire situation. When the fire threat level is level 2, the sound and light alarm will send out warning information, the broadcasting device will broadcast an alarm to remind residents to evacuate urgently, and the sprinkler device will automatically aim at the fire source to automatically spray water to extinguish the fire. At the same time, staff will be arranged to go to the fire point to use the fire hydrant to extinguish the fire. When the fire threat level is level three, the sound and light alarm will send out a warning message, the broadcasting device will broadcast an alarm to remind residents to evacuate urgently, the sprinkler device will automatically aim at the fire source to implement automatic water spraying fire extinguishing operations, and at the same time, a fire-fighting robot will be dispatched to the fire point to spray dust to extinguish the fire.

5. According to the Internet of Things-based smart fire protection system of claim 1, it is characterized in that: The fire characteristic sensing module includes a plurality of smoke sensors, a plurality of carbon monoxide sensors, a plurality of carbon dioxide sensors, a plurality of temperature sensors and a plurality of infrared sensors; wherein the smoke sensors, carbon monoxide sensors, carbon dioxide sensors, temperature sensors and infrared sensors are all provided with position marks and correspond one to one.

6. The smart fire fighting system based on the Internet of Things according to claim 1 is characterized in that: The video monitoring module is a plurality of monitoring cameras distributed in the fire protection area, which is used to obtain the video information group in the fire protection area in real time and transmit the video information group to the fire analysis module.

Images