Intelligent fire early warning and automatic extinguishing method and device

Abstract

The invention provides an intelligent fire early warning and automatic extinguishing method and device, electronic equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: carrying out region division on the whole region of a plant, determining a monitoring region set, carrying out thermal imaging monitoring on each monitoring region in real time, and determining a corresponding high-temperature-rise monitoring region based on the temperature change of each monitoring region; determining a corresponding alarm priority based on the primary alarm, the intermediate alarm, and the advanced alarm; the combustible gas concentration, the smoke image and the flame image of each high-temperature-rise monitoring area are monitored in real time, whether an alarm is triggered or not is judged based on the combustible gas concentration, the smoke image and the flame image, if yes, the alarm is given, and if yes, a target fire area is determined; and fire extinguishing facilities in the plant area corresponding to the target fire area are controlled to carry out area fire extinguishing. According to the invention, the problem of low accuracy of fire early warning in the industrial factory building in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of computer technology. Specifically, the present application relates to an intelligent fire warning and automatic fire fighting method, device, electronic equipment and storage medium. Background Art

[0002] In industrial production, industrial plants are the core areas of production activities, and their safety is directly related to the normal operation of enterprises and the safety of personnel. However, with the expansion of industrial production scale and the continuous advancement of technology, industrial plants are densely packed with equipment, complex electrical circuits, and many flammable and explosive items, and the risk of fire has increased significantly.

[0003] Traditional fire warning systems often rely on a single sensor for monitoring, which has problems such as false alarms and missed alarms, resulting in low accuracy of fire warnings, making it difficult to control fires in a timely and effective manner, causing huge losses to enterprises.

[0004] From the above, we can see that how to improve the accuracy of fire warning in industrial plants still needs to be solved. Summary of the invention

[0005] The present application provides an intelligent fire warning and automatic fire fighting method, device, electronic device and storage medium, which can solve the problem of low accuracy of fire warning in industrial plants in related technologies. The technical solution is as follows:

[0006] According to one aspect of the present application, an intelligent fire warning and automatic fire fighting method includes: dividing the entire area of ​​the plant into regions, determining a set of monitoring regions, performing real-time thermal imaging monitoring on each monitoring region, and determining a corresponding high temperature rise monitoring region based on the temperature change of each monitoring region; retrieving the real-time temperature and the corresponding combustible gas concentration threshold of each high temperature rise monitoring region, and determining a primary alarm based on the real-time temperature and the combustible gas concentration threshold; retrieving a smoke contrast image of each high temperature rise monitoring region, and determining an intermediate alarm based on the real-time temperature and the smoke contrast image; retrieving a flame contrast image of each high temperature rise monitoring region, and determining a high-level alarm based on the real-time temperature and the flame contrast image, and determining a corresponding alarm priority based on the primary alarm, the intermediate alarm, and the high-level alarm; real-time monitoring of the combustible gas concentration, smoke image, and flame image of each high temperature rise monitoring region, and judging whether an alarm is triggered based on the combustible gas concentration, the smoke image, and the flame image, and if triggered, issuing an alarm, wherein if a high-level alarm is triggered, a target fire region is determined, and the fire extinguishing facilities in the plant region corresponding to the target fire region are controlled to perform regional fire extinguishing.

[0007] In an exemplary embodiment, the method further comprises:

[0008] Determine the key monitoring area based on the departmental division of the entire factory area, among which the key monitoring area is the work area with a high probability of fire occurrence;

[0009] Determine the priority of the key monitoring area as the highest;

[0010] Obtain real-time environmental data corresponding to key monitoring areas at intervals, including combustible gas concentration, image data set, temperature and humidity data;

[0011] The fire warning model is called up to identify the environmental data and determine whether there is a fire risk.

[0012] In an exemplary embodiment, in the process of calling the fire warning model to identify the environmental data and determine whether there is a fire risk, the fire warning model needs to be trained first, and the method further includes:

[0013] Collect combustible gas concentration data sets, smoke image sets and flame image sets as training data sets respectively;

[0014] The regression model is used for combustible gas concentration data as the concentration monitoring training model framework, and the YOLO series of deep learning models are used for smoke image collection and flame image collection as the image recognition training model framework;

[0015] Input the combustible gas concentration data and the fire risk corresponding to the combustible gas concentration data into a concentration monitoring training model framework for training and determining a corresponding concentration monitoring model;

[0016] Inputting the smoke image and the fire risk corresponding to the smoke image, the flame data and the fire risk corresponding to the flame image into an image recognition training model framework for training and determining a corresponding image recognition model;

[0017] The concentration monitoring model is integrated with the image recognition model to determine the corresponding fire warning model

[0018] In an exemplary embodiment, in the process of determining whether to trigger an alarm based on the combustible gas concentration, the smoke image, and the flame image, the method further includes:

[0019] Retrieving the fire warning model;

[0020] Inputting the combustible gas concentration, the smoke image and the flame image into the fire warning model, the fire warning model identifies the combustible gas concentration, the smoke image and the flame image, and determines whether each of the high temperature rise monitoring areas reaches a fire warning level;

[0021] If it is determined that the fire warning level has been reached, the corresponding fire alarm level is determined.

[0022] In an exemplary embodiment, during the monitoring of the entire plant area, the method further includes:

[0023] If an open fire image is detected, determining a priority monitoring area based on the open fire image;

[0024] Acquiring corresponding environmental data based on the priority monitoring area;

[0025] Based on the open flame image and the environmental data, it is determined whether the environment is flammable. If so, a high-level alarm is issued for the priority monitoring area.

[0026] In an exemplary embodiment, in the process of determining the corresponding high temperature rise monitoring area based on the temperature change of each monitoring area, the method further includes:

[0027] Acquire current temperature and humidity data corresponding to the current environment, and determine corresponding temperature rise judgment data based on the current temperature and humidity data;

[0028] Obtain the rated temperature rise data of each monitoring area within the rated time period;

[0029] The rated temperature rise data is compared with the temperature rise judgment data, and if the rated temperature rise data is greater than the temperature rise judgment data, the monitoring area is determined as a high temperature rise monitoring area.

[0030] In an exemplary embodiment, after a fire occurs in a factory building, the method further includes:

[0031] Determine the disaster area corresponding to the fire, and determine work-related data based on the disaster area;

[0032] Selecting corresponding target fire extinguishing facilities based on the work-related data;

[0033] Control the target fire-fighting facilities to extinguish the fire in the disaster area.

[0034] According to one aspect of the present application, an intelligent fire warning and automatic fire fighting device is characterized by comprising:

[0035] The high temperature rise area determination module divides the entire plant area into regions, determines a set of monitoring areas, performs real-time thermal imaging monitoring on each monitoring area, and determines the corresponding high temperature rise monitoring area based on the temperature change of each monitoring area;

[0036] An alarm priority determination module is configured to retrieve the real-time temperature and the corresponding combustible gas concentration threshold of each high temperature rise monitoring area, and determine a primary alarm based on the real-time temperature and the combustible gas concentration threshold; retrieve the smoke contrast image of each high temperature rise monitoring area, and determine an intermediate alarm based on the real-time temperature and the smoke contrast image; retrieve the flame contrast image of each high temperature rise monitoring area, and determine an advanced alarm based on the real-time temperature and the flame contrast image, and determine the corresponding alarm priority based on the primary alarm, the intermediate alarm, and the advanced alarm;

[0037] The fire extinguishing control module monitors the combustible gas concentration, smoke image and flame image of each high temperature rise monitoring area in real time, and determines whether to trigger an alarm based on the combustible gas concentration, smoke image and flame image. If triggered, an alarm is issued. If a high-level alarm is triggered, a target fire area is determined to control the fire extinguishing facilities in the plant area corresponding to the target fire area to perform regional fire extinguishing.

[0038] According to one aspect of the present application, an electronic device includes at least one processor and at least one memory, wherein the memory stores computer-readable instructions; the computer-readable instructions are executed by one or more of the processors, so that the electronic device implements the intelligent fire warning and automatic fire extinguishing method as described above.

[0039] According to one aspect of the present application, a storage medium stores computer-readable instructions thereon, and the computer-readable instructions are executed by one or more processors to implement the intelligent fire warning and automatic fire fighting method as described above.

[0040] According to one aspect of the present application, a computer program product includes computer-readable instructions, which are stored in a storage medium. One or more processors of an electronic device read the computer-readable instructions from the storage medium, load and execute the computer-readable instructions, so that the electronic device implements the intelligent fire warning and automatic fire extinguishing method as described above.

[0041] The beneficial effects of the technical solution provided by this application are:

[0042] In the above technical scheme, the whole area of ​​the factory building is divided into regions, a set of monitoring areas is determined, thermal imaging monitoring is performed on each monitoring area in real time, and the corresponding high-temperature rise monitoring area is determined based on the temperature change of each monitoring area; then, the primary alarm, intermediate alarm and advanced alarm of each high-temperature rise monitoring area are determined, and the corresponding alarm priority is determined based on the primary alarm, intermediate alarm and advanced alarm; after determining the alarm priority, the combustible gas concentration, smoke image and flame image of each high-temperature rise monitoring area are monitored in real time, and based on the combustible gas concentration, smoke image and the flame image, it is determined whether the alarm is triggered. If triggered, an alarm is issued. At the same time, if a high-level alarm is triggered, the target fire area is determined, and the fire-fighting facilities in the factory area corresponding to the target fire area are controlled to perform regional fire extinguishing. Through refined area division and real-time thermal imaging monitoring technology, the potential fire risks in the factory are accurately captured and responded to quickly. Combined with multi-dimensional monitoring data such as combustible gas concentration, smoke images and flame images, the system can comprehensively evaluate the fire risk and automatically trigger the corresponding level of alarm according to the risk level; once the fire is confirmed, the system will immediately locate the target fire area and automatically start the fire-fighting facilities in the area to carry out rapid and effective fire-fighting operations, thereby greatly improving the timeliness, accuracy and response efficiency of fire warnings, effectively ensuring the safety and stability of the factory, and effectively solving the problem of low accuracy of fire warnings in industrial plants in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can obtain other drawings based on these drawings without creative work.

[0044] Figure 1 It is a schematic diagram of the implementation environment involved in this application;

[0045] Figure 2 is a flow chart of an intelligent fire early warning and automatic fire fighting method according to an exemplary embodiment;

[0046] Figure 3 is a flow chart from S101 to S104 in an intelligent fire early warning and automatic fire fighting method according to an exemplary embodiment;

[0047] Figure 4 is a flowchart from S121 to S123 in an intelligent fire early warning and automatic fire fighting method according to an exemplary embodiment;

[0048] Figure 5is a flowchart from S124 to S126 in an intelligent fire early warning and automatic fire fighting method according to an exemplary embodiment;

[0049] Figure 6 It is a structural block diagram of an intelligent fire warning and automatic fire fighting device according to an exemplary embodiment. DETAILED DESCRIPTION

[0050] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present application.

[0051] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present disclosure refers to the presence of the features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0052] The following is an introduction and explanation of several terms involved in this application:

[0053] As can be seen from the above, the relevant technology still has defects in the accuracy of fire warning in industrial plants.

[0054] To this end, the intelligent fire warning and automatic fire fighting method provided in the present application can effectively improve the accuracy of intelligent fire warning and automatic fire fighting. Accordingly, the intelligent fire warning and automatic fire fighting method is suitable for intelligent fire warning and automatic fire fighting device, and the intelligent fire warning and automatic fire fighting device can be deployed in electronic equipment.

[0055] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0056] Figure 1 The schematic diagram of an implementation environment involved in an intelligent fire early warning and automatic fire fighting method is shown in FIG. The implementation environment includes a collection end and a service end.

[0057] See also Figure 2 The embodiment of the present application provides an intelligent fire warning and automatic fire fighting method, which is applicable to electronic equipment, which can be Figure 1 The server side in the implementation environment is shown.

[0058] In the following method embodiments, for ease of description, the execution subject of each step of the method is taken as an electronic device as an example for illustration, but this does not constitute a specific limitation.

[0059] like Figure 2 As shown, the method may include the following steps:

[0060] S100, the entire plant area is divided into regions, a set of monitoring regions is determined, thermal imaging monitoring is performed on each monitoring region in real time, and a corresponding high temperature rise monitoring region is determined based on the temperature change of each monitoring region.

[0061] Among them, for area division, it can be divided according to specific working methods or working time periods, and high-resolution, high-sensitivity thermal imaging cameras can be selected to ensure that subtle temperature changes in the monitoring area can be captured.

[0062] When determining the corresponding high temperature rise monitoring area, the system can set the temperature rise threshold in advance. After the temperature rise data of a certain monitoring area within the rated time reaches the temperature rise threshold, it can be determined as a high temperature rise monitoring area; in addition, if the real-time temperature of a certain monitoring area reaches the pre-set real-time temperature threshold, the corresponding monitoring area also needs to be determined as a high temperature rise monitoring area.

[0063] Specifically, it includes: first, obtaining the current temperature and humidity data corresponding to the current environment, and determining the corresponding temperature rise judgment data based on the current temperature and humidity data, where the temperature rise judgment data can be set in advance; then obtaining the rated temperature rise data of each monitoring area within the rated time period; finally, comparing the rated temperature rise data with the temperature rise judgment data. If the rated temperature rise data is greater than the temperature rise judgment data, it means that the temperature of the corresponding monitoring area rises too fast, and the monitoring area needs to be determined as a high temperature rise monitoring area.

[0064] S110, retrieve the real-time temperature and the corresponding combustible gas concentration threshold of each high-temperature rise monitoring area, determine the primary alarm based on the real-time temperature and the disaster area, and based on the combustible gas concentration threshold of the disaster; retrieve the smoke comparison image of each high-temperature rise monitoring area, determine the intermediate alarm based on the real-time temperature and the disaster area, and based on the disaster smoke comparison image; retrieve the flame comparison image of each high-temperature rise monitoring area, determine the advanced alarm based on the real-time temperature and the flame comparison image, and determine the corresponding alarm priority based on the primary alarm, the disaster area, the intermediate alarm of the disaster, and the advanced alarm.

[0065] Among them, after determining that a high temperature rise monitoring area has appeared, it is necessary to monitor the real-time temperature of the high temperature rise monitoring area through a temperature sensor. At this time, a temperature sensor can be used for monitoring, and a gas sensor installed in the monitoring area is required to collect the possible gas concentration, and the smoke image in the monitoring area is collected through a camera. At the same time, the corresponding flame image of the monitoring area can be collected through the camera.

[0066] The combustible gas concentration, smoke image and flame image in the high temperature rise monitoring area are associated with the corresponding real-time temperature to set the priority. In the embodiment of the present application, the real-time temperature and the combustible gas concentration threshold are used as the primary priority. When the combustible gas concentration in the high temperature rise monitoring area reaches the combustible gas concentration threshold and the real-time temperature reaches the temperature threshold set for the high temperature rise monitoring area, the primary alarm is triggered. Similarly, the real-time temperature and smoke comparison image are used as the intermediate priority. If the corresponding intermediate priority is reached, the corresponding intermediate alarm is triggered. In addition, the real-time temperature and flame comparison image are used as the intermediate priority. After the corresponding high priority is reached, the high alarm is triggered.

[0067] In the above process, by retrieving the temperature data of each high temperature rise monitoring area and the combustible gas concentration threshold in real time, the system can promptly detect potential fire hazards. When the real-time temperature approaches or exceeds the safe range indicated by the combustible gas concentration threshold, the system can trigger a primary alarm to alert relevant personnel, which is the first line of defense to prevent fires. In addition, the system not only relies on temperature data, but also combines smoke contrast images and flame contrast images for further risk assessment. Smoke is a significant sign of the early stage of a fire, while flames are direct evidence that the fire has developed to a certain extent. By analyzing these image data, the system can more accurately determine the development stage of the fire, and issue intermediate and advanced alarms accordingly, providing more detailed and accurate information for subsequent emergency responses.

[0068] It should be pointed out here that the embodiments of the present application are applied to high-risk fields such as industrial production, warehousing and logistics, and are also applicable to daily living environments such as commercial buildings and residential houses; through real-time monitoring and timely warning, the system can significantly improve the safety level of the venue.

[0069] S120, monitor the combustible gas concentration, smoke image and flame image of each high temperature rise monitoring area in real time, and determine whether to trigger an alarm based on the combustible gas concentration, smoke image and flame image. If triggered, an alarm is issued. If a high-level alarm is triggered, the target fire area is determined, and the fire-fighting facilities in the plant area corresponding to the target fire area are controlled to perform regional fire extinguishing.

[0070] Among them, in the process of fire early warning monitoring, such as Figure 3As shown, the following steps are also performed:

[0071] S101, determine the key monitoring areas based on the departmental divisions of the entire factory area.

[0072] Among them, the key monitoring areas are work areas with a high probability of fire and work areas that may involve the production, manufacturing and processing of flammable materials, and these areas need to be monitored closely.

[0073] S102, determining the priority of the key monitoring area as the highest.

[0074] In the entire factory area, all areas are divided into priorities. Low-priority monitoring areas only need to be monitored regularly, while high-priority monitoring areas need to be monitored in key areas, especially the highest-priority monitoring areas, which need to be monitored in real time.

[0075] S103, obtaining corresponding real-time environmental data of key monitoring areas at intervals.

[0076] Among them, environmental data include combustible gas concentration, image data set, temperature and humidity data;

[0077] S104, calling the fire warning model to identify the environmental data and determine whether there is a fire risk.

[0078] It should be pointed out here that the fire warning model is trained in advance, and the corresponding training process is as follows: collect combustible gas concentration data sets, smoke image sets and flame image sets as training data sets respectively; it should be pointed out that in the embodiment of the present application, the regression model is selected for the combustible gas concentration data as the concentration monitoring training model framework, and the YOLO series of deep learning models are selected as the smoke image set and the flame image set as the image recognition training model framework. Different models are used for learning and training for the training set of combustible gas and the image training set. The regression model is particularly suitable for predicting continuous value problems, such as combustible gas concentration. By training the regression model, the complex relationship between concentration data and time and environmental parameters (such as temperature, humidity, wind speed, etc.) can be learned, so as to more accurately predict future concentration changes; the YOLO series model is a deep learning framework designed for real-time target detection, which can quickly and accurately identify targets (such as smoke, flames) in images. When processing image data, this model can make full use of the spatial information and contextual information of the image to improve the accuracy and efficiency of recognition.

[0079] After the model is selected, the combustible gas concentration data and the fire risk corresponding to the combustible gas concentration data are input into the concentration monitoring training model framework for training and the corresponding concentration monitoring model is determined. In addition, the disaster area, based on the disaster smoke image and the fire risk corresponding to the smoke image, the flame data and the fire risk corresponding to the flame image, are input into the image recognition training model framework for training and the corresponding image recognition model is determined. After the two models are determined, the concentration monitoring model and the image recognition model can be integrated to determine the corresponding fire warning model.

[0080] By combining combustible gas concentration data and smoke / flame image data, the fire warning model can comprehensively consider multiple fire indicators to more accurately judge the fire risk. The multi-source data fusion method can reduce the false alarms or omissions that may be caused by a single data source. Combustible gas concentration data and image data each have their own advantages and disadvantages in fire warning; concentration data can monitor changes in gas concentration in real time, but may not directly reflect the intuitive phenomenon of fire; and image data can intuitively display the smoke and flame conditions at the fire scene, but may be affected by factors such as ambient lighting and occlusion. The fusion of the two can form a complementary effect.

[0081] In the process of judging the triggering alarm through the fire warning model, if Figure 4 As shown, the method specifically includes:

[0082] S121, retrieve the fire warning model;

[0083] The specific training process has been explained above and will not be repeated here.

[0084] S122, inputting the combustible gas concentration, smoke image and flame image into the fire warning model, the fire warning model identifies the combustible gas concentration, smoke image and flame image, and determines whether each high temperature rise monitoring area reaches the fire warning level;

[0085] Among them, the fire warning level can be defined in the model training process, and the fire warning level can be set as primary, intermediate and advanced.

[0086] S123: If it is determined that the fire warning level has been reached, the corresponding fire alarm level is determined.

[0087] It should be pointed out here that when the corresponding fire warning level reaches primary, the corresponding fire alarm level is primary alarm.

[0088] When the fire warning level is primary, the system issues a primary alarm, which usually means that there is a potential fire risk, but it has not yet reached an emergency state. At this time, preliminary response measures can be initiated, such as automatically opening the ventilation system to reduce the concentration of combustible gas, or notifying relevant personnel to go to the scene for preliminary inspection and treatment. This hierarchical response mechanism helps to avoid unnecessary panic, while ensuring that appropriate preventive measures are taken in a timely manner. With timely response and hierarchical treatment, the fire warning system can control the fire within a smaller range at the early stage, thereby effectively reducing the loss of fire to people, property and the environment. Especially in the advanced alarm stage, the system can quickly initiate a comprehensive emergency response mechanism, including evacuating personnel, isolating the fire source, extinguishing the fire, etc., to minimize the harm of the fire.

[0089] In addition, during the monitoring of the factory, some areas of the factory may require open flame operations, so corresponding monitoring is required, such as Figure 5 As shown, the specific process includes:

[0090] S124, if an open fire image is detected, determining a priority monitoring area based on the open fire image;

[0091] In the event of an open fire, monitoring needs to be determined as real-time monitoring.

[0092] S125, acquiring corresponding environmental data based on the priority monitoring area;

[0093] S126, based on the open flame image and environmental data, determine whether it is in a flammable environment. If so, issue a high-level alarm for the priority monitoring area.

[0094] When judging whether it is in a flammable environment, the fire warning model mentioned above can be used for real-time judgment. If not, continue real-time monitoring. If so, it is necessary to issue a high-level alarm for the priority monitoring area as soon as possible.

[0095] Finally, if a fire does occur in the factory, follow these steps:

[0096] First, determine the disaster area corresponding to the fire, based on the disaster area, determine work-related data based on the disaster area, select the corresponding target fire-fighting facilities based on the work-related data, and control the target fire-fighting facilities to extinguish the fire in the disaster area.

[0097] Through fire detection systems (such as smoke detectors, temperature sensors, etc.) and image recognition technology, the specific location of the fire, that is, the disaster area, can be quickly determined. This helps the fire department quickly understand the fire situation and provide accurate targets for subsequent firefighting work. After quickly locating the disaster area, measures can be taken immediately to isolate the fire source and prevent the fire from spreading to other areas, thereby minimizing the loss of fire to people, property and the environment.

[0098] In addition, work-related data include the building structure, personnel distribution, types and quantities of combustibles, wind direction and speed and other meteorological conditions in the disaster area. These data provide an important basis for the fire department to formulate fire-fighting plans and deploy rescue forces. According to the specific conditions of the disaster area, the fire department can reasonably deploy fire trucks, fire-fighting equipment, rescue personnel and other resources to ensure the smooth progress of fire-fighting work.

[0099] The following is an embodiment of the device of the present application, which can be used to implement the intelligent fire warning and automatic fire fighting method involved in the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the method embodiment of the intelligent fire warning and automatic fire fighting method involved in the present application.

[0100] See also Figure 6 , an intelligent fire warning and automatic fire fighting device is provided in the embodiment of the present application, including but not limited to:

[0101] The high temperature rise area determination module 200 divides the entire plant area into regions, determines a set of monitoring regions, performs real-time thermal imaging monitoring on each monitoring region, and determines the corresponding high temperature rise monitoring region based on each disaster area and the temperature change of the disaster monitoring region;

[0102] The alarm priority determination module 210 retrieves the real-time temperature of each high temperature rise monitoring area and the corresponding combustible gas concentration threshold, and determines a primary alarm based on the disaster area, the real-time temperature of the disaster and the disaster area, and the combustible gas concentration threshold of the disaster; retrieves the smoke contrast image of each high temperature rise monitoring area, and determines an intermediate alarm based on the disaster area, the real-time temperature of the disaster and the disaster area, and the smoke contrast image of the disaster; retrieves the flame contrast image of each high temperature rise monitoring area, and determines an advanced alarm based on the disaster area, the real-time temperature of the disaster and the disaster area, and the flame contrast image of the disaster, and determines the corresponding alarm priority based on the disaster area, the primary alarm of the disaster, the disaster area, the intermediate alarm of the disaster, and the advanced alarm;

[0103] The fire extinguishing control module 220 monitors each disaster area in real time, and determines whether to trigger an alarm based on the combustible gas concentration, smoke image and flame image in the high temperature rise monitoring area of ​​the disaster, and based on the disaster area, based on the combustible gas concentration, the disaster area, based on the disaster smoke image and the disaster area, and based on the disaster flame image. If triggered, an alarm is issued. If a high-level alarm is triggered, a target fire area is determined to control the fire extinguishing facilities in the plant area corresponding to the target fire area to perform regional fire extinguishing.

[0104] In an exemplary embodiment, the device further includes but is not limited to:

[0105] The key monitoring area determination module is used to determine the key monitoring area according to the department division of the entire plant area. The key monitoring area is the working area with a high probability of fire occurrence;

[0106] A highest priority determination module, used to determine the disaster area as having the highest priority based on the disaster key monitoring area;

[0107] Environmental data acquisition module, used to obtain real-time environmental data corresponding to key monitoring areas at intervals, where environmental data includes combustible gas concentration, image data set, temperature and humidity data;

[0108] The fire risk judgment module calls the fire warning model to identify the environmental data and use it to determine whether there is a fire risk.

[0109] In an exemplary embodiment, the device further includes but is not limited to:

[0110] A training data set collection module is used to collect a combustible gas concentration data set, a smoke image set and a flame image set as training data sets respectively;

[0111] The framework selection module is used to select the regression model for combustible gas concentration data as the concentration monitoring training model framework, and to select the YOLO series of deep learning models as the smoke image set and the flame image set as the image recognition training model framework;

[0112] A concentration training module is used to input the disaster area, the combustible gas concentration data of the disaster and the fire risk corresponding to the combustible gas concentration data into the concentration monitoring training model framework for training and determining the corresponding concentration monitoring model;

[0113] An image training module is used to input the disaster area based on the disaster smoke image and the fire risk corresponding to the smoke image, and the disaster area based on the disaster flame data and the fire risk corresponding to the flame image into the image recognition training model framework for training and determining the corresponding image recognition model;

[0114] The fire warning module determination module is used to fuse the disaster area based on the disaster concentration monitoring model with the disaster area based on the disaster image recognition model to determine the corresponding fire warning model.

[0115] In an exemplary embodiment, the device further includes but is not limited to:

[0116] A fire warning model retrieval module is used to retrieve the disaster area based on the disaster fire warning model;

[0117] The fire warning level determination module inputs the disaster area, based on the combustible gas concentration of the disaster, the disaster area, based on the disaster smoke image and the disaster area, based on the disaster flame image into the disaster area, based on the disaster fire warning model, the disaster area, based on the disaster fire warning model to identify the combustible gas concentration, the smoke image and the flame image, and is used to determine whether each disaster area, based on the disaster high temperature rise monitoring area, reaches the fire warning level;

[0118] The fire alarm level determination module is used to determine the corresponding fire alarm level if it is determined that the fire warning level has been reached.

[0119] In an exemplary embodiment, the device further includes but is not limited to:

[0120] A priority monitoring area determination module, if an open fire image is detected, based on the disaster area, the disaster open fire image is used to determine the priority monitoring area;

[0121] An environmental data acquisition module, based on the disaster area and the disaster priority monitoring area, is used to acquire corresponding environmental data;

[0122] The flammable environment judgment module is based on the disaster area, the disaster open fire image and the disaster area, and the disaster environment data to judge whether it is in a flammable environment. If so, a high-level alarm is issued for the priority monitoring area.

[0123] In an exemplary embodiment, the device further includes but is not limited to:

[0124] A temperature rise judgment data determination module is used to obtain current temperature and humidity data corresponding to the current environment, based on the disaster area, and to determine corresponding temperature rise judgment data based on the current temperature and humidity data of the disaster;

[0125] A rated temperature rise data acquisition module is used to obtain the rated temperature rise data of each monitoring area within a rated time period;

[0126] The comparison module is used to compare the disaster area based on the disaster rated temperature rise data with the temperature rise judgment data. If the disaster area based on the disaster rated temperature rise data is greater than the temperature rise judgment data, the monitoring area is determined as a high temperature rise monitoring area.

[0127] In an exemplary embodiment, the device further includes but is not limited to:

[0128] A work-related data determination module determines a disaster area corresponding to the fire, and based on the disaster area, determines work-related data based on the disaster area;

[0129] A target fire-fighting facility selection module is used to select corresponding target fire-fighting facilities based on the disaster area and the disaster work related data;

[0130] The control module is used to control the target fire-fighting facilities to extinguish the fire in the disaster area.

[0131] It should be noted that the intelligent fire warning and automatic fire extinguishing device provided in the above embodiment only uses the division of the above-mentioned functional modules as an example when performing intelligent fire warning and automatic fire extinguishing. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the intelligent fire warning and automatic fire extinguishing device will be divided into different functional modules to complete all or part of the functions described above.

[0132] In addition, the embodiments of the intelligent fire warning and automatic fire fighting device and the intelligent fire warning and automatic fire fighting method provided in the above embodiments belong to the same concept, and the specific way in which each module performs the operation has been described in detail in the method embodiment and will not be repeated here.

[0133] According to one aspect of the present application, an electronic device includes at least one processor and at least one memory, wherein the memory stores computer-readable instructions; the computer-readable instructions are executed by one or more of the processors, so that the electronic device implements the intelligent fire warning and automatic fire extinguishing method as described above.

[0134] In addition, a storage medium is provided in an embodiment of the present application, on which computer-readable instructions are stored, and the computer-readable instructions are executed by one or more processors to implement the intelligent fire warning and automatic fire fighting method as described above.

[0135] In an embodiment of the present application, a computer program product is provided. The computer program product includes computer-readable instructions. The computer-readable instructions are stored in a storage medium. One or more processors of an electronic device read the computer-readable instructions from the storage medium, load and execute the computer-readable instructions, so that the electronic device implements the intelligent fire warning and automatic fire fighting method as described above.

[0136] Compared with related technologies, through refined area division and real-time thermal imaging monitoring technology, the system can accurately capture and quickly respond to potential fire risks in the factory. Combined with multi-dimensional monitoring data such as combustible gas concentration, smoke images and flame images, the system can comprehensively evaluate fire risks and automatically trigger alarms of corresponding levels based on risk levels; once a fire is confirmed, the system will immediately locate the target fire area and automatically start the fire-fighting facilities in the area to carry out rapid and effective fire-fighting operations, thereby greatly improving the timeliness, accuracy and response efficiency of fire warnings, effectively ensuring the safety and stability of the factory, and effectively solving the problem of low accuracy of fire warnings in industrial plants that exists in related technologies.

[0137] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0138] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An intelligent fire warning and automatic fire fighting method, characterized in that: include: Divide the entire plant area into regions, determine a set of monitoring areas, conduct real-time thermal imaging monitoring of each monitoring area, and determine the corresponding high temperature rise monitoring area based on the temperature change of each monitoring area; Retrieving the real-time temperature and the corresponding combustible gas concentration threshold of each high temperature rise monitoring area, and determining a primary alarm based on the real-time temperature and the combustible gas concentration threshold; Retrieving the smoke contrast image of each high temperature rise monitoring area, and determining a medium-level alarm based on the real-time temperature and the smoke contrast image; Retrieving the flame contrast image of each high temperature rise monitoring area, and determining a high-level alarm based on the real-time temperature and the flame contrast image, and determining a corresponding alarm priority based on the primary alarm, the medium-level alarm, and the high-level alarm; The combustible gas concentration, smoke image and flame image of each high temperature rise monitoring area are monitored in real time, and based on the combustible gas concentration, the smoke image and the flame image, it is determined whether an alarm is triggered. If triggered, an alarm is issued. If a high-level alarm is triggered, a target fire area is determined, and the fire-fighting facilities in the plant area corresponding to the target fire area are controlled to carry out regional fire extinguishing.

2. The method according to claim 1, characterized in that The method further comprises: Determine the key monitoring area based on the departmental division of the entire factory area, among which the key monitoring area is the work area with a high probability of fire occurrence; Determine the priority of the key monitoring area as the highest; Obtain real-time environmental data corresponding to key monitoring areas at intervals, including combustible gas concentration, image data set, temperature and humidity data; The fire warning model is called up to identify the environmental data and determine whether there is a fire risk.

3. The method according to claim 2, characterized in that In the process of calling the fire warning model to identify the environmental data and determine whether there is a fire risk, the fire warning model needs to be trained first, and the method also includes: Collect combustible gas concentration data sets, smoke image sets and flame image sets as training data sets respectively; The regression model is used for combustible gas concentration data as the concentration monitoring training model framework, and the YOLO series of deep learning models are used for smoke image collection and flame image collection as the image recognition training model framework; Input the combustible gas concentration data and the fire risk corresponding to the combustible gas concentration data into a concentration monitoring training model framework for training and determining a corresponding concentration monitoring model; Inputting the smoke image and the fire risk corresponding to the smoke image, the flame data and the fire risk corresponding to the flame image into an image recognition training model framework for training and determining a corresponding image recognition model; The concentration monitoring model is integrated with the image recognition model to determine a corresponding fire warning model.

4. The method according to claim 3, characterized in that In the process of determining whether to trigger an alarm based on the combustible gas concentration, the smoke image, and the flame image, the method further includes: Retrieving the fire warning model; Inputting the combustible gas concentration, the smoke image and the flame image into the fire warning model, the fire warning model identifies the combustible gas concentration, the smoke image and the flame image, and determines whether each of the high temperature rise monitoring areas reaches a fire warning level; If it is determined that the fire warning level has been reached, the corresponding fire alarm level is determined.

5. The method according to claim 4, characterized in that During the monitoring of the entire plant area, the method further includes: If an open fire image is detected, determining a priority monitoring area based on the open fire image; Acquiring corresponding environmental data based on the priority monitoring area; Based on the open flame image and the environmental data, it is determined whether the environment is flammable. If so, a high-level alarm is issued for the priority monitoring area.

6. The method according to claim 1, characterized in that In the process of determining the corresponding high temperature rise monitoring area based on the temperature change of each monitoring area, the method further includes: Acquire current temperature and humidity data corresponding to the current environment, and determine corresponding temperature rise judgment data based on the current temperature and humidity data; Obtain the rated temperature rise data of each monitoring area within the rated time period; The rated temperature rise data is compared with the temperature rise judgment data, and if the rated temperature rise data is greater than the temperature rise judgment data, the monitoring area is determined as a high temperature rise monitoring area.

7. The method according to claim 1, characterized in that After a fire occurs in the factory building, the method further comprises: Determine the disaster area corresponding to the fire, and determine work-related data based on the disaster area; Selecting corresponding target fire extinguishing facilities based on the work-related data; Control the target fire-fighting facilities to extinguish the fire in the disaster area.

8. An intelligent fire warning and automatic fire fighting device, characterized in that: include: The high temperature rise area determination module divides the entire plant area into regions, determines a set of monitoring areas, performs real-time thermal imaging monitoring on each monitoring area, and determines the corresponding high temperature rise monitoring area based on the temperature change of each monitoring area; An alarm priority determination module is configured to retrieve the real-time temperature and the corresponding combustible gas concentration threshold of each high temperature rise monitoring area, and determine a primary alarm based on the real-time temperature and the combustible gas concentration threshold; retrieve the smoke contrast image of each high temperature rise monitoring area, and determine an intermediate alarm based on the real-time temperature and the smoke contrast image; retrieve the flame contrast image of each high temperature rise monitoring area, and determine an advanced alarm based on the real-time temperature and the flame contrast image, and determine the corresponding alarm priority based on the primary alarm, the intermediate alarm, and the advanced alarm; The fire extinguishing control module monitors the combustible gas concentration, smoke image and flame image of each high temperature rise monitoring area in real time, and determines whether to trigger an alarm based on the combustible gas concentration, smoke image and flame image. If triggered, an alarm is issued. If a high-level alarm is triggered, a target fire area is determined to control the fire extinguishing facilities in the plant area corresponding to the target fire area to perform regional fire extinguishing.

9. An electronic device, characterized in that: include: at least one processor and at least one memory, wherein: The memory has computer-readable instructions stored thereon; The computer-readable instructions are executed by one or more of the processors, so that the electronic device implements the intelligent fire warning and automatic fire fighting method according to any one of claims 1 to 7.

10. A storage medium having computer-readable instructions stored thereon, characterized in that: The computer-readable instructions are executed by one or more processors to implement the intelligent fire warning and automatic fire fighting method according to any one of claims 1 to 7.

Images