Fire early warning system based on intelligent platform

Abstract

The invention provides a fire early warning system based on an intelligent platform, and relates to the field of fire early warning, and the system comprises a plurality of fire monitoring devices which are configured at different monitoring points and are used for collecting the temperature, smoke and video data of a monitoring area in real time; the integrated monitoring platform is used for receiving, displaying and managing the real-time fire information of each monitoring point location, and the integrated monitoring platform presents a monitoring picture through a Web interface of a B / S architecture and has the functions of real-time alarm, video monitoring, video playback and historical alarm query; and the industrial-grade ring network switch is used for establishing a stable communication channel between the fire monitoring equipment and the integrated monitoring platform so as to realize high-bandwidth and low-delay data transmission. Based on the system provided by the invention, the fire condition can be monitored in real time, the fire detection accuracy is improved, the false alarm rate is reduced, a visual interface is provided, and management and traceability analysis are facilitated.

Description

Technical Field

[0001] The present application relates to the field of fire warning, and in particular to a fire warning system based on an intelligent platform. Background Art

[0002] Existing fire warning systems are mostly based on traditional single monitoring methods such as smoke detection and temperature detection, which are prone to false alarms, especially in complex environments (such as rainy weather, night, etc.). In addition, traditional systems lack a centralized management visual interface, which is not convenient for real-time monitoring and retrospective analysis of multiple areas. Summary of the invention

[0003] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0004] To this end, the purpose of this application is to propose a fire warning system based on an intelligent platform.

[0005] To achieve the above objectives, the present application embodiment proposes a fire warning system based on an intelligent platform, including:

[0006] Multiple fire monitoring devices are deployed at different monitoring points to collect temperature, smoke and video data of the monitoring area in real time;

[0007] An integrated monitoring platform is used to receive, display and manage real-time fire information of each monitoring point. The integrated monitoring platform presents monitoring images through a Web interface with a B / S architecture and has real-time alarm, video monitoring, video playback and historical alarm query functions;

[0008] The industrial-grade ring network switch is used to establish a stable communication channel between the fire monitoring equipment and the integrated monitoring platform to achieve high-bandwidth, low-latency data transmission.

[0009] Optionally, the integrated monitoring platform also includes an alarm module. When the fire monitoring equipment detects that the temperature or smoke exceeds a preset threshold, the alarm module is used to generate alarm information including the location and time of the fire, display the alarm information through real-time pop-up windows and page scrolling broadcasts, and push the alarm information to management personnel.

[0010] Optionally, the pop-up window interface of the alarm module has a split-screen display function, wherein:

[0011] The left half displays in real time a screenshot of a suspected fire obtained by the fire monitoring device, including visible light image data, for preliminary display of the suspected fire;

[0012] The right half displays the current monitoring screen of the fire monitoring device in real time, which is convenient for users to verify the fire information through real-time video;

[0013] The displayed alarm information also includes alarm time, alarm level, alarm location, temperature and smoke concentration data, so that users can comprehensively judge the fire level.

[0014] Optionally, the integrated monitoring platform further includes a video playback module, wherein:

[0015] The video playback module is used to call historical video data related to the fire situation so that the user can select a specific date and time period for playback;

[0016] The video playback module supports playback speed adjustment to facilitate fire source tracing and analysis afterwards.

[0017] Optionally, the integrated monitoring platform further includes a real-time video monitoring module, wherein:

[0018] The real-time video monitoring module has a PTZ control function, which supports users to click on the fire monitoring equipment at the corresponding point to view the real-time monitoring screen;

[0019] The real-time video monitoring module supports users to adjust and zoom the monitoring screen up, down, left, and right, and select single-screen, four-screen, nine-screen and sixteen-screen modes in the split screen;

[0020] The real-time video monitoring module supports users to remotely adjust the shooting angle and focal length of the fire monitoring equipment through pan-tilt control. The control accuracy is adjustable from 1 to 7 levels, which can meet the needs of multi-area and multi-directional fire monitoring.

[0021] Optionally, the integrated monitoring platform includes a false alarm filtering module, wherein:

[0022] The false alarm filtering module performs secondary analysis and processing on the fire information based on multi-dimensional data, filters non-fire features through a false alarm screening mechanism, and records confirmed fire alarm information;

[0023] The false alarm filtering module supports manual review, allowing users to confirm or cancel alarms in historical alarm records.

[0024] Optionally, the fire monitoring equipment is used to:

[0025] Obtain visible light video stream data and real-time temperature data of the target area;

[0026] Detecting fire characteristics in the visible light video stream data according to a fire monitoring model, and obtaining temperature characteristics according to the real-time temperature data;

[0027] Real-time fire information is generated based on the detected fire characteristics and the obtained temperature data, and sent to the integrated monitoring platform.

[0028] Optionally, the fire monitoring device is also used for:

[0029] By analyzing the light and weather conditions of the current environment in real time, the detection parameters of the fire monitoring model are autonomously adjusted;

[0030] The fire monitoring model is regularly updated according to the accumulated detection data to enhance the adaptability and fire detection accuracy of the fire monitoring equipment in different application scenarios, wherein the fire monitoring model has a multi-layer neural network structure and can continuously optimize the identification parameters of fire characteristics through historical alarm data and environmental parameters;

[0031] Providing update notifications for the fire monitoring model facilitates system maintenance personnel to manage the frequency and conditions of model updates.

[0032] Optionally, the industrial ring network switch has a link redundancy function, which can automatically switch to a backup link when any node fails, ensuring continuous transmission of the video stream;

[0033] The industrial ring network switch supports STP / RSTP protocol;

[0034] The industrial-grade ring network switch adopts multi-mode / single-mode optical fiber transmission, supports Gigabit Ethernet, and meets the needs of long-distance data transmission.

[0035] The technical solution provided by the embodiments of the present application brings at least the following beneficial effects:

[0036] By introducing industrial-grade ring network switches, high-bandwidth, low-latency data transmission between fire monitoring equipment and integrated monitoring platform is achieved, avoiding alarm information delays caused by network delays or single point failures, thereby improving the continuity of video stream transmission and the reliability of the system; through the real-time pop-up window and rolling broadcast function of the alarm module, the rapid push of fire information is achieved, avoiding the omission or delay of fire information, and improving the fire response speed of the system; through the secondary analysis and processing of fire characteristics by the false alarm filtering module, effective screening of false alarm information is achieved, avoiding false alarms interfering with the normal operation of the system, and improving the accuracy of fire monitoring; through the intelligent parameter optimization function, the fire monitoring equipment can identify fires under low light and bad weather conditions, avoiding the influence of environmental factors on the detection effect, and improving the adaptability and recognition accuracy of the system; through the regular update of the AI ​​model optimization module, the self-learning and optimization of the fire detection model is achieved, avoiding the decrease in detection accuracy due to scene changes, thereby improving the system's fire recognition ability in different application scenarios. These technical effects ensure the stability, efficiency and accuracy of the system in fire warning, and improve the overall level of fire monitoring and warning.

[0037] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0039] Figure 1 A schematic diagram of the structure of a fire warning system based on an intelligent platform provided in an embodiment of the present application;

[0040] Figure 2 A schematic diagram of an integrated monitoring platform provided in an embodiment of the present application;

[0041] Figure 3 A schematic diagram of an integrated monitoring platform provided by another embodiment of the present application;

[0042] Figure 4 A schematic diagram of an integrated monitoring platform provided by another embodiment of the present application;

[0043] Figure 5 A schematic diagram of an integrated monitoring platform provided by another embodiment of the present application;

[0044] Figure 6 A schematic diagram of an integrated monitoring platform provided by another embodiment of the present application;

[0045] Figure 7 A schematic diagram of an integrated monitoring platform provided in another embodiment of the present application. DETAILED DESCRIPTION

[0046] 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 intended to be used to explain the present application, and should not be construed as limiting the present application.

[0047] Existing fire warning systems are mostly based on traditional single monitoring methods such as smoke detection and temperature detection, which are prone to false alarms, especially in complex environments (such as rainy weather, night, etc.). In addition, traditional systems lack a centralized management visual interface, which is not convenient for real-time monitoring and retrospective analysis of multiple areas.

[0048] To address this problem, the present invention provides a fire warning system based on an intelligent platform. Figure 1 The structure diagram of a fire warning system 10 based on an intelligent platform provided in an embodiment of the present application is shown in FIG. Figure 1As shown, the system includes multiple fire monitoring devices 1, an integrated monitoring platform 2 and an industrial-grade ring network switch 3.

[0049] In the embodiment of the present application, multiple fire monitoring devices 1 are configured at different monitoring points to collect temperature, smoke and video data of the monitoring area in real time; the integrated monitoring platform 2 is used to receive, display and manage real-time fire information of each monitoring point. The integrated monitoring platform 2 presents the monitoring screen through a Web interface with a B / S architecture, and has real-time alarm, video monitoring, video playback and historical alarm query functions; the industrial-grade ring network switch 3 is used to establish a stable communication channel between the fire monitoring equipment and the integrated monitoring platform to achieve high-bandwidth, low-latency data transmission.

[0050] First, for the fire monitoring device 1, in the embodiment of the present application, the fire monitoring device is used to: obtain visible light video stream data and real-time temperature data of the target area; detect fire characteristics in the visible light video stream data according to the fire monitoring model, and obtain temperature characteristics according to the real-time temperature data; generate real-time fire information based on the detected fire characteristics and the obtained temperature data, and send it to the integrated monitoring platform.

[0051] In the embodiment of the present application, firstly, the visible light video stream data of the target area can be obtained through the camera in the fire monitoring device, and the temperature data of the target area can be collected through the infrared sensor in the fire monitoring device. Then, the fire characteristics and temperature characteristics are extracted through the pre-trained fire monitoring model. The fire characteristics can be further subdivided into smoke characteristics and flame characteristics. The smoke characteristics include area change rate, position change and shape change rate. The flame characteristics include flame height and flame color. The temperature characteristics include temperature value, temperature change rate and temperature distribution characteristics. Finally, real-time fire information is generated based on the detected fire characteristics and the obtained temperature data, and sent to the integrated monitoring platform.

[0052] It is understandable that images with different types of features can be collected for training to achieve detection and recognition of various features, and this application does not make specific limitations on this.

[0053] Furthermore, the fire monitoring device proposed in this application also has an intelligent parameter optimization function, which can specifically realize the following functions:

[0054] 1. The camera can analyze the light and weather conditions of the current environment in real time. For complex environments such as rainy weather or insufficient light at night, the camera can intelligently adjust the detection parameters, that is, autonomously adjust the detection parameters of the fire monitoring model to improve recognition accuracy;

[0055] 2. The fire monitoring model can be updated regularly based on the accumulated detection data to enhance the adaptability and fire detection accuracy of the fire monitoring equipment in different application scenarios. The fire monitoring model has a multi-layer neural network structure and can continuously optimize the identification parameters of fire characteristics through historical alarm data and environmental parameters;

[0056] 3. It can provide update notifications of the fire monitoring model, so that system maintenance personnel can manage the frequency and conditions of model updates.

[0057] Secondly, for the integrated monitoring platform 2, under normal circumstances, its schematic diagram is as follows Figure 2 As shown, the schematic diagram in the alarm situation is as follows Figure 3 shown.

[0058] When the user logs into the system and enters the monitoring map interface, the integrated monitoring platform can display the location information and real-time alarm information of each monitoring point. The camera color is white, indicating that there is no abnormality. The camera turns red and flashes, indicating that a fire is detected at the corresponding point, and there is a corresponding pop-up reminder.

[0059] In the embodiment of the present application, the integrated monitoring platform 2 also includes an alarm module 21. When the fire monitoring device detects that the temperature or smoke exceeds a preset threshold, the alarm module 21 is used to generate an alarm message including the location and time of the fire, display the alarm message through a real-time pop-up window and page scrolling broadcast, and push the alarm message to the management personnel, such as Figure 4 shown.

[0060] In addition, the pop-up window interface of the alarm module 21 has a split-screen display function, where:

[0061] The left half displays in real time a screenshot of a suspected fire obtained by the fire monitoring device, including visible light image data, which is used to preliminarily display the suspected fire; the right half displays in real time the current monitoring screen of the fire monitoring device, allowing users to verify fire information through real-time video; the displayed alarm information also includes alarm time, alarm level, alarm location, temperature and smoke concentration data, so that users can comprehensively judge the fire level.

[0062] It should be noted that after a fire is detected, the corresponding point monitoring will continue to monitor the fire location for two minutes and record the video, and remind the staff to pay attention to the corresponding location monitoring situation in time. If it is a false alarm, the staff will be prompted to click the cancel button in the historical alarm information to resume the patrol scanning status.

[0063] In the embodiment of the present application, the integrated monitoring platform 2 also includes a video playback module 22, and the video playback function can call the on-site camera video to view the historical monitoring screen.

[0064] Specifically, the video playback module 22 can call historical video data related to the fire so that the user can select a specific date and time period for playback, and supports playback speed adjustment such as fast forward and slow play to facilitate subsequent fire tracing and analysis.

[0065] In a possible embodiment, a schematic diagram of video playback displayed by an integrated monitoring platform in a certain scenario is as follows: Figure 6 shown.

[0066] In the embodiment of the present application, the integrated monitoring platform 2 also includes a real-time video monitoring module 23, wherein:

[0067] The real-time video monitoring module 23 has a pan / tilt control function, which supports users to click on the fire monitoring equipment at the corresponding point to view the real-time monitoring picture. After the real-time picture appears, a red × close button will appear in the upper right corner of the small split screen. Click it to close the playback.

[0068] In a possible embodiment, a schematic diagram of video surveillance displayed by an integrated monitoring platform in a certain scenario is as follows: Figure 5 shown.

[0069] In addition, the real-time video monitoring module 23 also supports users to adjust and zoom the monitoring screen in the up, down, left, and right directions, and supports users to remotely adjust the shooting angle and focal length of the fire monitoring equipment through the pan / tilt control, and the control accuracy can be adjusted from 1 to 7 levels. It also supports users to select the monitoring screen display window in the split screen, and the monitoring screen display window can be selected as a single window, four split screens, nine split screens, and sixteen split screens. After clicking the corresponding split screen, the monitoring screen will be played in the default order, thereby meeting the fire monitoring needs in multiple areas and directions.

[0070] In the embodiment of the present application, the integrated monitoring platform 2 also includes a false alarm filtering module 24 .

[0071] Specifically, the false alarm filtering module 24 performs secondary analysis and processing on the fire information based on multi-dimensional data, filters non-fire features through a false alarm screening mechanism, and records confirmed fire alarm information; and, the false alarm filtering module 24 supports manual review, allowing users to confirm or cancel alarms in historical alarm records.

[0072] In a possible embodiment, a historical alarm diagram displayed by the integrated monitoring platform in a certain scenario is as follows: Figure 7 shown.

[0073] All the alarm information of the system can be queried through the historical alarm function of this application system. You can select the query conditions (confirmation status, time) at the top of the page. Every time a fire occurs, the system will push two alarm messages. The first one is the alarm message that needs to be confirmed or cancelled by the system user; the second one is the restoration message, which is used by the system maintenance developer to confirm the device status in the background, and the system user can ignore it.

[0074] Finally, the industrial-grade ring network switch 3 has a link redundancy function, which can automatically switch to the backup link when any node fails, ensuring the continuous transmission of the video stream; in addition, the industrial-grade ring network switch 3 also supports the STP / RSTP protocol, which can enhance the stability of the ring network structure; in addition, the industrial-grade ring network switch 3 adopts multi-mode / single-mode optical fiber transmission, supports Gigabit Ethernet, and meets the needs of long-distance data transmission.

[0075] The embodiment of the present application realizes high-bandwidth, low-latency data transmission between the fire monitoring equipment and the integrated monitoring platform by introducing an industrial-grade ring network switch, avoiding the delay of alarm information caused by network delay or single point failure, thereby improving the continuity of video stream transmission and the reliability of the system; through the real-time pop-up window and rolling broadcast function of the alarm module, the rapid push of fire information is realized, avoiding the omission or delay of fire information, and improving the fire response speed of the system; through the secondary analysis and processing of fire characteristics by the false alarm filtering module, the effective screening of false alarm information is realized, avoiding the interference of false alarms on the normal operation of the system, and improving the accuracy of fire monitoring; through the intelligent parameter optimization function, the fire monitoring equipment can identify fires under low light and bad weather conditions, avoiding the influence of environmental factors on the detection effect, and improving the adaptability and recognition accuracy of the system; through the regular update of the AI ​​model optimization module, the self-learning and optimization of the fire detection model is realized, avoiding the decrease in detection accuracy due to scene changes, thereby improving the fire recognition ability of the system in different application scenarios. These technical effects ensure the stability, efficiency and accuracy of the system in fire warning, and improve the overall level of fire monitoring and warning.

[0076] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution of this application can be achieved, and this document is not limited here.

[0077] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A fire warning system based on an intelligent platform, characterized in that: include: Multiple fire monitoring devices are deployed at different monitoring points to collect temperature, smoke and video data of the monitoring area in real time; An integrated monitoring platform is used to receive, display and manage real-time fire information of each monitoring point. The integrated monitoring platform presents monitoring images through a Web interface with a B / S architecture and has real-time alarm, video monitoring, video playback and historical alarm query functions; The industrial-grade ring network switch is used to establish a stable communication channel between the fire monitoring equipment and the integrated monitoring platform to achieve high-bandwidth, low-latency data transmission.

2. According to the fire warning system of claim 1, the integrated monitoring platform also includes an alarm module. When the fire monitoring equipment detects that the temperature or smoke exceeds a preset threshold, the alarm module is used to generate alarm information including the location and time of the fire, display the alarm information through real-time pop-up windows and page scrolling broadcasts, and push the alarm information to management personnel.

3. The fire warning system according to claim 2, characterized in that: The pop-up window interface of the alarm module has a split-screen display function, where: The left half displays in real time a screenshot of a suspected fire obtained by the fire monitoring device, including visible light image data, for preliminary display of the suspected fire; The right half displays the current monitoring screen of the fire monitoring device in real time, which is convenient for users to verify the fire information through real-time video; The displayed alarm information also includes alarm time, alarm level, alarm location, temperature and smoke concentration data, so that users can comprehensively judge the fire level.

4. The fire warning system according to claim 1, characterized in that: The integrated monitoring platform also includes a video playback module, wherein: The video playback module is used to call historical video data related to the fire situation so that the user can select a specific date and time period for playback; The video playback module supports playback speed adjustment to facilitate fire source tracing and analysis afterwards.

5. The fire warning system according to claim 1, characterized in that: The integrated monitoring platform also includes a real-time video monitoring module, wherein: The real-time video monitoring module has a PTZ control function, which supports users to click on the fire monitoring equipment at the corresponding point to view the real-time monitoring screen; The real-time video monitoring module supports users to adjust and zoom the monitoring screen up, down, left, and right, and select single-screen, four-screen, nine-screen and sixteen-screen modes in the split screen; The real-time video monitoring module supports users to remotely adjust the shooting angle and focal length of the fire monitoring equipment through pan-tilt control. The control accuracy is adjustable from 1 to 7 levels, which can meet the needs of multi-area and multi-directional fire monitoring.

6. The fire warning system according to claim 1, characterized in that: The integrated monitoring platform includes a false alarm filtering module, wherein: The false alarm filtering module performs secondary analysis and processing on the fire information based on multi-dimensional data, filters non-fire features through a false alarm screening mechanism, and records confirmed fire alarm information; The false alarm filtering module supports manual review, allowing users to confirm or cancel alarms in historical alarm records.

7. The fire warning system according to claim 1, characterized in that: The fire monitoring equipment is used for: Obtain visible light video stream data and real-time temperature data of the target area; Detecting fire characteristics in the visible light video stream data according to a fire monitoring model, and obtaining temperature characteristics according to the real-time temperature data; Real-time fire information is generated based on the detected fire characteristics and the obtained temperature data, and sent to the integrated monitoring platform.

8. The fire warning system according to claim 7, characterized in that: The fire monitoring equipment is also used for: By analyzing the light and weather conditions of the current environment in real time, the detection parameters of the fire monitoring model are autonomously adjusted; The fire monitoring model is regularly updated according to the accumulated detection data to enhance the adaptability and fire detection accuracy of the fire monitoring equipment in different application scenarios, wherein the fire monitoring model has a multi-layer neural network structure and can continuously optimize the identification parameters of fire characteristics through historical alarm data and environmental parameters; Providing update notifications for the fire monitoring model facilitates system maintenance personnel to manage the frequency and conditions of model updates.

9. The fire warning system according to claim 1, characterized in that: The industrial ring network switch has a link redundancy function and can automatically switch to a backup link when any node fails, ensuring continuous transmission of the video stream; The industrial ring network switch supports STP / RSTP protocol; The industrial-grade ring network switch adopts multi-mode / single-mode optical fiber transmission, supports Gigabit Ethernet, and meets the needs of long-distance data transmission.

Images