Building fire alarm dangerous case early warning method and system based on Internet of Things

Abstract

The invention provides a building fire alarm dangerous case early warning method and system based on the Internet of Things, and the method comprises the steps: recognizing a first type of sensing equipment in a detection operation abnormal state based on the real-time detection data of the first type of sensing equipment subordinate to the Internet of Things, and determining a key detection region in a building based on the detection range of the first type of sensing equipment in the building, performing identification and calibration in an area which cannot be normally and continuously detected due to abnormal work of the first type of sensing equipment in the building; based on the spatial physical characteristics of the key detection area, determining a second type of sensing equipment capable of performing live-action detection so as to determine heat source characteristic information in the building, and accurately identifying a fire alarm dangerous case source in the building; based on the heat source characteristic information, the fire behavior change trend in the building is predicted, so that an instruction is sent to the alarm device subordinate to the Internet of Things and alarm operation is performed, fire alarm dangerous case false alarm is effectively avoided, and the early warning reliability and accuracy of the Internet of Things to the building fire alarm dangerous case are improved.

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things, and in particular to a building fire alarm hazard early warning method and system based on Internet of Things. Background Art

[0002] Commercial buildings such as office buildings and shopping malls have complex internal structures, and the fire safety requirements for commercial buildings are high. Not only do commercial buildings need to be equipped with sufficient and reliable fire safety passages and fire-fighting equipment, but also the building materials inside commercial buildings must be clearly specified. Internet of Things technology is also widely used in fire protection work in commercial buildings. Existing technologies use the Internet of Things to centrally control all sensor devices and alarm devices inside commercial buildings, so that when a fire occurs inside a commercial building, the fire can be accurately located and the alarm can be notified in a timely and rapid manner. At present, different types of sensor devices inside the Internet of Things operate independently. When any sensor device detects a fire-related state, it will immediately trigger the alarm device to work. This method can maximize the efficiency of fire warning; however, if the alarm operation is directly performed based on the detection result of only one sensor device, false alarms are likely to occur. When the performance of the sensor device ages, the frequency of false alarms in the Internet of Things will increase significantly, reducing the reliability and accuracy of the Internet of Things' warning of building fire dangers. Summary of the invention

[0003] The purpose of the present invention is to provide a building fire hazard warning method and system based on the Internet of Things. Based on the real-time detection data of the first type of sensor equipment under the Internet of Things, the first type of sensor equipment in an abnormal detection operation state is identified, and based on its detection range inside the building, the key detection area inside the building is determined, and the area inside the building that cannot be normally and continuously detected due to the abnormal operation of the first type of sensor equipment is identified and calibrated; based on the spatial physical characteristics of the key detection area, the second type of sensor equipment capable of real-scene detection is determined, so as to determine the heat source characteristic information inside the building and accurately identify the source of the fire hazard inside the building; based on the heat source characteristic information, the trend of fire changes inside the building is predicted, so as to send instructions to the alarm equipment under the Internet of Things and perform alarm operations, and by screening the two types of sensor equipment to eliminate unreliable sensor equipment, effectively avoid false alarms of fire hazard, and improve the reliability and accuracy of the Internet of Things' warning of building fire hazard.

[0004] The present invention is achieved through the following technical solutions:

[0005] The building fire alarm danger early warning method based on the Internet of Things includes:

[0006] Acquire the real-time detection data of all first-category sensing devices under the Internet of Things inside the building, analyze the real-time detection data, and identify all first-category sensing devices that are currently in an abnormal detection operation state; determine the key detection area inside the building based on the detection range of all first-category sensing devices that are currently in an abnormal detection operation state inside the building;

[0007] Based on the spatial physical characteristics of the key detection area, determine all the second-type sensor devices of the Internet of Things subordinates that can cooperate in real-time real-scene detection; analyze the real-scene detection data from the second-type sensor devices to determine the heat source characteristic information inside the building;

[0008] Based on the heat source characteristic information, the fire situation change trend of the internal environment of the building is predicted to obtain a fire situation change prediction result; based on the fire situation change prediction result, an instruction is sent to the alarm device under the Internet of Things, so that the alarm device performs a corresponding alarm operation.

[0009] Optionally, real-time detection data of all first-category sensing devices under the Internet of Things inside the building are obtained, the real-time detection data are analyzed, and all first-category sensing devices that are currently in an abnormal detection operation state are identified; based on the detection range of all first-category sensing devices that are currently in an abnormal detection operation state inside the building, a key detection area inside the building is determined, including:

[0010] Monitor all smoke sensor devices under the Internet of Things inside the building to obtain real-time smoke concentration detection data of all smoke sensor devices within a preset time interval; identify abnormal data components of the real-time smoke concentration detection data based on the detection sensitivity of the smoke sensor devices to determine the abnormal data proportion of the real-time smoke concentration detection data;

[0011] Based on the abnormal data ratio deviation information corresponding to any two adjacent smoke sensor devices among all the smoke sensor devices, all the smoke sensor devices that are currently in an abnormal detection operation state are identified;

[0012] Based on the detection coverage space range of all smoke sensing devices currently in abnormal detection operation state inside the building, the detection failure area of ​​all smoke sensing devices inside the building is determined as the key detection area.

[0013] Optionally, adjusting the time length of the reference time interval corresponding to each smoke sensor device based on the detection sensitivity of the smoke sensor device, acquiring a time interval corresponding to the adjusted time length, and the time interval corresponding to the adjusted time length is the preset time interval, including:

[0014] Extract the detection sensitivity of each smoke sensing device;

[0015] Obtaining a sensitivity coefficient corresponding to the smoke sensor device network according to the detection sensitivity of each smoke sensor device;

[0016] The sensitivity coefficient is obtained by the following formula:

[0017]

[0018] Where L represents the sensitivity coefficient; n represents the total number of smoke sensor devices; M b represents the standard deviation of the sensitivity of n smoke sensing devices; M i represents the sensitivity corresponding to the i-th smoke sensor; T i represents the length of the time interval corresponding to the i-th smoke sensor; M f Indicates the preset sensitivity reference value; T f Indicates the preset time length reference value; T b represents the standard deviation of the time length of n smoke sensor devices;

[0019] The sensitivity coefficient is combined with the detection sensitivity of each smoke sensor device to obtain a duration adjustment coefficient corresponding to each smoke sensor;

[0020] The duration adjustment coefficient is obtained by the following formula:

[0021]

[0022] Wherein, f represents the duration adjustment coefficient; L represents the sensitivity coefficient; M represents the detection sensitivity of each smoke sensor device; T represents the time length of the time interval of each smoke sensor device; T b represents the standard deviation of the time length of n smoke sensor devices; M b represents the standard deviation of the sensitivity of n smoke sensing devices; M max Indicates the maximum sensitivity of n smoke sensing devices;

[0023] Obtaining the adjusted time length corresponding to each smoke sensor device using the time length adjustment coefficient corresponding to each smoke sensor device;

[0024] The adjusted time length is obtained by the following formula:

[0025]

[0026] Among them, T t represents the adjusted time length corresponding to each smoke sensor device; T represents the time length of the time interval of each smoke sensor device; f represents the time length adjustment coefficient;

[0027] The adjusted time length is projected onto the reference time interval corresponding to each smoke sensor device, and the reference time interval is adjusted to obtain the preset time area corresponding to each smoke sensor device.

[0028] Optionally, based on the spatial physical characteristics of the key detection area, all second-type sensor devices of the Internet of Things subordinates that can cooperate in real-time real-scene detection are determined; and the real-scene detection data from the second-type sensor devices are analyzed to determine the heat source characteristic information inside the building, including:

[0029] Based on the shape and size of the three-dimensional space range of the key detection area, estimate the shooting blind spot feature information of all the camera sensor devices installed adjacent to the key detection area under the Internet of Things; based on the shooting blind spot feature information, select all the camera sensor devices that can cooperate in real-time real-scene detection of the key detection area from all the camera sensor devices installed adjacent to the key detection area;

[0030] The real-scene image data from the camera sensor device is identified to determine the heat source distribution position, heat source temperature and heat source size inside the key detection area, which are used as the heat source characteristic information inside the building.

[0031] Optionally, based on the heat source characteristic information, predicting the fire situation change trend of the internal environment of the building to obtain a fire situation change prediction result; based on the fire situation change prediction result, sending an instruction to the alarm device under the Internet of Things, so that the alarm device performs a corresponding alarm operation, including:

[0032] Based on the heat source distribution position, heat source temperature and heat source size inside the key detection area contained in the heat source characteristic information and the air flow state information inside the key detection area, the fire spread trend of the key detection area is predicted to obtain the fire spread speed and fire spread direction inside the key detection area as the fire change prediction result;

[0033] Based on the fire spreading speed and the fire spreading direction, the sub-area inside the building that is first affected by the fire is determined; and based on the distribution positions of the sub-areas inside the building, a matching alarm device is selected from within the Internet of Things, and an instruction is sent to the matching alarm device, so that the alarm device performs a sound alarm operation and / or a light alarm operation.

[0034] Building fire alarm warning system based on the Internet of Things, including:

[0035] The first-category sensor device screening module is used to obtain the real-time detection data of all the first-category sensor devices under the Internet of Things inside the building, analyze the real-time detection data, and identify all the first-category sensor devices that are currently in an abnormal detection operation state;

[0036] A key detection area determination module, configured to determine a key detection area inside the building based on the detection range of all first-category sensing devices that are currently in an abnormal detection operation state inside the building;

[0037] A second-category sensor device screening module, for determining all second-category sensor devices of the Internet of Things subordinates that can cooperate in real-time real-scene detection based on the spatial physical characteristics of the key detection area;

[0038] A heat source feature recognition module, used to analyze the real-scene detection data from the second type of sensing equipment to determine the heat source feature information inside the building;

[0039] A fire situation change prediction module, used to predict the fire situation change trend of the internal environment of the building based on the heat source characteristic information, and obtain a fire situation change prediction result;

[0040] The alarm operation control module is used to send instructions to the alarm device under the Internet of Things based on the fire situation change prediction result, so that the alarm device performs corresponding alarm operations.

[0041] Optionally, the first-category sensor device screening module is used to obtain real-time detection data of all first-category sensor devices under the Internet of Things inside the building, analyze the real-time detection data, and identify all first-category sensor devices that are currently in an abnormal detection operation state, including:

[0042] Monitor all smoke sensor devices under the Internet of Things inside the building to obtain real-time smoke concentration detection data of all smoke sensor devices within a preset time interval; identify abnormal data components of the real-time smoke concentration detection data based on the detection sensitivity of the smoke sensor devices to determine the abnormal data proportion of the real-time smoke concentration detection data;

[0043] Based on the abnormal data ratio deviation information corresponding to any two adjacent smoke sensor devices among all the smoke sensor devices, all the smoke sensor devices that are currently in an abnormal detection operation state are identified;

[0044] The key detection area determination module is used to determine the key detection area inside the building based on the detection range of all first-category sensing devices that are currently in an abnormal detection operation state inside the building, including:

[0045] Based on the detection coverage space range of all smoke sensing devices currently in abnormal detection operation state inside the building, the detection failure area of ​​all smoke sensing devices inside the building is determined as the key detection area.

[0046] Optionally, adjusting the time length of the reference time interval corresponding to each smoke sensor device based on the detection sensitivity of the smoke sensor device, acquiring a time interval corresponding to the adjusted time length, and the time interval corresponding to the adjusted time length is the preset time interval, including:

[0047] Extract the detection sensitivity of each smoke sensing device;

[0048] Obtaining a sensitivity coefficient corresponding to the smoke sensor device network according to the detection sensitivity of each smoke sensor device;

[0049] The sensitivity coefficient is obtained by the following formula:

[0050]

[0051] Where L represents the sensitivity coefficient; n represents the total number of smoke sensor devices; M b represents the standard deviation of the sensitivity of n smoke sensing devices; M i represents the sensitivity corresponding to the i-th smoke sensor; T i represents the length of the time interval corresponding to the i-th smoke sensor; M f Indicates the preset sensitivity reference value; T f Indicates the preset time length reference value; T b represents the standard deviation of the time length of n smoke sensor devices;

[0052] The sensitivity coefficient is combined with the detection sensitivity of each smoke sensor device to obtain a duration adjustment coefficient corresponding to each smoke sensor;

[0053] The duration adjustment coefficient is obtained by the following formula:

[0054]

[0055] Wherein, f represents the duration adjustment coefficient; L represents the sensitivity coefficient; M represents the detection sensitivity of each smoke sensor device; T represents the time length of the time interval of each smoke sensor device; T b represents the standard deviation of the time length of n smoke sensor devices; M b represents the standard deviation of the sensitivity of n smoke sensing devices; M max Indicates the maximum sensitivity of n smoke sensing devices;

[0056] Obtaining the adjusted time length corresponding to each smoke sensor device using the time length adjustment coefficient corresponding to each smoke sensor device;

[0057] The adjusted time length is obtained by the following formula:

[0058]

[0059] Among them, T t represents the adjusted time length corresponding to each smoke sensor device; T represents the time length of the time interval of each smoke sensor device; f represents the time length adjustment coefficient;

[0060] The adjusted time length is projected onto the reference time interval corresponding to each smoke sensor device, and the reference time interval is adjusted to obtain the preset time area corresponding to each smoke sensor device.

[0061] Optionally, the second-category sensor device screening module is used to determine all second-category sensor devices of the Internet of Things subordinates that can cooperate in real-time real-scene detection based on the spatial physical characteristics of the key detection area, including:

[0062] Based on the shape and size of the three-dimensional space range of the key detection area, estimate the shooting blind spot feature information of all the camera sensor devices installed adjacent to the key detection area under the Internet of Things; based on the shooting blind spot feature information, select all the camera sensor devices that can cooperate in real-time real-scene detection of the key detection area from all the camera sensor devices installed adjacent to the key detection area;

[0063] The heat source feature recognition module is used to analyze the real-scene detection data from the second type of sensor equipment to determine the heat source feature information inside the building, including:

[0064] The real-scene image data from the camera sensor device is identified to determine the heat source distribution position, heat source temperature and heat source size inside the key detection area, which are used as the heat source characteristic information inside the building.

[0065] Optionally, the fire situation change prediction module is used to predict the fire situation change trend of the internal environment of the building based on the heat source characteristic information to obtain a fire situation change prediction result, including:

[0066] Based on the heat source distribution position, heat source temperature and heat source size inside the key detection area contained in the heat source characteristic information and the air flow state information inside the key detection area, the fire spread trend of the key detection area is predicted to obtain the fire spread speed and fire spread direction inside the key detection area as the fire change prediction result;

[0067] The alarm operation control module is used to send instructions to the alarm device under the Internet of Things based on the fire situation change prediction result, so that the alarm device performs corresponding alarm operations, including:

[0068] Based on the fire spreading speed and the fire spreading direction, the sub-area inside the building that is first affected by the fire is determined; and based on the distribution positions of the sub-areas inside the building, a matching alarm device is selected from within the Internet of Things, and an instruction is sent to the matching alarm device, so that the alarm device performs a sound alarm operation and / or a light alarm operation.

[0069] Compared with the prior art, the present invention has the following beneficial effects:

[0070] The Internet of Things-based building fire hazard warning method and system provided in the present application is based on the real-time detection data of the first type of sensor equipment under the Internet of Things, identifies the first type of sensor equipment in an abnormal detection operation state, and determines the key detection area inside the building based on its detection range inside the building, and identifies and calibrates the area inside the building that cannot be normally and continuously detected due to the abnormal operation of the first type of sensor equipment; based on the spatial physical characteristics of the key detection area, determines the second type of sensor equipment that can perform real-scene detection, thereby determining the heat source characteristic information inside the building, and accurately identifying the source of the fire hazard inside the building; based on the heat source characteristic information, predicts the trend of fire changes in the building, thereby sending instructions to the alarm equipment under the Internet of Things and performing alarm operations, and by screening the two types of sensor equipment to eliminate unreliable sensor equipment, effectively avoids false alarms of fire hazard situations, and improves the reliability and accuracy of the Internet of Things' warning of building fire hazard situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. 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 creative work. Among them:

[0072] Figure 1 A schematic flow chart of the method for early warning of building fire danger based on the Internet of Things provided by the present invention.

[0073] Figure 2 This is a schematic structural diagram of the Internet of Things-based building fire alarm warning system provided by the present invention. DETAILED DESCRIPTION

[0074] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings. It is to be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for ease of description, only some structures related to the present application are shown in the accompanying drawings, rather than all structures. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0075] The terms "including" and "having" and any variations thereof in this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0076] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0077] See also Figure 1 As shown, an embodiment of the present application provides a building fire alarm danger warning method based on the Internet of Things. The building fire alarm danger warning method based on the Internet of Things includes:

[0078] Acquire the real-time detection data of all first-category sensor devices under the Internet of Things inside the building, analyze the real-time detection data, and identify all first-category sensor devices that are currently in an abnormal detection operation state; determine the key detection area inside the building based on the detection range of all first-category sensor devices that are currently in an abnormal detection operation state inside the building;

[0079] Based on the spatial physical characteristics of the key detection area, determine all the second-category sensing devices under the Internet of Things that can cooperate in real-time real-scene detection; analyze the real-scene detection data from the second-category sensing devices to determine the characteristic information of the heat source inside the building;

[0080] Based on the heat source characteristic information, the fire change trend of the internal environment of the building is predicted to obtain a fire change prediction result; based on the fire change prediction result, an instruction is sent to the alarm device under the Internet of Things, so that the alarm device performs a corresponding alarm operation.

[0081] The beneficial effects of the above embodiments are as follows: the Internet of Things-based building fire hazard warning method identifies the first type of sensor equipment in an abnormal detection operation state based on the real-time detection data of the first type of sensor equipment under the Internet of Things, and determines the key detection area inside the building based on its detection range inside the building, and identifies and calibrates the area inside the building that cannot be normally and continuously detected due to the abnormal operation of the first type of sensor equipment; based on the spatial physical characteristics of the key detection area, determines the second type of sensor equipment that can perform real-scene detection, thereby determining the heat source characteristic information inside the building, and accurately identifying the source of the fire hazard inside the building; based on the heat source characteristic information, predicts the trend of fire changes inside the building, thereby sending instructions to the alarm equipment under the Internet of Things and performing alarm operations, and by screening the two types of sensor equipment to eliminate unreliable sensor equipment, effectively avoids false alarms of fire hazards, and improves the reliability and accuracy of the Internet of Things' warning of building fire hazards.

[0082] In another embodiment, real-time detection data of all first-category sensing devices under the Internet of Things in the building are obtained, and the real-time detection data are analyzed to identify all first-category sensing devices that are currently in an abnormal detection operation state; based on the detection range of all first-category sensing devices that are currently in an abnormal detection operation state in the building, a key detection area in the building is determined, including:

[0083] Monitor all smoke sensor devices under the Internet of Things inside the building to obtain real-time smoke concentration detection data of all smoke sensor devices within a preset time interval; identify abnormal data components of the real-time smoke concentration detection data based on the detection sensitivity of the smoke sensor devices to determine the abnormal data proportion of the real-time smoke concentration detection data;

[0084] Based on the abnormal data ratio deviation information corresponding to any two adjacent smoke sensor devices among all the smoke sensor devices, all the smoke sensor devices that are currently in an abnormal detection operation state are identified;

[0085] Based on the detection coverage space range of all smoke sensing devices currently in abnormal detection operation state inside the building, the detection failure area of ​​all smoke sensing devices inside the building is determined as the key detection area.

[0086] The beneficial effect of the above embodiment is that a number of smoke sensing devices (i.e., first-class sensing devices) are distributedly installed at different floors and different locations inside the building, and each smoke sensing device can detect the smoke concentration data at its location and within the adjacent space, and all smoke sensors. Under normal circumstances, when the smoke concentration data detected by the smoke sensing device indicates that the smoke concentration in its corresponding detection range exceeds the preset concentration threshold, it is determined that a fire event has occurred in the detection range. However, in actual operation, as the working time of the smoke sensing device increases, the smoke sensing device will inevitably fail and have other problems, so that the detection sensitivity of the smoke sensing device will deteriorate, causing the smoke sensing device to misjudge the trigger signal that does not belong to the smoke generation as a smoke-related signal, so that the smoke concentration detection data generated by the smoke sensing device contains erroneous data. In order to accurately identify smoke sensor devices with false detection or detection errors, all smoke sensor devices under the Internet of Things are monitored to obtain real-time smoke concentration detection data generated by each smoke sensor device within a preset time interval; then, based on the nominal detection sensitivity of the smoke sensor device itself (that is, the detection sensitivity marked on the smoke sensor device when leaving the factory), each detection sub-data under the real-time smoke concentration detection data is identified. If the detection sub-data does not match the nominal detection sensitivity, the detection sub-data is determined as an abnormal data component; otherwise, the detection sub-data is not determined as an abnormal data component, and the abnormal data proportion of the real-time smoke concentration detection data is determined. All smoke sensor devices installed inside a building usually have the same working performance, that is, when all smoke sensor devices are in an ideal state of normal operation, the difference between the abnormal data ratios of any two adjacent smoke sensor devices should be small (because the detection coverage of the two is similar). If one of the smoke sensor devices is in an abnormal detection operation state, there will be a large difference in the abnormal data ratio between it and the adjacent smoke sensor device in normal operation. For this reason, based on the abnormal data ratio deviation information corresponding to any two adjacent smoke sensor devices among all smoke sensor devices, the smoke sensor device with a large abnormal data ratio deviation is determined to be currently in an abnormal detection operation state, thereby improving the accuracy of abnormal state recognition of the smoke sensor device. In addition, all smoke sensor devices that are currently in an abnormal detection operation state are spatially combined in their respective detection coverage space ranges inside the building to determine the detection failure area of ​​all smoke sensor devices inside the building, so as to facilitate subsequent detection and identification of the second type of sensor devices only in the detection failure area.

[0087] In another embodiment, the time length of the reference time interval corresponding to each smoke sensor device is adjusted based on the detection sensitivity of the smoke sensor device, and the time interval corresponding to the adjusted time length is obtained, and the time interval corresponding to the adjusted time length is the preset time interval, including:

[0088] Extract the detection sensitivity of each smoke sensing device;

[0089] Obtaining a sensitivity coefficient corresponding to the smoke sensor device network according to the detection sensitivity of each smoke sensor device;

[0090] The sensitivity coefficient is obtained by the following formula:

[0091]

[0092] Where L represents the sensitivity coefficient; n represents the total number of smoke sensor devices; M b represents the standard deviation of the sensitivity of n smoke sensing devices; M i represents the sensitivity corresponding to the i-th smoke sensor; T i represents the length of the time interval corresponding to the i-th smoke sensor; M f Indicates the preset sensitivity reference value; T f Indicates the preset time length reference value; T b represents the standard deviation of the time length of n smoke sensor devices;

[0093] The sensitivity coefficient is combined with the detection sensitivity of each smoke sensor device to obtain a duration adjustment coefficient corresponding to each smoke sensor;

[0094] The duration adjustment coefficient is obtained by the following formula:

[0095]

[0096] Wherein, f represents the duration adjustment coefficient; L represents the sensitivity coefficient; M represents the detection sensitivity of each smoke sensor device; T represents the time length of the time interval of each smoke sensor device; T b represents the standard deviation of the time length of n smoke sensor devices; M b represents the standard deviation of the sensitivity of n smoke sensing devices; M max Indicates the maximum sensitivity of n smoke sensing devices;

[0097] Obtaining the adjusted time length corresponding to each smoke sensor device using the time length adjustment coefficient corresponding to each smoke sensor device;

[0098] The adjusted time length is obtained by the following formula:

[0099]

[0100] Among them, T trepresents the adjusted time length corresponding to each smoke sensor device; T represents the time length of the time interval of each smoke sensor device; f represents the time length adjustment coefficient;

[0101] The adjusted time length is projected onto the reference time interval corresponding to each smoke sensor device, and the reference time interval is adjusted to obtain the preset time area corresponding to each smoke sensor device.

[0102] The beneficial effect of the above embodiment is that the technical solution can dynamically adjust the corresponding time interval of each smoke sensor device according to the detection sensitivity of each smoke sensor device. This means that for a smoke sensor device with a higher detection sensitivity, its time interval may be shortened accordingly, because high sensitivity means that it can respond to smoke changes more quickly. On the contrary, for a smoke sensor device with a lower detection sensitivity, its time interval may be extended to ensure sufficient detection time. This adaptive adjustment helps to improve the efficiency and accuracy of the entire smoke sensor device network. By calculating the sensitivity coefficient and the time adjustment coefficient, the scheme can comprehensively consider the performance differences of all smoke sensor devices and optimize the time interval of each device accordingly. This helps to balance the sensitivity and response time of the entire network, thereby improving the overall performance of the network. Since the time interval is adjusted according to the actual detection sensitivity of the smoke sensor device, the scheme can reduce false alarms or missed alarms caused by improper time interval settings. This helps to improve the accuracy of smoke detection, thereby more effectively protecting people's lives and property. The technical solution not only takes into account the detection sensitivity of the smoke sensor device, but also takes into account factors such as the standard deviation of the time length, so that the system can be flexibly adjusted according to actual conditions. This flexibility helps to meet the smoke detection needs in different scenarios and improve the adaptability and reliability of the system. By automatically adjusting the time interval of each smoke sensor device, the solution reduces the need for manual intervention and reduces management costs. At the same time, since the adjustment of the time interval is based on the performance of the device and the overall performance of the network, it also improves the scientificity and effectiveness of management.

[0103] In summary, this technical solution optimizes and improves the network performance of smoke sensor equipment by adaptively adjusting the time interval based on the detection sensitivity of the smoke sensor equipment, improves the accuracy and efficiency of smoke detection, enhances the flexibility and reliability of the system, and simplifies management operations.

[0104] In another embodiment, based on the spatial physical characteristics of the key detection area, all second-type sensor devices of the Internet of Things that can cooperate in real-time real-scene detection are determined; the real-scene detection data from the second-type sensor devices are analyzed to determine the heat source characteristic information inside the building, including:

[0105] Based on the shape and size of the three-dimensional space range of the key detection area, estimate the shooting blind spot feature information of the key detection area of ​​all the camera sensor devices under the Internet of Things installed adjacent to the key detection area; based on the shooting blind spot feature information, select all the camera sensor devices that can cooperate in real-time real-scene detection of the key detection area from all the camera sensor devices installed adjacent to the key detection area;

[0106] The real-scene image data from the camera sensor device is identified to determine the heat source distribution position, heat source temperature and heat source size within the key detection area, which is used as the heat source characteristic information inside the building.

[0107] The beneficial effect of the above embodiment is that the key detection area is the detection coverage space range of all smoke sensor devices in the building that are in an abnormal detection operation state. In order to accurately shoot the detection coverage space range globally through the camera sensor device (i.e., the second type of sensor device), the three-dimensional spatial range shape and size of the key detection area are combined with the installation position of the corresponding camera sensor device to estimate the shooting blind area feature information of the key detection area of ​​all camera sensor devices under the Internet of Things installed adjacent to the key detection area, wherein the shooting blind area feature information can be but is not limited to the shooting blind area range value (such as area value). Then, the shooting blind area feature information is compared with the threshold value, and all camera sensor devices that can cooperate in real-time real-scene detection of the key detection area are selected from all camera sensor devices installed adjacent to the key detection area. For example, if the shooting blind area range value is less than the preset range value, the corresponding camera sensor device is determined as a camera sensor device that can cooperate in real-time real-scene detection of the key detection area, which can reduce the probability of missing incomplete shooting of the key detection area. The spectral distribution and pixel chromaticity distribution of the real-scene image data from the camera sensor equipment are also identified to determine the heat source distribution position, heat source temperature and heat source size within the key detection area. This is used as the heat source characteristic information inside the building, providing a basic basis for subsequent judgment of the fire trend inside the building.

[0108] In another embodiment, based on the heat source characteristic information, the fire change trend of the internal environment of the building is predicted to obtain a fire change prediction result; based on the fire change prediction result, an instruction is sent to the alarm device under the Internet of Things, so that the alarm device performs a corresponding alarm operation, including:

[0109] Based on the heat source distribution position, heat source temperature and heat source size within the key detection area and the air flow state information within the key detection area contained in the heat source characteristic information, the fire spread trend of the key detection area is predicted to obtain the fire spread speed and fire spread direction within the key detection area as the fire change prediction result;

[0110] Based on the fire spread speed and the fire spread direction, the sub-area inside the building that is first affected by the fire is determined; and based on the distribution position of the sub-area inside the building, a matching alarm device is selected from within the Internet of Things, and an instruction is sent to the matching alarm device, so that the alarm device performs a sound alarm operation and / or a light alarm operation.

[0111] The beneficial effect of the above embodiment is that when there are heat sources such as tiny flames in the internal environment of a building, the air flow state information such as the air flow speed and direction of the internal environment of the building will directly affect the diffusion speed and direction of the heat source. For this reason, the heat source distribution position, heat source temperature and heat source size inside the key detection area contained in the heat source characteristic information and the air flow state information inside the key detection area are combined to predict the fire spread trend in the key detection area, and the fire spread speed and fire spread direction inside the key detection area are obtained, which are used as the fire change prediction result, wherein the fire spread trend prediction can be achieved through a convolutional neural network model, which belongs to the conventional technical means in this field and will not be described in detail here. In addition, based on the fire spread speed and the fire spread direction, the sub-area inside the building that is first affected by the fire is determined, that is, the sub-area that the fire inside the building reaches first during the diffusion process is determined. Based on the distribution location of the sub-area inside the building, the alarm device installed inside the sub-area (i.e., the matching alarm device) is selected from the Internet of Things, and an instruction is sent to the matching alarm device, so that the alarm device performs a sound alarm operation and / or a light alarm operation, thereby improving the reliability and accuracy of the Internet of Things' early warning of building fire hazards.

[0112] See also Figure 2 As shown, an embodiment of the present application provides a building fire alarm danger warning system based on the Internet of Things. The building fire alarm danger warning system based on the Internet of Things includes:

[0113] The first-category sensor device screening module is used to obtain the real-time detection data of all the first-category sensor devices under the Internet of Things inside the building, analyze the real-time detection data, and identify all the first-category sensor devices that are currently in an abnormal detection operation state;

[0114] A key detection area determination module, used to determine the key detection area inside the building based on the detection range of all first-category sensing devices currently in an abnormal detection operation state inside the building;

[0115] The second type of sensor device screening module is used to determine all the second type of sensor devices of the IoT subordinate that can cooperate in real-time real-scene detection based on the spatial physical characteristics of the key detection area;

[0116] A heat source feature recognition module is used to analyze the real-scene detection data from the second type of sensing equipment to determine the heat source feature information inside the building;

[0117] A fire situation change prediction module is used to predict the fire situation change trend of the internal environment of the building based on the heat source characteristic information to obtain a fire situation change prediction result;

[0118] The alarm operation control module is used to send instructions to the alarm device under the Internet of Things based on the fire situation change prediction result, so that the alarm device performs corresponding alarm operations.

[0119] The beneficial effects of the above embodiments are as follows: the building fire hazard warning system based on the Internet of Things identifies the first type of sensor equipment in an abnormal detection operation state based on the real-time detection data of the first type of sensor equipment under the Internet of Things, and determines the key detection area inside the building based on its detection range inside the building, and identifies and calibrates the area inside the building that cannot be continuously detected normally due to the abnormal operation of the first type of sensor equipment; based on the spatial physical characteristics of the key detection area, determines the second type of sensor equipment that can perform real-scene detection, thereby determining the heat source characteristic information inside the building, and accurately identifying the source of the fire hazard inside the building; based on the heat source characteristic information, predicts the trend of fire changes in the building, thereby sending instructions to the alarm equipment under the Internet of Things and performing alarm operations, and by screening the two types of sensor equipment to eliminate unreliable sensor equipment, effectively avoids false alarms of fire hazards, and improves the reliability and accuracy of the Internet of Things' warning of building fire hazards.

[0120] In another embodiment, the first-category sensor device screening module is used to obtain real-time detection data of all first-category sensor devices under the Internet of Things inside the building, analyze the real-time detection data, and identify all first-category sensor devices that are currently in an abnormal detection operation state, including:

[0121] Monitor all smoke sensor devices under the Internet of Things inside the building to obtain real-time smoke concentration detection data of all smoke sensor devices within a preset time interval; identify abnormal data components of the real-time smoke concentration detection data based on the detection sensitivity of the smoke sensor devices to determine the abnormal data proportion of the real-time smoke concentration detection data;

[0122] Based on the abnormal data ratio deviation information corresponding to any two adjacent smoke sensor devices among all the smoke sensor devices, all the smoke sensor devices that are currently in an abnormal detection operation state are identified;

[0123] The key detection area determination module is used to determine the key detection area inside the building based on the detection range of all first-class sensor devices currently in the abnormal detection operation state inside the building, including:

[0124] Based on the detection coverage space range of all smoke sensing devices currently in abnormal detection operation state inside the building, the detection failure area of ​​all smoke sensing devices inside the building is determined as the key detection area.

[0125] The beneficial effect of the above embodiment is that a number of smoke sensing devices (i.e., first-class sensing devices) are distributedly installed at different floors and different locations inside the building, and each smoke sensing device can detect the smoke concentration data at its location and within the adjacent space, and all smoke sensors. Under normal circumstances, when the smoke concentration data detected by the smoke sensing device indicates that the smoke concentration in its corresponding detection range exceeds the preset concentration threshold, it is determined that a fire event has occurred in the detection range. However, in actual operation, as the working time of the smoke sensing device increases, the smoke sensing device will inevitably fail and have other problems, so that the detection sensitivity of the smoke sensing device will deteriorate, causing the smoke sensing device to misjudge the trigger signal that does not belong to the smoke generation as a smoke-related signal, so that the smoke concentration detection data generated by the smoke sensing device contains erroneous data. In order to accurately identify smoke sensor devices with false detection or detection errors, all smoke sensor devices under the Internet of Things are monitored to obtain real-time smoke concentration detection data generated by each smoke sensor device within a preset time interval; then, based on the nominal detection sensitivity of the smoke sensor device itself (that is, the detection sensitivity marked on the smoke sensor device when leaving the factory), each detection sub-data under the real-time smoke concentration detection data is identified. If the detection sub-data does not match the nominal detection sensitivity, the detection sub-data is determined as an abnormal data component; otherwise, the detection sub-data is not determined as an abnormal data component, and the abnormal data proportion of the real-time smoke concentration detection data is determined. All smoke sensor devices installed inside a building usually have the same working performance, that is, when all smoke sensor devices are in an ideal state of normal operation, the difference between the abnormal data ratios of any two adjacent smoke sensor devices should be small (because the detection coverage of the two is similar). If one of the smoke sensor devices is in an abnormal detection operation state, there will be a large difference in the abnormal data ratio between it and the adjacent smoke sensor device in normal operation. For this reason, based on the abnormal data ratio deviation information corresponding to any two adjacent smoke sensor devices among all smoke sensor devices, the smoke sensor device with a large abnormal data ratio deviation is determined to be currently in an abnormal detection operation state, thereby improving the accuracy of abnormal state recognition of the smoke sensor device. In addition, all smoke sensor devices that are currently in an abnormal detection operation state are spatially combined in their respective detection coverage space ranges inside the building to determine the detection failure area of ​​all smoke sensor devices inside the building, so as to facilitate subsequent detection and identification of the second type of sensor devices only in the detection failure area.

[0126] In another embodiment, the time length of the reference time interval corresponding to each smoke sensor device is adjusted based on the detection sensitivity of the smoke sensor device, and the time interval corresponding to the adjusted time length is obtained, and the time interval corresponding to the adjusted time length is the preset time interval, including:

[0127] Extract the detection sensitivity of each smoke sensing device;

[0128] Obtaining a sensitivity coefficient corresponding to the smoke sensor device network according to the detection sensitivity of each smoke sensor device;

[0129] The sensitivity coefficient is obtained by the following formula:

[0130]

[0131] Where L represents the sensitivity coefficient; n represents the total number of smoke sensor devices; M b represents the standard deviation of the sensitivity of n smoke sensing devices; M i represents the sensitivity corresponding to the i-th smoke sensor; T i represents the length of the time interval corresponding to the i-th smoke sensor; M f Indicates the preset sensitivity reference value; T f Indicates the preset time length reference value; T b represents the standard deviation of the time length of n smoke sensor devices;

[0132] The sensitivity coefficient is combined with the detection sensitivity of each smoke sensor device to obtain a duration adjustment coefficient corresponding to each smoke sensor;

[0133] The duration adjustment coefficient is obtained by the following formula:

[0134]

[0135] Wherein, f represents the duration adjustment coefficient; L represents the sensitivity coefficient; M represents the detection sensitivity of each smoke sensor device; T represents the time length of the time interval of each smoke sensor device; T b represents the standard deviation of the time length of n smoke sensor devices; M b represents the standard deviation of the sensitivity of n smoke sensing devices; M max Indicates the maximum sensitivity of n smoke sensing devices;

[0136] Obtaining the adjusted time length corresponding to each smoke sensor device using the time length adjustment coefficient corresponding to each smoke sensor device;

[0137] The adjusted time length is obtained by the following formula:

[0138]

[0139] Among them, T t represents the adjusted time length corresponding to each smoke sensor device; T represents the time length of the time interval of each smoke sensor device; f represents the time length adjustment coefficient;

[0140] The adjusted time length is projected onto the reference time interval corresponding to each smoke sensor device, and the reference time interval is adjusted to obtain the preset time area corresponding to each smoke sensor device.

[0141] The beneficial effect of the above embodiment is that the technical solution can dynamically adjust the corresponding time interval of each smoke sensor device according to the detection sensitivity of each smoke sensor device. This means that for a smoke sensor device with a higher detection sensitivity, its time interval may be shortened accordingly, because high sensitivity means that it can respond to smoke changes more quickly. On the contrary, for a smoke sensor device with a lower detection sensitivity, its time interval may be extended to ensure sufficient detection time. This adaptive adjustment helps to improve the efficiency and accuracy of the entire smoke sensor device network. By calculating the sensitivity coefficient and the time adjustment coefficient, the scheme can comprehensively consider the performance differences of all smoke sensor devices and optimize the time interval of each device accordingly. This helps to balance the sensitivity and response time of the entire network, thereby improving the overall performance of the network. Since the time interval is adjusted according to the actual detection sensitivity of the smoke sensor device, the scheme can reduce false alarms or missed alarms caused by improper time interval settings. This helps to improve the accuracy of smoke detection, thereby more effectively protecting people's lives and property. The technical solution not only takes into account the detection sensitivity of the smoke sensor device, but also takes into account factors such as the standard deviation of the time length, so that the system can be flexibly adjusted according to actual conditions. This flexibility helps to meet the smoke detection needs in different scenarios and improve the adaptability and reliability of the system. By automatically adjusting the time interval of each smoke sensor device, the solution reduces the need for manual intervention and reduces management costs. At the same time, since the adjustment of the time interval is based on the performance of the device and the overall performance of the network, it also improves the scientificity and effectiveness of management.

[0142] In summary, this technical solution optimizes and improves the network performance of smoke sensor equipment by adaptively adjusting the time interval based on the detection sensitivity of the smoke sensor equipment, improves the accuracy and efficiency of smoke detection, enhances the flexibility and reliability of the system, and simplifies management operations.

[0143] In another embodiment, the second-category sensor device screening module is used to determine all second-category sensor devices of the Internet of Things that can cooperate in real-time real-scene detection based on the spatial physical characteristics of the key detection area, including:

[0144] Based on the shape and size of the three-dimensional space range of the key detection area, estimate the shooting blind spot feature information of the key detection area of ​​all the camera sensor devices under the Internet of Things installed adjacent to the key detection area; based on the shooting blind spot feature information, select all the camera sensor devices that can cooperate in real-time real-scene detection of the key detection area from all the camera sensor devices installed adjacent to the key detection area;

[0145] The heat source feature recognition module is used to analyze the real-scene detection data from the second type of sensor equipment to determine the heat source feature information inside the building, including:

[0146] The real-scene image data from the camera sensor device is identified to determine the heat source distribution position, heat source temperature and heat source size within the key detection area, which is used as the heat source characteristic information inside the building.

[0147] The beneficial effect of the above embodiment is that the key detection area is the detection coverage space range of all smoke sensor devices in the building that are in an abnormal detection operation state. In order to accurately shoot the detection coverage space range globally through the camera sensor device (i.e., the second type of sensor device), the three-dimensional spatial range shape and size of the key detection area are combined with the installation position of the corresponding camera sensor device to estimate the shooting blind area feature information of the key detection area of ​​all camera sensor devices under the Internet of Things installed adjacent to the key detection area, wherein the shooting blind area feature information can be but is not limited to the shooting blind area range value (such as area value). Then, the shooting blind area feature information is compared with the threshold value, and all camera sensor devices that can cooperate in real-time real-scene detection of the key detection area are selected from all camera sensor devices installed adjacent to the key detection area. For example, if the shooting blind area range value is less than the preset range value, the corresponding camera sensor device is determined as a camera sensor device that can cooperate in real-time real-scene detection of the key detection area, which can reduce the probability of missing incomplete shooting of the key detection area. The spectral distribution and pixel chromaticity distribution of the real-scene image data from the camera sensor equipment are also identified to determine the heat source distribution position, heat source temperature and heat source size within the key detection area. This is used as the heat source characteristic information inside the building, providing a basic basis for subsequent judgment of the fire trend inside the building.

[0148] In another embodiment, the fire situation change prediction module is used to predict the fire situation change trend of the internal environment of the building based on the heat source characteristic information, and obtain the fire situation change prediction result, including:

[0149] Based on the heat source distribution position, heat source temperature and heat source size within the key detection area and the air flow state information within the key detection area contained in the heat source characteristic information, the fire spread trend of the key detection area is predicted to obtain the fire spread speed and fire spread direction within the key detection area as the fire change prediction result;

[0150] The alarm operation control module is used to send instructions to the alarm device under the Internet of Things based on the fire change prediction result, so that the alarm device performs corresponding alarm operations, including:

[0151] Based on the fire spread speed and the fire spread direction, the sub-area inside the building that is first affected by the fire is determined; and based on the distribution position of the sub-area inside the building, a matching alarm device is selected from within the Internet of Things, and an instruction is sent to the matching alarm device, so that the alarm device performs a sound alarm operation and / or a light alarm operation.

[0152] The beneficial effect of the above embodiment is that when there are heat sources such as tiny flames in the internal environment of a building, the air flow state information such as the air flow speed and direction of the internal environment of the building will directly affect the diffusion speed and direction of the heat source. For this reason, the heat source distribution position, heat source temperature and heat source size inside the key detection area contained in the heat source characteristic information and the air flow state information inside the key detection area are combined to predict the fire spread trend in the key detection area, and the fire spread speed and fire spread direction inside the key detection area are obtained, which are used as the fire change prediction result, wherein the fire spread trend prediction can be achieved through a convolutional neural network model, which belongs to the conventional technical means in this field and will not be described in detail here. In addition, based on the fire spread speed and the fire spread direction, the sub-area inside the building that is first affected by the fire is determined, that is, the sub-area that the fire inside the building reaches first during the diffusion process is determined. Based on the distribution location of the sub-area inside the building, the alarm device installed inside the sub-area (i.e., the matching alarm device) is selected from the Internet of Things, and an instruction is sent to the matching alarm device, so that the alarm device performs a sound alarm operation and / or a light alarm operation, thereby improving the reliability and accuracy of the Internet of Things' early warning of building fire hazards.

[0153] In general, the Internet of Things-based building fire hazard warning method and system identifies the first-class sensor equipment in an abnormal detection operation state based on the real-time detection data of the first-class sensor equipment under the Internet of Things, and determines the key detection area inside the building based on its detection range inside the building, and identifies and calibrates the area inside the building that cannot be normally and continuously detected due to the abnormal operation of the first-class sensor equipment; based on the spatial physical characteristics of the key detection area, determines the second-class sensor equipment that can perform real-scene detection, thereby determining the heat source characteristic information inside the building, and accurately identifying the source of the fire hazard inside the building; based on the heat source characteristic information, predicts the trend of fire changes in the building, thereby sending instructions to the alarm equipment under the Internet of Things and performing alarm operations, and by screening the two types of sensor equipment to eliminate unreliable sensor equipment, effectively avoids false alarms of fire hazard situations, and improves the reliability and accuracy of the Internet of Things' warning of building fire hazard situations.

[0154] The above is only a specific implementation of the present invention, and any other improvements made based on the concept of the present invention are considered to be within the protection scope of the present invention.

Claims

1. A building fire alarm danger early warning method based on the Internet of Things, characterized in that: include: Acquire the real-time detection data of all first-category sensing devices under the Internet of Things inside the building, analyze the real-time detection data, and identify all first-category sensing devices that are currently in an abnormal detection operation state; determine the key detection area inside the building based on the detection range of all first-category sensing devices that are currently in an abnormal detection operation state inside the building; Based on the spatial physical characteristics of the key detection area, determine all the second-type sensor devices of the Internet of Things subordinates that can cooperate in real-time real-scene detection; analyze the real-scene detection data from the second-type sensor devices to determine the heat source characteristic information inside the building; Based on the heat source characteristic information, the fire situation change trend of the internal environment of the building is predicted to obtain a fire situation change prediction result; based on the fire situation change prediction result, an instruction is sent to the alarm device under the Internet of Things, so that the alarm device performs a corresponding alarm operation.

2. The method for early warning of building fire danger based on the Internet of Things as claimed in claim 1, characterized in that: Acquire real-time detection data of all first-category sensor devices under the Internet of Things inside the building, analyze the real-time detection data, and identify all first-category sensor devices that are currently in an abnormal detection operation state; Based on the detection range of all the first-category sensing devices currently in the abnormal detection operation state inside the building, determining the key detection area inside the building includes: Monitor all smoke sensor devices under the Internet of Things inside the building to obtain real-time smoke concentration detection data of all smoke sensor devices within a preset time interval; identify abnormal data components of the real-time smoke concentration detection data based on the detection sensitivity of the smoke sensor devices to determine the abnormal data proportion of the real-time smoke concentration detection data; Based on the abnormal data proportion deviation information corresponding to any two adjacent smoke sensor devices among all smoke sensor devices, all smoke sensor devices that are currently in an abnormal detection operation state are identified; based on the detection coverage space range of all smoke sensor devices that are currently in an abnormal detection operation state inside the building, the detection failure area of ​​all smoke sensor devices inside the building is determined as the key detection area.

3. The building fire alarm danger early warning method based on the Internet of Things as claimed in claim 2, characterized in that: The time length of the reference time interval corresponding to each smoke sensor device is adjusted based on the detection sensitivity of the smoke sensor device, and a time interval corresponding to the adjusted time length is obtained, and the time interval corresponding to the adjusted time length is the preset time interval, including: Extract the detection sensitivity of each smoke sensing device; Obtaining a sensitivity coefficient corresponding to the smoke sensor device network according to the detection sensitivity of each smoke sensor device; The sensitivity coefficient is obtained by the following formula: Where L represents the sensitivity coefficient; n represents the total number of smoke sensor devices; M b represents the standard deviation of the sensitivity of n smoke sensing devices; M i represents the sensitivity corresponding to the i-th smoke sensor; T i represents the length of the time interval corresponding to the i-th smoke sensor; M f Indicates the preset sensitivity reference value; T f Indicates the preset time length reference value; T b represents the standard deviation of the time length of n smoke sensor devices; The sensitivity coefficient is combined with the detection sensitivity of each smoke sensor device to obtain a duration adjustment coefficient corresponding to each smoke sensor; The duration adjustment coefficient is obtained by the following formula: Wherein, f represents the duration adjustment coefficient; L represents the sensitivity coefficient; M represents the detection sensitivity of each smoke sensor device; T represents the time length of the time interval of each smoke sensor device; T b represents the standard deviation of the time length of n smoke sensor devices; M b represents the standard deviation of the sensitivity of n smoke sensing devices; M max Indicates the maximum sensitivity of n smoke sensing devices; Obtaining the adjusted time length corresponding to each smoke sensor device using the time length adjustment coefficient corresponding to each smoke sensor device; The adjusted time length is obtained by the following formula: Among them, T t represents the adjusted time length corresponding to each smoke sensor device; T represents the time length of the time interval of each smoke sensor device; f represents the time length adjustment coefficient; The adjusted time length is projected onto the reference time interval corresponding to each smoke sensor device, and the reference time interval is adjusted to obtain the preset time area corresponding to each smoke sensor device.

4. The method for early warning of building fire danger based on the Internet of Things as claimed in claim 1, characterized in that: Based on the spatial physical characteristics of the key detection area, determine all the second-category sensing devices of the Internet of Things subordinates that can cooperate in real-time real-scene detection; Analyzing the real-scene detection data from the second type of sensing equipment to determine the heat source characteristic information inside the building, including: Based on the shape and size of the three-dimensional space range of the key detection area, estimate the shooting blind spot feature information of all the camera sensor devices installed adjacent to the key detection area under the Internet of Things; based on the shooting blind spot feature information, select all the camera sensor devices that can cooperate in real-time real-scene detection of the key detection area from all the camera sensor devices installed adjacent to the key detection area; The real-scene image data from the camera sensor device is identified to determine the heat source distribution position, heat source temperature and heat source size inside the key detection area, which are used as the heat source characteristic information inside the building.

5. The method for early warning of building fire danger based on the Internet of Things as claimed in claim 1, characterized in that: Based on the heat source characteristic information, predict the fire situation change trend of the internal environment of the building to obtain a fire situation change prediction result; Based on the fire situation change prediction result, a command is sent to the alarm device under the Internet of Things, so that the alarm device performs a corresponding alarm operation, including: Based on the heat source distribution position, heat source temperature and heat source size within the key detection area contained in the heat source characteristic information and the air flow state information within the key detection area, the fire spread trend of the key detection area is predicted to obtain the fire spread speed and fire spread direction within the key detection area, which are used as the fire change prediction result; based on the fire spread speed and the fire spread direction, the sub-area inside the building that is first affected by the fire is determined; and based on the distribution position of the sub-area inside the building, a matching alarm device is selected from the Internet of Things, and an instruction is sent to the matching alarm device, so that the alarm device performs a sound alarm operation and / or a light alarm operation.

6. The building fire alarm warning system based on the Internet of Things is characterized by: include: The first-category sensor device screening module is used to obtain the real-time detection data of all the first-category sensor devices under the Internet of Things inside the building, analyze the real-time detection data, and identify all the first-category sensor devices that are currently in an abnormal detection operation state; A key detection area determination module, configured to determine a key detection area inside the building based on the detection range of all first-category sensing devices that are currently in an abnormal detection operation state inside the building; A second-category sensor device screening module, for determining all second-category sensor devices of the Internet of Things subordinates that can cooperate in real-time real-scene detection based on the spatial physical characteristics of the key detection area; A heat source feature recognition module, used to analyze the real-scene detection data from the second type of sensing equipment to determine the heat source feature information inside the building; A fire situation change prediction module, used to predict the fire situation change trend of the internal environment of the building based on the heat source characteristic information, and obtain a fire situation change prediction result; The alarm operation control module is used to send instructions to the alarm device under the Internet of Things based on the fire situation change prediction result, so that the alarm device performs corresponding alarm operations.

7. The building fire alarm danger warning system based on the Internet of Things as claimed in claim 6, characterized in that: The first-category sensor device screening module is used to obtain the real-time detection data of all first-category sensor devices under the Internet of Things inside the building, analyze the real-time detection data, and identify all first-category sensor devices that are currently in an abnormal detection operation state, including: Monitor all smoke sensor devices under the Internet of Things inside the building to obtain real-time smoke concentration detection data of all smoke sensor devices within a preset time interval; identify abnormal data components of the real-time smoke concentration detection data based on the detection sensitivity of the smoke sensor devices to determine the abnormal data proportion of the real-time smoke concentration detection data; Based on the abnormal data proportion deviation information corresponding to any two adjacent smoke sensor devices among all the smoke sensor devices, all smoke sensor devices currently in an abnormal detection operation state are identified; the key detection area determination module is used to determine the key detection area inside the building based on the detection range of all the first-class sensor devices currently in an abnormal detection operation state inside the building, including: Based on the detection coverage space range of all smoke sensing devices currently in abnormal detection operation state inside the building, the detection failure area of ​​all smoke sensing devices inside the building is determined as the key detection area.

8. The building fire alarm danger warning system based on the Internet of Things as claimed in claim 7, characterized in that: The time length of the reference time interval corresponding to each smoke sensor device is adjusted based on the detection sensitivity of the smoke sensor device, and a time interval corresponding to the adjusted time length is obtained, and the time interval corresponding to the adjusted time length is the preset time interval, including: Extract the detection sensitivity of each smoke sensing device; Obtaining a sensitivity coefficient corresponding to the smoke sensor device network according to the detection sensitivity of each smoke sensor device; The sensitivity coefficient is obtained by the following formula: Where L represents the sensitivity coefficient; n represents the total number of smoke sensor devices; M b represents the standard deviation of the sensitivity of n smoke sensing devices; M i represents the sensitivity corresponding to the i-th smoke sensor; T i represents the length of the time interval corresponding to the i-th smoke sensor; M f Indicates the preset sensitivity reference value; T f Indicates the preset time length reference value; T b represents the standard deviation of the time length of n smoke sensor devices; The sensitivity coefficient is combined with the detection sensitivity of each smoke sensor device to obtain a duration adjustment coefficient corresponding to each smoke sensor; The duration adjustment coefficient is obtained by the following formula: Wherein, f represents the duration adjustment coefficient; L represents the sensitivity coefficient; M represents the detection sensitivity of each smoke sensor device; T represents the time length of the time interval of each smoke sensor device; T b represents the standard deviation of the time length of n smoke sensor devices; M b represents the standard deviation of the sensitivity of n smoke sensing devices; M max Indicates the maximum sensitivity of n smoke sensing devices; Obtaining the adjusted time length corresponding to each smoke sensor device using the time length adjustment coefficient corresponding to each smoke sensor device; The adjusted time length is obtained by the following formula: Among them, T t represents the adjusted time length corresponding to each smoke sensor device; T represents the time length of the time interval of each smoke sensor device; f represents the time length adjustment coefficient; The adjusted time length is projected onto the reference time interval corresponding to each smoke sensor device, and the reference time interval is adjusted to obtain the preset time area corresponding to each smoke sensor device.

9. The building fire alarm danger warning system based on the Internet of Things as claimed in claim 6, characterized in that: The second-category sensor device screening module is used to determine all second-category sensor devices of the Internet of Things that can cooperate in real-time real-scene detection based on the spatial physical characteristics of the key detection area, including: Based on the shape and size of the three-dimensional space range of the key detection area, estimate the shooting blind spot feature information of all the camera sensor devices installed adjacent to the key detection area under the Internet of Things; based on the shooting blind spot feature information, select all the camera sensor devices that can cooperate in real-time real-scene detection of the key detection area from all the camera sensor devices installed adjacent to the key detection area; The heat source feature recognition module is used to analyze the real-scene detection data from the second type of sensor equipment to determine the heat source feature information inside the building, including: The real-scene image data from the camera sensor device is identified to determine the heat source distribution position, heat source temperature and heat source size inside the key detection area, which are used as the heat source characteristic information inside the building.

10. The building fire alarm danger warning system based on the Internet of Things as claimed in claim 6, characterized in that: The fire situation change prediction module is used to predict the fire situation change trend of the internal environment of the building based on the heat source characteristic information to obtain the fire situation change prediction result, including: Based on the heat source distribution position, heat source temperature and heat source size inside the key detection area contained in the heat source characteristic information and the air flow state information inside the key detection area, the fire spread trend of the key detection area is predicted to obtain the fire spread speed and fire spread direction inside the key detection area as the fire change prediction result; the alarm operation control module is used to send instructions to the alarm device under the Internet of Things based on the fire change prediction result, so that the alarm device performs corresponding alarm operations, including: Based on the fire spreading speed and the fire spreading direction, the sub-area inside the building that is first affected by the fire is determined; and based on the distribution positions of the sub-areas inside the building, a matching alarm device is selected from within the Internet of Things, and an instruction is sent to the matching alarm device, so that the alarm device performs a sound alarm operation and / or a light alarm operation.

Images