Intelligent building monitoring management system based on Internet of Things

Abstract

The invention relates to the field of building fire defense, and provides an intelligent building monitoring management system based on the Internet of Things, and the system comprises a DS evidence theory module and a management module which are carried on an Internet of Things cloud platform. The DS evidence theory module generates a fire early warning score based on a first evidence set, a second evidence set or a third evidence set, the first evidence set is constructed based on collection values of multiple sensors in a set area, and the second evidence set is constructed based on the first evidence set and the area scene association degree of the multiple sensors and the set area; the third evidence set is constructed based on the correlation degree between the second evidence set and the multiple sensors; the management module carries out management, display and early warning on the plurality of fire early warning scores of the plurality of set areas. According to the invention, comprehensive fire early warning for different types of sensors in different areas in the building is realized through the DS evidence theory, and a more intelligent fire early warning function of the Internet of Things monitoring management system of the building is realized.

Description

Technical Field

[0001] The present invention relates to the field of building fire defense, and in particular to an intelligent building monitoring and management system based on the Internet of Things. Background Art

[0002] When a fire occurs, the combustion of combustibles will produce various physical phenomena such as flames, smoke, heat, gas, etc. Therefore, the environment can be monitored using multiple sensors. The changes in these physical quantities are converted into characteristic electrical signal outputs through sensors. Once a fire occurs, the fire can be discovered in time. However, in the actual fire environment, the changes in various physical signals in the early stage of the fire are unstable, resulting in unstable changes in the signals collected by the sensors. It is difficult to accurately determine whether a fire has actually occurred from the data collected by the sensors. In addition, interference sources such as the increase in temperature, dust, smoking, and sunlight in the monitoring environment will cause changes in the sensor output signal. Due to the randomness and uncertainty of the interference signal, it directly affects the stability of the fire monitoring system. Therefore, it is necessary to use the DS evidence theory in the statistical algorithm to fuse the data collected by multiple sensors to improve the accuracy, stability and reliability of the system.

[0003] DS evidence theory was first proposed by Dempster in the 1960s, and Shafer's book "A Mathematical Theory of Evidence" published in 1976 marked the formal establishment of the theory. In theory, DS evidence theory can represent and process uncertain information more effectively than probability theory. After more than 40 years of development, the foundation of DS evidence theory has been continuously improved and its application scope has been continuously expanded. It has been widely used in expert systems, target recognition, artificial intelligence, decision-making and risk analysis, and has become an important foundation in the field of uncertain information processing and fusion.

[0004] At present, for example, the invention patent with application number 201410067387.2 discloses a method for using the fusion of multiple sensor values ​​to determine whether a fire has occurred. However, its judgment method is relatively simple and only determines whether a fire has occurred. It cannot make targeted judgments on various scenes in a building. Therefore, it cannot adapt to the high judgment accuracy requirements of the Internet of Things in a building.

[0005] Therefore, how to obtain more targeted fire warning scores for different scenarios represented by different areas of a building through the DS evidence theory, and then make it applicable to the building's Internet of Things platform, is a technical problem that needs to be solved. Summary of the invention

[0006] To this end, the present invention provides an intelligent building monitoring and management system based on the Internet of Things. By inputting a trust distribution function that combines regional scenarios and the degree of correlation between sensors into a data fusion model based on the DS evidence theory for processing, a fire warning score is generated, and a comprehensive fire warning for different types of sensors in different areas of the building is implemented through the DS evidence theory, thereby realizing a more intelligent fire warning function of the building's Internet of Things monitoring and management system.

[0007] To achieve the above-mentioned object, the present invention proposes an intelligent building monitoring and management system based on the Internet of Things, including a DS evidence theory module and a management module, both of which are mounted on an Internet of Things cloud platform;

[0008] The first evidence set is constructed based on the collected values ​​of multiple sensors for detecting fire in a set area, the second evidence set is constructed based on the correlation between the first evidence set and the multiple sensors and the regional scene of the set area, and the third evidence set is constructed based on the correlation between the second evidence set and the multiple sensors;

[0009] The management module is used to manage, display and warn multiple fire warning scores of multiple set areas.

[0010] Further, the DS evidence theory module includes a trust allocation function determination unit and a model operation unit;

[0011] The trust allocation function determination unit normalizes the collected values ​​to obtain normalized values, corresponds the normalized values ​​to a set interval of the basic trust allocation value library of the sensor, obtains the number of highly likely fires, likely fires, less likely fires, and extremely unlikely fires corresponding to the set interval, divides the number by the total number to obtain the first evidence set, the first evidence set includes multiple evidences corresponding to multiple different sensors, each evidence includes a trust allocation function of a sensor.

[0012] In the above scheme, the first evidence set reflecting the possible number of fire occurrences is generated by normalizing the collected values ​​of the sensors, thereby avoiding different precisions of the set intervals caused by different unit magnitudes of different sensors.

[0013] Further, the trust allocation function determination unit includes a correlation trust allocation function determination subunit;

[0014] The association trust allocation function determines that the subunit carries a sensor scene association database to determine weight coefficients corresponding to multiple sensors respectively, and multiplies each evidence in the first evidence set by the weight coefficient to obtain the second evidence set.

[0015] In the above scheme, the sensitivity of DS evidence theory to evidence is utilized, and then through the second evidence set, a fire warning score with a high correlation with the scene in the set area can be obtained.

[0016] Furthermore, the DS evidence theory module is equipped with a correlation degree calculation model and a DS evidence theory model;

[0017] The association degree calculation model determines the credibility of the trust allocation function of each sensor in the second evidence set by calculation, and obtains the third evidence set after weighted averaging each trust allocation function in the second trust allocation function using the credibility as a weight;

[0018] The DS evidence theory model fuses the third evidence set using the DS evidence theory to obtain possible values ​​of highly likely fire, relatively likely fire, relatively unlikely fire, and extremely unlikely fire, and multiplies the possible values ​​and the level values ​​to obtain the fire warning score.

[0019] Furthermore, the correlation calculation model determines the correlation coefficient between the trust allocation functions of each sensor by calculation, and normalizes the correlation coefficient to obtain the credibility.

[0020] In the above scheme, through the statistical correlation coefficient and the normalization of the correlation coefficient, the third evidence set can represent the degree of correlation between the trust allocation functions of each sensor, avoiding sensor failure and data conflict between sensors that lead to inaccurate fire warning scores derived from the DS evidence theory model.

[0021] Further, if the DS evidence theory module determines that the credibility between the trust allocation function of a sensor and the trust allocation functions of other sensors is lower than the lower threshold, the sensor abnormality information is sent to the management module;

[0022] The management module displays the sensor abnormality information.

[0023] Furthermore, the multiple different sensors are at least two of a temperature sensor, a humidity sensor, a flame light sensor, a smoke sensor, a solid particle sensor, and a sound sensor.

[0024] Furthermore, the intelligent building monitoring and management system also includes an audible and visual alarm device, an electric switch, and a fire extinguishing system that communicate with the management module;

[0025] The management module controls the operation of the fire extinguishing system, the sound and light alarm device to sound an alarm, and the switch to shut down the electrical equipment in the set area according to the fire warning score;

[0026] The management module carries information about the distance between the fire-fighting facilities and the set area, as well as the service life of the fire-fighting facilities, and determines whether to improve the fire warning score based on a comparison result of the distance and the service life with corresponding set thresholds.

[0027] Furthermore, the IoT cloud platform is a OneNET IoT cloud platform, which communicates with mobile devices of building users and sends location information of the fire-fighting facilities to building users when the fire warning score exceeds a warning value.

[0028] Furthermore, the management module also carries the building's power load level information;

[0029] When the power load level is level three or level two, the management module controls the switch to shut down the power equipment in the set area according to the fire warning score;

[0030] When the power load level is level one, the management module sends a switch-off request to the user according to the fire warning score, and controls the switch to shut off the electrical equipment in the set area after receiving the user's confirmation shutdown information.

[0031] In the above solution, building information carried in the Internet of Things is utilized to make the fire warning score more in line with the needs of fire handling.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] 1. By inputting the trust distribution function that combines regional scenarios and the degree of correlation between sensors into the data fusion model based on DS evidence theory for processing, a fire warning score is generated. This realizes the comprehensive fire warning of different types of sensors in different areas of the building through DS evidence theory, and realizes a more intelligent fire warning function of the building's Internet of Things monitoring and management system.

[0034] 2. The sensitivity of DS evidence theory to evidence is utilized, and then through the second evidence set, a fire warning score with a high correlation with the scene in the set area can be obtained.

[0035] 3. Through the statistical correlation coefficient and the normalization of the correlation coefficient, the third evidence set can represent the degree of correlation between the trust allocation functions of each sensor, avoiding the inaccurate fire warning score derived from the DS evidence theory model due to sensor failure and data conflict between sensors. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic diagram of the general structure of an intelligent building monitoring and management system according to an embodiment of the present invention;

[0037] Figure 2A schematic diagram of the general flow of the intelligent building monitoring and management system according to an embodiment of the present invention;

[0038] Figure 3 A detailed flowchart of the intelligent building monitoring and management system according to an embodiment of the present invention;

[0039] Figure 4 The figure is a detailed structural diagram of the intelligent building monitoring and management system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0041] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0042] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0043] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0044] like Figures 1 to 4 As shown, the present invention provides an intelligent building monitoring and management system based on the Internet of Things. By inputting the trust distribution function combining regional scenes and the degree of correlation between sensors into a data fusion model based on the DS evidence theory for processing, a fire warning score is generated, and a comprehensive fire warning for different types of sensors in different areas of the building is realized through the DS evidence theory, thereby realizing a more intelligent fire warning function of the Internet of Things monitoring and management system of the building.

[0045] in, Figure 1 A schematic diagram of the general structure of an intelligent building monitoring and management system according to an embodiment of the present invention; Figure 2A schematic diagram of the general flow of the intelligent building monitoring and management system according to an embodiment of the present invention; Figure 3 A detailed flowchart of the intelligent building monitoring and management system according to an embodiment of the present invention; Figure 4 The figure is a detailed structural diagram of the intelligent building monitoring and management system according to an embodiment of the present invention.

[0046] Embodiment 1:

[0047] like Figures 1 to 4 As shown, this embodiment proposes an intelligent building monitoring and management system based on the Internet of Things, including a DS evidence theory module and a management module, both of which are installed on the Internet of Things cloud platform; the DS evidence theory module is used to generate a fire warning score based on a first evidence set, a second evidence set or a third evidence set, wherein the first evidence set is constructed based on the collected values ​​of multiple sensors for detecting fires in a set area, the second evidence set is constructed based on the first evidence set and the correlation between multiple sensors and the regional scenes of the set area, and the third evidence set is constructed based on the correlation between the second evidence set and multiple sensors; the management module is used to manage, display and warn multiple fire warning scores of multiple set areas.

[0048] It can be understood that the IoT cloud platform can display and manage fire warning scores in real time through its application layer, while also providing sufficient data support for the DS evidence theory module. This embodiment uses fire warning scores to make the IoT cloud platform display and control the actions of the hardware layer more intelligent.

[0049] Furthermore, the DS evidence theory module includes a trust allocation function determination unit and a model operation unit; the trust allocation function determination unit normalizes the collected value to obtain a normalized value, corresponds the normalized value to a set interval of the sensor basic trust allocation value library, obtains the number of highly likely fires, more likely fires, less likely fires, and extremely unlikely fires corresponding to the set interval, divides the number by the total number to obtain the first evidence set, the first evidence set includes multiple evidences corresponding to multiple different sensors, and each evidence includes a trust allocation function of a sensor.

[0050] Specifically, the first evidence set includes the first evidence {ma(X), ma(Y), ma(Z), ma(M)}, the second evidence {mb(X), mb(Y), mb(Z), mb(M)}...the nth evidence {mn(X), mn(Y), mn(Z), mn(M)}, wherein a, b...n represent multiple different sensors, X represents a fire that is very likely to occur, Y represents a fire that is very likely to occur, Z represents a fire that is less likely to occur, M represents a fire that is extremely unlikely to occur, and ma(X) represents the trust distribution function that sensor a is very likely to cause a fire.

[0051] It should be noted that the normalization is performed using conventional normalization conversion formulas such as a deviation normalization formula and an arctan function, and it is only necessary to ensure that the normalized value outputted is between [0, 1].

[0052] It should be noted that the sensor basic trust allocation value library is the number of possible fire occurrences obtained based on historical data from experiments or building monitoring. For example, in the set interval where the temperature sensor's collected value is above 300 degrees (normalized to 0.9), there are 25 fires that are very likely to occur, 2 fires that are likely to occur, and 0 fires that are unlikely to occur and extremely unlikely to occur. The temperature sensor detects that in the set interval from 200 degrees to 300 degrees, there are 20 fires that are very likely to occur, 5 fires that are likely to occur, and 2 fires that are unlikely to occur and extremely unlikely to occur. Divide 25 times, 2 times, etc. by the total number of times in the corresponding set interval, and then ensure that the sum of the four trust allocation functions in each piece of evidence is equal to 1, which complies with the evidence construction rules of the DS evidence theory model. Therefore, the first evidence set can be directly used in the DS evidence theory model.

[0053] It can be understood that the trust allocation function m of the DS evidence theory model is: u →[0,1], the following conditions must be met at the same time:

[0054] That is, the trust allocation to the empty set is 0, and the sum of the trust allocations of all elements in the identification framework U (ie, the first evidence set to the third evidence set) is 1.

[0055] Therefore, by normalizing the collected values ​​of the sensor, a first evidence set reflecting the possible number of times a fire may occur is generated, thereby avoiding different precisions in the set interval caused by different unit magnitudes of different sensors.

[0056] Furthermore, the trust allocation function determination unit includes a correlation trust allocation function determination subunit; the correlation trust allocation function determination subunit is equipped with a sensor scene correlation database to determine the weight coefficients corresponding to multiple sensors respectively, and each evidence in the first evidence set is multiplied by the weight coefficient to obtain the second evidence set.

[0057] Specifically, the corresponding relationship between the sensor type and the weight coefficient in the scene association database is:

[0058] The areas in the building are divided into kitchen areas, residential areas, high-rise areas, etc. according to their fire prevention scenarios. In the kitchen area, it is mainly necessary to prevent oil pollution from causing fires due to high-temperature sparks or open flames. The weight coefficients of the evidence corresponding to each sensor in this area are, from large to small, flame light sensor, gas sensor for detecting oil smoke, temperature sensor, and the weight coefficients of humidity sensor, smoke sensor, solid particle sensor and sound sensor are all minimum values. In the residential area, electrical and natural gas fires are mainly prevented. The weight coefficients of the evidence corresponding to each sensor in this area are, from large to small, flame light sensor, smoke sensor, sound sensor, etc. Fires in high-rise areas are prone to form a "chimney effect". The weight coefficients of the evidence corresponding to each sensor in this area are, from large to small, flame light sensor, smoke sensor, solid particle sensor, sound sensor, etc. The specific values ​​of the above weight coefficients can be set according to the actual situation of the building.

[0059] Therefore, the sensitivity of DS evidence theory to evidence is utilized, and then through the second evidence set, a fire warning score with a high correlation with the scene in the set area can be obtained.

[0060] Furthermore, the DS evidence theory module is equipped with a data fusion model, which includes a correlation calculation model and a DS evidence theory model; the correlation calculation model determines the credibility of the trust allocation function of each sensor in the second evidence set by calculation, and obtains the third evidence set after weighted averaging each trust allocation function in the second trust allocation function using the credibility as a weight; the DS evidence theory model fuses the third evidence set using DS evidence theory to obtain possible values ​​of highly likely fire, relatively likely fire, relatively unlikely fire, and extremely unlikely fire, and multiplies the possible value by the level value to obtain the fire warning score.

[0061] Furthermore, the correlation calculation model determines the correlation coefficient between the trust allocation functions of each sensor by calculation, and normalizes the correlation coefficient to obtain the credibility.

[0062] Specifically, the correlation calculation model carries a calculation formula for determining the credibility, which is:

[0063]

[0064] In the formula, ρ(m i ,m j ) is the correlation coefficient between two different trust allocation functions, r(m i ) is the trust distribution function m i The support degree, C(m i ) represents the trust distribution function m icredibility.

[0065] It should be noted that the correlation coefficient is a quantity that represents the degree of correlation between variables in statistics, which is the expected value of the covariate divided by the square root. Therefore, the support and credibility can represent the degree of correlation between the trust allocation functions of each sensor. The support is normalized by the second formula, so that the sum of each support is equal to 1, which conforms to the evidence construction rule of the DS evidence theory model.

[0066] In the above scheme, through the statistical correlation coefficient and the normalization of the correlation coefficient, the third evidence set can represent the degree of correlation between the trust allocation functions of each sensor, avoiding sensor failure and data conflict between sensors that lead to inaccurate fire warning scores derived from the DS evidence theory model.

[0067] Furthermore, if the DS evidence theory module determines that the credibility between the trust allocation function of a sensor and the trust allocation functions of other sensors is lower than the lower limit threshold, the sensor abnormality information is sent to the management module; the management module displays the sensor abnormality information.

[0068] Furthermore, the multiple different sensors are at least two of a temperature sensor, a humidity sensor, a flame light sensor, a smoke sensor, a solid particle sensor, and a sound sensor.

[0069] In a specific application of this embodiment, the formats of the first evidence set, the second evidence set and the third evidence set are: first evidence {ma(X), ma(Y), ma(Z), ma(M)}, second evidence {mb(X), mb(Y), mb(Z), mb(M)}...nth evidence {mn(X), mn(Y), mn(Z), mn(M)}, wherein a, b...n represent multiple different sensors, X represents a fire that is very likely to occur, Y represents a fire that is very likely to occur, Z represents a fire that is less likely to occur, M represents a fire that is extremely unlikely to occur, and ma(X) represents the trust distribution function that sensor a is very likely to cause a fire.

[0070] Through the synthesis rules of the DS evidence theory model, the first to nth evidences are processed, specifically: Identify a finite number of ma, mb, ..., mn functions in the framework U (i.e., the evidence set), then

[0071]

[0072] In the formula, A represents one of X, Y, Z, and M, and K is the evidence conflict coefficient, which indicates the degree of conflict between the evidences. is a normalization factor, which can avoid assigning probability to the empty set when data fusion.

[0073] See also Figure 3 , the data of the second evidence set shown in the following table is an example:

[0074] ma() mb() mc() X 0.75 0.10 0.07 Y 0.15 0.07 0.13 Z 0.07 0.60 0.50 M 0.03 0.23 0.30

[0075] When the data of the second evidence set are directly fused using the DS evidence theory, due to the low correlation between sensor a and sensors b and c, the evidence conflict coefficient K = 0.98 is obtained, indicating that the degree of conflict between the evidence is severe. Due to the veto problem of the DS evidence theory, the possible value of Z is the largest. However, since the support of sensor a for Z is unreasonably low, the DS evidence theory cannot produce accurate results for high-conflict information.

[0076] At this time, by calculating the correlation coefficient and credibility of the data of the second evidence set, it can be obtained that the credibility of sensors b and c is greater than the credibility of sensor a, that is, the higher the correlation coefficient between evidence b and evidence c or other evidence, the higher the support of other evidence for evidence b, and thus it is considered that evidence b has a higher credibility, so a higher weight can be assigned to the evidence. The third evidence set is obtained by weighted averaging the second evidence set, and then fused through DS evidence theory to obtain the final fusion decision result, which can reduce the impact of sensor failure or noise interference on the fusion result.

[0077] When the data in the above table are used as the first evidence set, the second evidence set and the third evidence set respectively, the results of data fusion of DS evidence theory are as shown in the following table:

[0078]

[0079]

[0080] Comparing the above table with the original data, it can be concluded that the results of the third evidence set are obviously more accurate.

[0081] Furthermore, the intelligent building monitoring and management system also includes an audible and visual alarm device, a switch, and a fire extinguishing system that communicate with the management module; the management module controls the operation of the fire extinguishing system, the audible and visual alarm device to sound an alarm, and the switch to shut down electrical equipment in a set area according to the fire warning score; the management module carries information on the distance between the fire-fighting facilities and the set area, as well as the service life of the fire-fighting facilities, and determines whether to increase the fire warning score based on the comparison result of the distance and the service life with the corresponding set threshold value.

[0082] The fire extinguishing system is a system for automatically spraying fires in buildings, including a water spray system and a foam fire extinguishing system. When the fire warning score exceeds the upper threshold, the fire extinguishing system is controlled to operate, the sound and light alarm device sounds an alarm, and the switch shuts off the electrical equipment in the set area.

[0083] When the distance exceeds the safety value, the fire warning score is increased by a set value, so that the fire warning score is more likely to exceed the upper threshold, thereby ensuring that even if the fire is not extinguished by the limited fire extinguishing agent of the fire extinguishing system, personnel can use fire-fighting facilities to extinguish the fire in time.

[0084] Furthermore, the IoT cloud platform is a OneNET IoT cloud platform, which communicates with mobile devices of building users and sends location information of the fire-fighting facilities to building users when the fire warning score exceeds a warning value.

[0085] See also Figure 4 The deployment based on the OneNET cloud platform realizes functions such as data storage, monitoring, and early warning, and the UI application controls realize the visualization of data and the issuance of control commands.

[0086] Furthermore, the management module also carries the power load level information of the building; when the power load level is level three or level two, the management module controls the power switch to shut off the electrical equipment in the set area according to the fire warning score; when the power load level is level one, the management module sends a power switch shutoff request to the user according to the fire warning score, and after receiving the user's confirmation shutoff information, controls the power switch to shut off the electrical equipment in the set area.

[0087] It should be noted that the power load level and its regulations described in this implementation are as follows: When one of the following conditions is met, it should be a first-level power load: 1. When power interruption will cause personal injury or death. 2. When power interruption will cause significant economic losses. For example: damage to major equipment, scrapping of major products, large-scale scrapping of products produced with important raw materials, disruption of the continuous production process of key enterprises in the national economy, and a long time to recover. 3. Power interruption will affect the normal work of power users with significant economic significance. When one of the following conditions is met, it should be a second-level load: 1. When power interruption will cause significant economic losses. For example: damage to major equipment, scrapping of a large number of products, disruption of the continuous production process, and a long time to recover, and a large-scale reduction in production of key enterprises. 2. Power interruption will affect the normal work of important power users. Those that do not belong to the first and second level loads should be third-level loads, and short-term power outages are allowed for third-level loads.

[0088] In the above solution, building information carried in the Internet of Things is utilized to make the fire warning score more in line with the needs of fire handling.

[0089] like Figure 4 As shown in the figure, data transmission layer: as the bridge of the entire architecture, data transmission is carried out through industrial ring network or 4G / 5G network. Remote control is a human-machine interaction window for intelligent management. Rapid judgment and early warning of fire information are conducive to the formulation of production optimization decision-making plans, and timely response to coordinated linkage in different situations, to achieve linkage control and emergency rescue assistance in emergency situations.

[0090] In this embodiment, the trust allocation function combining the regional scene and the degree of correlation between sensors is input into the data fusion model based on the DS evidence theory for processing to generate a fire warning score, thereby realizing a comprehensive fire warning for different types of sensors in different areas of the building through the DS evidence theory, and realizing a more intelligent fire warning function of the building's Internet of Things monitoring and management system. The sensitivity of the DS evidence theory to evidence is utilized, and then through the second evidence set, a fire warning score with a high degree of correlation with the scene can be obtained. Through the statistical correlation coefficient and the normalization of the correlation coefficient, the third evidence set can represent the degree of correlation between the trust allocation functions of each sensor, avoiding sensor failures and data conflicts between sensors that lead to inaccurate fire warning scores obtained by the DS evidence theory model.

[0091] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0092] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent building monitoring and management system based on the Internet of Things, characterized in that: It includes DS evidence theory module and management module, both of which are installed on the IoT cloud platform; The DS evidence theory module is used to generate a fire warning score based on a first evidence set, a second evidence set or a third evidence set, wherein the first evidence set is constructed based on the collected values ​​of multiple sensors for detecting fire in a set area, the second evidence set is constructed based on the first evidence set and the correlation between multiple sensors and the regional scene of the set area, and the third evidence set is constructed based on the correlation between the second evidence set and multiple sensors; The management module is used to manage, display and warn multiple fire warning scores of multiple set areas.

2. According to the Internet of Things-based intelligent building monitoring and management system according to claim 1, it is characterized in that: The DS evidence theory module includes a trust allocation function determination unit and a model operation unit; The trust allocation function determination unit normalizes the collected values ​​to obtain normalized values, corresponds the normalized values ​​to a set interval of the basic trust allocation value library of the sensor, obtains the number of highly likely fires, likely fires, less likely fires, and extremely unlikely fires corresponding to the set interval, divides the number by the total number to obtain the first evidence set, the first evidence set includes multiple evidences corresponding to multiple different sensors, each evidence includes a trust allocation function of a sensor.

3. The intelligent building monitoring and management system based on the Internet of Things according to claim 2 is characterized in that: The trust allocation function determination unit includes a correlation trust allocation function determination subunit; The association trust allocation function determines that the subunit carries a sensor scene association database to determine weight coefficients corresponding to multiple sensors respectively, and multiplies each evidence in the first evidence set by the weight coefficient to obtain the second evidence set.

4. The intelligent building monitoring and management system based on the Internet of Things according to claim 3 is characterized in that: The DS evidence theory module is equipped with a correlation calculation model and a DS evidence theory model; The association degree calculation model determines the credibility of the trust allocation function of each sensor in the second evidence set by calculation, and obtains the third evidence set after weighted averaging each trust allocation function in the second trust allocation function using the credibility as a weight; The DS evidence theory model fuses the third evidence set using the DS evidence theory to obtain possible values ​​of highly likely fire, relatively likely fire, relatively unlikely fire, and extremely unlikely fire, and multiplies the possible values ​​and the level values ​​to obtain the fire warning score.

5. The intelligent building monitoring and management system based on the Internet of Things according to claim 4 is characterized in that: The correlation calculation model determines the correlation coefficient between the trust allocation functions of each sensor by calculation, and normalizes the correlation coefficient to obtain the credibility.

6. The intelligent building monitoring and management system based on the Internet of Things according to claim 4 is characterized in that: If the DS evidence theory module determines that the credibility between the trust allocation function of a sensor and the trust allocation functions of other sensors is lower than the lower threshold, the sensor abnormality information is sent to the management module; The management module displays the sensor abnormality information.

7. The intelligent building monitoring and management system based on the Internet of Things according to claim 3 is characterized in that: The multiple different sensors are at least two of a temperature sensor, a humidity sensor, a flame light sensor, a smoke sensor, a solid particle sensor, and a sound sensor.

8. The intelligent building monitoring and management system based on the Internet of Things according to any one of claims 1 to 7, characterized in that: Also included are an audible and visual alarm device, an electric switch, and a fire extinguishing system that communicate with the management module; The management module controls the operation of the fire extinguishing system, the sound and light alarm device to sound an alarm, and the switch to shut down the electrical equipment in the set area according to the fire warning score; The management module carries information about the distance between the fire-fighting facilities and the set area, as well as the service life of the fire-fighting facilities, and determines whether to improve the fire warning score based on a comparison result of the distance and the service life with corresponding set thresholds.

9. The intelligent building monitoring and management system based on the Internet of Things according to claim 8 is characterized in that: The IoT cloud platform is the OneNET IoT cloud platform, which communicates with the mobile devices of the building users and sends the location information of the fire-fighting facilities to the building users when the fire warning score exceeds the warning value.

10. The intelligent building monitoring and management system based on the Internet of Things according to claim 8, characterized in that: The management module also carries the building's power load level information; When the power load level is level three or level two, the management module controls the switch to shut down the power equipment in the set area according to the fire warning score; When the power load level is level one, the management module sends a switch-off request to the user according to the fire warning score, and controls the switch to shut off the electrical equipment in the set area after receiving the user's confirmation shutdown information.

Images