Intelligent building fire safety monitoring system based on artificial intelligence

Abstract

The invention belongs to the field of fire safety, relates to a data analysis technology, is used for solving the problem that a fire safety monitoring system in the prior art cannot automatically screen a fire behavior control processing decision according to a field environment, and particularly relates to an intelligent building fire safety monitoring system based on artificial intelligence, which comprises a safety monitoring platform, the safety monitoring platform is in communication connection with a safety monitoring module, a risk analysis module, a decision processing module and a database, and the risk analysis module is also in communication connection with an instant control module; the safety monitoring module is used for carrying out fire safety monitoring analysis on the intelligent building; according to the method, the spreading coefficient can be obtained through calculation in combination with the multiple risk parameters about the fire point in the risk data set, the fire spreading trend of the floor where the fire point is located is evaluated according to the spreading coefficient, then the most appropriate control means is adopted for fire control according to the evaluation result, and the fire handling efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the field of fire safety and relates to data analysis technology, and specifically is an intelligent building fire safety monitoring system based on artificial intelligence. Background Art

[0002] The fire monitoring and control system consists of two parts: fire monitoring and fire control system. The overall system monitors the presence of fire hazards in real time through fire monitoring, and in case of danger, the control system is linked to control the fire and evacuate personnel.

[0003] The fire safety monitoring system in the prior art often requires rescue personnel to determine the fire control method based on the on-site conditions when conducting fire control after triggering a fire alarm. Due to the harsh environment at the fire scene and the chaotic order when people escape, these factors will affect the accuracy of the judgment of the fire control method, and thus the efficiency of fire handling cannot be guaranteed, and it is difficult to minimize the negative impact caused by the fire.

[0004] In view of the above technical problems, this application proposes a solution. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent building fire safety monitoring system based on artificial intelligence, which is used to solve the problem that the fire safety monitoring system in the prior art cannot automatically screen the fire control processing decision according to the on-site environment;

[0006] The technical problem to be solved by the present invention is: how to provide an intelligent building fire safety monitoring system based on artificial intelligence that can automatically screen fire control processing decisions according to the on-site environment.

[0007] The purpose of the present invention can be achieved by the following technical solutions:

[0008] An intelligent building fire safety monitoring system based on artificial intelligence, comprising a safety monitoring platform, wherein the safety monitoring platform is communicatively connected to a safety monitoring module, a risk analysis module, a decision processing module and a database, and the risk analysis module is also communicatively connected to an instant control module;

[0009] The safety monitoring module is used to perform fire safety monitoring and analysis on intelligent buildings: detection points are set in the intelligent building, and the monitoring coefficients JC of the detection points are obtained in real time; the monitoring coefficients JC of all detection points are sent to the risk analysis module through the safety monitoring platform;

[0010] The risk analysis module is used to analyze the overall fire risk of the intelligent building: the detection point is marked as a safe point or a risk point through the monitoring coefficient KC of the detection point; whether all the detection points are marked as safe points is determined: if so, it is determined that the fire safety of the intelligent building meets the requirements; if not, firstly, a risk warning signal is generated and sent to the immediate control module, and after receiving the risk warning signal, the immediate control module controls the fire treatment facilities in the area where the risk point is located to start, and then all the risk points are combined according to the floors where they are located to obtain several risk data groups, and the risk points in each risk data group are located on the same floor; whether a control decision analysis is needed is determined according to the number of risk points in the risk data group;

[0011] The decision processing module is used to analyze the fire control decision of the risk data group.

[0012] Furthermore, the acquisition process of the detection point JC includes: setting a detection terminal at the detection point and acquiring the air temperature value KW and the smoke concentration value YW of the detection point in real time through the detection terminal, and performing numerical calculation on the air temperature value KW and the smoke concentration value YW to obtain the monitoring coefficient JC of the detection point.

[0013] Furthermore, the specific process of marking the detection point as a safe point or a risk point includes: retrieving the monitoring threshold JCmax through the database, and comparing the monitoring coefficient JC of the detection point with the monitoring threshold JCmax: if the monitoring coefficient JC is less than the monitoring threshold JCmax, it is determined that the fire safety hazard of the detection point meets the requirements, and the corresponding detection point is marked as a safe point; if the monitoring coefficient JC is greater than or equal to the monitoring threshold JCmax, it is determined that the fire safety hazard of the detection point does not meet the requirements, and the corresponding detection point is marked as a risk point.

[0014] Furthermore, the specific process of determining whether a control decision analysis is needed includes: determining whether the number of risk points in the risk data group is less than L1: if so, marking the risk point with the largest monitoring coefficient JC value in the risk data group as the ignition point, generating a decision processing signal and sending the decision processing signal and the ignition point to the decision processing module; if not, generating a spread control signal and sending the spread control signal to the manager's mobile terminal through the security monitoring platform.

[0015] Furthermore, the specific process of analyzing the fire control decision of the risk data group by the decision processing module includes: obtaining trend data QS, spatial data KJ, vertical data CZ and center data ZX; The spread coefficient MY of the fire point is obtained, where k1, k2, k3 and k4 are all proportional coefficients, and k1>k2>k3>k4>1; the spread threshold MYmax is obtained through the database, the spread coefficient MY is compared with the spread threshold MYmax, and a spread control signal or a central control signal is generated based on the comparison result and sent to the mobile terminal of the manager.

[0016] Furthermore, the process of acquiring trend data QS, spatial data KJ, vertical data CZ and center data ZX includes: obtaining a hidden danger threshold value YH through the formula YH=t1*JCmax, marking the detection point on the same floor whose monitoring coefficient JC is not less than the hidden danger threshold value YH as a hidden danger point, marking the straight-line distance between the hidden danger point and the fire point as the straight-line distance value of the hidden danger point, marking the hidden danger point with the largest straight-line distance value as a spread boundary point, drawing a circle with the fire point as the center and the straight-line distance value of the spread boundary point as the radius to obtain a spread prediction range, marking the ratio of the number of hidden danger points within the spread prediction range to the number of detection points as the trend data QS of the spread prediction range, marking the ratio of the area value of the spread prediction range to the area value of the floor where the fire point is located as the spatial data KJ of the spread prediction range, marking the ratio of the number of floors of the fire point to the total number of floors of the intelligent building as the vertical data CZ, sorting the detection points in order of the straight-line distance values ​​to the center point of the floor from near to far to obtain a center sequence, and marking the ratio of the sequence number of the fire point in the center sequence to the number of all detection points on the floor as the center data ZX.

[0017] Furthermore, the specific process of comparing the spread coefficient MY with the spread threshold MYmax includes: if the spread coefficient MY is less than the spread threshold MYmax, it is determined that the spread trend of the fire point meets the requirements, a central control signal is generated and the central control signal is sent to the mobile terminal of the manager through the security monitoring platform; if the spread coefficient MY is greater than or equal to the spread threshold MYmax, it is determined that the spread trend of the fire point does not meet the requirements, a spread control signal is generated and the spread control signal is sent to the mobile terminal of the manager through the security monitoring platform.

[0018] Furthermore, the working method of the intelligent building fire safety monitoring system based on artificial intelligence includes the following steps:

[0019] Step 1: Conduct fire safety monitoring and analysis on intelligent buildings: Set up detection points in the intelligent building, set up detection terminals at the detection points, and obtain the air temperature value KW and smoke concentration value YW of the detection points in real time through the detection terminals, and perform numerical calculations to obtain the monitoring coefficient JC;

[0020] Step 2: Analyze the overall fire risk of the intelligent building: mark the detection point as a safe point or a risk point through the monitoring coefficient JC, and judge whether the fire safety of the intelligent building meets the requirements based on the marking results of the safe point and the risk point. If it does not meet the requirements, execute step 3;

[0021] Step 3: All risk points are combined according to the floors where they are located to obtain several risk data groups, and the control decision is determined by the number of risk points in the risk data groups;

[0022] Step 4: Further analyze the fire control decision of the risk data group and obtain the spread coefficient MY of the fire point. Generate a spread control signal or a central control signal through the spread coefficient MY and send it to the mobile phone terminal of the manager.

[0023] The present invention has the following beneficial effects:

[0024] 1. The safety monitoring module can be used to monitor and analyze the fire safety of intelligent buildings. Multiple detection points are set on each floor of the intelligent building, and the fire hazard parameters of the detection points are monitored in real time according to the detection terminal. The monitoring coefficient is calculated for multiple parameters, so as to evaluate the safety of the detection points through the monitoring coefficient;

[0025] 2. The risk analysis module can be used to analyze the overall fire risk of intelligent buildings. In the case of risk points, the risk points are grouped according to the floors to obtain risk data groups, so as to conduct risk point distribution analysis for each risk data group and adopt different fire control methods for different floors;

[0026] 3. The decision-making processing module can be used to analyze the fire control decisions of the risk data group, and the spread coefficient can be calculated by combining multiple risk parameters about the fire point in the risk data group. The fire spread trend on the floor where the fire point is located can be evaluated based on the spread coefficient. Then, the most appropriate control measures can be taken based on the evaluation results to control the fire and improve the efficiency of fire handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 is a system block diagram of Embodiment 1 of the present invention;

[0029] Figure 2This is a flow chart of the method of Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0030] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] Embodiment 1

[0032] like Figure 1 As shown, an intelligent building fire safety monitoring system based on artificial intelligence includes a security monitoring platform, which is communicatively connected to a security monitoring module, a risk analysis module, a decision processing module and a database, and the risk analysis module is also communicatively connected to an instant control module.

[0033] The safety monitoring module is used to perform fire safety monitoring and analysis on intelligent buildings: detection points are set up in the intelligent buildings, detection terminals are set up at the detection points, and the air temperature value KW and smoke concentration value YW of the detection points are obtained in real time through the detection terminals. The monitoring coefficient JC of the detection points is obtained by the formula JC=a1*KW+a2*YW, where a1 and a2 are both proportional coefficients, and a1>a2>1; the monitoring coefficient JC of all detection points is sent to the risk analysis module through the safety monitoring platform; multiple detection points are set up on each floor of the intelligent building, and the fire hazard parameters of the detection points are monitored in real time according to the detection terminals, and the monitoring coefficient is calculated for multiple parameters, so as to evaluate the safety level of the detection points through the monitoring coefficient.

[0034] The risk analysis module is used to analyze the overall fire risk of intelligent buildings: retrieve the monitoring threshold JCmax through the database, and compare the monitoring coefficient JC of the detection point with the monitoring threshold JCmax: if the monitoring coefficient JC is less than the monitoring threshold JCmax, it is determined that the fire safety hazard of the detection point meets the requirements, and the corresponding detection point is marked as a safe point; if the monitoring coefficient JC is greater than or equal to the monitoring threshold JCmax, it is determined that the fire safety hazard of the detection point does not meet the requirements, and the corresponding detection point is marked as a risk point; determine whether all detection points are marked as safe points: if so, it is determined that the fire safety of the intelligent building meets the requirements; if not, first generate a risk warning signal and send the risk warning signal to the immediate control module. After receiving the risk warning signal, the immediate control module controls the risk point The fire handling facilities in the area are turned on, and then all risk points are combined according to the floors they are on to obtain several risk data groups, and the risk points in each risk data group are on the same floor; determine whether the number of risk points in the risk data group is less than L1: if so, the risk point with the largest monitoring coefficient JC value in the risk data group is marked as the fire point, and a decision processing signal is generated and the decision processing signal and the fire point are sent to the decision processing module; if not, a spread control signal is generated and sent to the mobile phone terminal of the manager through the security monitoring platform; in the case of risk points, the risk points are grouped according to the floors to obtain risk data groups, so as to perform risk point distribution analysis for each risk data group, and adopt different fire control methods for different floors.

[0035] The decision processing module is used to analyze the fire control decision of the risk data group: the hidden danger threshold YH is obtained by the formula YH=t1*JCmax, the detection point whose monitoring coefficient JC is not less than the hidden danger threshold YH on the same floor is marked as the hidden danger point, the straight-line distance between the hidden danger point and the fire point is marked as the straight-line distance value of the hidden danger point, and the hidden danger point with the largest straight-line value is marked as the spread boundary point. A circle is drawn with the fire point as the center and the straight-line distance value of the spread boundary point as the radius to obtain the spread prediction range, and the ratio of the number of hidden danger points within the spread prediction range to the number of detection points is marked as the trend data QS of the spread prediction range, the ratio of the area value of the spread prediction range to the area value of the floor where the fire point is located is marked as the spatial data KJ of the spread prediction range, the ratio of the number of floors of the fire point to the total number of floors of the intelligent building is marked as the vertical data CZ, the detection points are sorted in the order of the straight-line distance value to the center point of the floor from near to far to obtain the center sequence, and the ratio of the sequence number of the fire point in the center sequence to the number of all detection points on the floor is marked as the center data ZX; by the formula The spread coefficient MY of the fire point is obtained, where k1, k2, k3 and k4 are all proportional coefficients, and k1>k2>k3>k4>1; the spread threshold MYmax is obtained through the database, and the spread coefficient MY is compared with the spread threshold MYmax: if the spread coefficient MY is less than the spread threshold MYmax, it is determined that the spread trend of the fire point meets the requirements, and a central control signal is generated and sent to the mobile terminal of the manager through the security monitoring platform; if the spread coefficient MY is greater than or equal to the spread threshold MYmax, it is determined that the spread trend of the fire point does not meet the requirements, and a spread control signal is generated and sent to the mobile terminal of the manager through the security monitoring platform; the spread coefficient is calculated by combining multiple risk parameters about the fire point in the risk data group, and the fire spread trend of the floor where the fire point is located is evaluated according to the spread coefficient, and then the most appropriate control measures are taken according to the evaluation results to control the fire and improve the handling efficiency during fire.

[0036] Embodiment 2

[0037] like Figure 2 As shown, an intelligent building fire safety monitoring method based on artificial intelligence includes the following steps:

[0038] Step 1: Conduct fire safety monitoring and analysis on intelligent buildings: Set up detection points in the intelligent building, set up detection terminals at the detection points, and obtain the air temperature value KW and smoke concentration value YW of the detection points in real time through the detection terminals, and perform numerical calculations to obtain the monitoring coefficient JC;

[0039] Step 2: Analyze the overall fire risk of the intelligent building: mark the detection point as a safe point or a risk point through the monitoring coefficient JC, and judge whether the fire safety of the intelligent building meets the requirements based on the marking results of the safe point and the risk point. If it does not meet the requirements, execute step 3;

[0040] Step 3: All risk points are combined according to the floors where they are located to obtain several risk data groups, and the control decision is determined by the number of risk points in the risk data groups;

[0041] Step 4: Further analyze the fire control decision of the risk data group and obtain the spread coefficient MY of the fire point. Generate a spread control signal or a central control signal through the spread coefficient MY and send it to the mobile phone terminal of the manager.

[0042] An intelligent building fire safety monitoring system based on artificial intelligence, when working, sets detection points in the intelligent building, sets detection terminals at the detection points, obtains the air temperature value KW and the smoke concentration value YW of the detection points in real time through the detection terminals, and performs numerical calculation to obtain the monitoring coefficient JC; marks the detection points as safe points or risk points through the monitoring coefficient JC, and judges whether the fire safety of the intelligent building meets the requirements according to the marking results of the safe points and risk points, and executes step three when the requirements are not met; combines all risk points according to the floors where they are located to obtain several risk data groups, and judges the control decision by the number of risk points in the risk data groups; further analyzes the fire control decision of the risk data group and obtains the spread coefficient MY of the fire starting point, and generates a spread control signal or a central control signal through the spread coefficient MY and sends it to the mobile phone terminal of the manager.

[0043] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0044] The above formulas are obtained by collecting a large amount of data and performing software simulation to select a formula close to the actual value. The coefficients in the formula are set by technicians in this field according to actual conditions; for example: Formula A technician in this field collects multiple groups of sample data and sets a corresponding spreading coefficient for each group of sample data; substitutes the set harmful coefficient and the collected sample data into the formula, and any four formulas constitute a four-variable linear equation system. The calculated coefficients are screened and averaged, and the values ​​of k1, k2, k3 and k4 are obtained to be 3.82, 3.47, 2.63 and 2.19 respectively;

[0045] The size of the coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the coefficient depends on the amount of sample data and the preliminary setting of the corresponding spread coefficient for each set of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantified value, such as the spread coefficient is proportional to the value of the trend data.

[0046] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0047] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An intelligent building fire safety monitoring system based on artificial intelligence, characterized in that: It includes a security monitoring platform, which is communicatively connected to a security monitoring module, a risk analysis module, a decision processing module and a database, and the risk analysis module is also communicatively connected to an immediate control module; The safety monitoring module is used to perform fire safety monitoring and analysis on intelligent buildings: detection points are set in the intelligent building, and the monitoring coefficients JC of the detection points are obtained in real time; the monitoring coefficients JC of all detection points are sent to the risk analysis module through the safety monitoring platform; The risk analysis module is used to analyze the overall fire risk of the intelligent building: the detection point is marked as a safe point or a risk point through the monitoring coefficient KC of the detection point; whether all the detection points are marked as safe points is determined: if so, it is determined that the fire safety of the intelligent building meets the requirements; if not, firstly, a risk warning signal is generated and sent to the immediate control module, and after receiving the risk warning signal, the immediate control module controls the fire treatment facilities in the area where the risk point is located to start, and then all the risk points are combined according to the floors where they are located to obtain several risk data groups, and the risk points in each risk data group are located on the same floor; whether a control decision analysis is needed is determined according to the number of risk points in the risk data group; The decision processing module is used to analyze the fire control decision of the risk data group.

2. The intelligent building fire safety monitoring system based on artificial intelligence according to claim 1 is characterized in that: The acquisition process of the detection point JC includes: setting a detection terminal at the detection point and obtaining the air temperature value KW and the smoke concentration value YW of the detection point in real time through the detection terminal, and performing numerical calculation on the air temperature value KW and the smoke concentration value YW to obtain the monitoring coefficient JC of the detection point.

3. The intelligent building fire safety monitoring system based on artificial intelligence according to claim 2 is characterized in that: The specific process of marking a detection point as a safe point or a risk point includes: retrieving the monitoring threshold JCmax through the database, and comparing the monitoring coefficient JC of the detection point with the monitoring threshold JCmax: if the monitoring coefficient JC is less than the monitoring threshold JCmax, it is determined that the fire safety hazard of the detection point meets the requirements, and the corresponding detection point is marked as a safe point; if the monitoring coefficient JC is greater than or equal to the monitoring threshold JCmax, it is determined that the fire safety hazard of the detection point does not meet the requirements, and the corresponding detection point is marked as a risk point.

4. The intelligent building fire safety monitoring system based on artificial intelligence according to claim 3 is characterized in that: The specific process of determining whether a control decision analysis is needed includes: determining whether the number of risk points in the risk data group is less than L1: if so, marking the risk point with the largest monitoring coefficient JC value in the risk data group as the fire point, generating a decision processing signal and sending the decision processing signal and the fire point to the decision processing module; if not, generating a spread control signal and sending the spread control signal to the manager's mobile terminal through the security monitoring platform.

5. The intelligent building fire safety monitoring system based on artificial intelligence according to claim 4 is characterized in that: The specific process of the decision processing module analyzing the fire control decision of the risk data group includes: obtaining trend data QS, spatial data KJ, vertical data CZ and center data ZX; The spread coefficient MY of the fire point is obtained, where k1, k2, k3 and k4 are all proportional coefficients, and k1>k2>k3>k4>1; the spread threshold MYmax is obtained through the database, the spread coefficient MY is compared with the spread threshold MYmax, and a spread control signal or a central control signal is generated based on the comparison result and sent to the mobile terminal of the manager.

6. The intelligent building fire safety monitoring system based on artificial intelligence according to claim 5 is characterized in that: The process of acquiring trend data QS, spatial data KJ, vertical data CZ and center data ZX includes: obtaining a hidden danger threshold value YH through the formula YH=t1*JCmax, marking the detection point whose monitoring coefficient JC is not less than the hidden danger threshold value YH on the same floor as a hidden danger point, marking the straight-line distance between the hidden danger point and the fire point as the straight-line distance value of the hidden danger point, marking the hidden danger point with the largest straight-line distance value as a spreading boundary point, drawing a circle with the fire point as the center and the straight-line distance value of the spreading boundary point as the radius to obtain a spreading prediction range, marking the ratio of the number of hidden danger points to the number of detection points within the spreading prediction range as the trend data QS of the spreading prediction range, marking the ratio of the area value of the spreading prediction range to the area value of the floor where the fire point is located as the spatial data KJ of the spreading prediction range, marking the ratio of the number of floors of the fire point to the total number of floors of the intelligent building as the vertical data CZ, sorting the detection points in the order of the straight-line distance values ​​to the center point of the floor from near to far to obtain a center sequence, and marking the ratio of the sequence number of the fire point in the center sequence to the number of all detection points on the floor as the center data ZX.

7. The intelligent building fire safety monitoring system based on artificial intelligence according to claim 6 is characterized in that: The specific process of comparing the spread coefficient MY with the spread threshold MYmax includes: if the spread coefficient MY is less than the spread threshold MYmax, it is determined that the spread trend of the fire point meets the requirements, a central control signal is generated and the central control signal is sent to the mobile terminal of the manager through the security monitoring platform; if the spread coefficient MY is greater than or equal to the spread threshold MYmax, it is determined that the spread trend of the fire point does not meet the requirements, a spread control signal is generated and the spread control signal is sent to the mobile terminal of the manager through the security monitoring platform.

8. An intelligent building fire safety monitoring system based on artificial intelligence according to any one of claims 1 to 7, characterized in that: The working method of the intelligent building fire safety monitoring system based on artificial intelligence includes the following steps: Step 1: Conduct fire safety monitoring and analysis on intelligent buildings: Set up detection points in the intelligent building, set up detection terminals at the detection points, and obtain the air temperature value KW and smoke concentration value YW of the detection points in real time through the detection terminals, and perform numerical calculations to obtain the monitoring coefficient JC; Step 2: Analyze the overall fire risk of the intelligent building: mark the detection point as a safe point or a risk point through the monitoring coefficient JC, and judge whether the fire safety of the intelligent building meets the requirements based on the marking results of the safe point and the risk point. If it does not meet the requirements, execute step 3; Step 3: All risk points are combined according to the floors where they are located to obtain several risk data groups, and the control decision is determined by the number of risk points in the risk data groups; Step 4: Further analyze the fire control decision of the risk data group and obtain the spread coefficient MY of the fire point. Generate a spread control signal or a central control signal through the spread coefficient MY and send it to the mobile phone terminal of the manager.

Images