Fire safety monitoring method and device for smart building and electronic equipment
Through multiple smoke alarms, a fire source positioning model is constructed, which solves the problem of inefficient traditional manual positioning, achieves efficient and accurate fire rescue, and reduces fire losses.
Patent Information
- Application Number
- CN202411192484.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-28
- Publication Date
- 2024-12-03
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional fire rescue methods rely on manual positioning, are inefficient and have safety risks, resulting in low fire rescue efficiency.
Through multiple smoke alarms simultaneously monitoring the smoke concentration and combining position data, a fire source positioning model based on actual data is built, and computer programs are used to achieve automated and intelligent processing, quickly determine the location of the fire source, and reduce human operation errors and delays.
It improves the efficiency, accuracy and safety of fire rescue, reduces the losses of fire to personnel, property and environment, and can extinguish the fire source in a timely manner to prevent the spread of the fire.
Smart Images

Figure CN119068621A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of data processing, and specifically to a fire safety monitoring method, device and electronic equipment for a smart building. Background Art
[0002] Fire is a highly destructive and dangerous disaster that can be caused by a variety of reasons, such as electrical short circuits, gas leaks, open flames, etc. During fire rescue, determining the location of the fire source is one of the top priorities, because only by accurately finding the fire source can we effectively carry out fire extinguishing and rescue work, prevent the fire from spreading further, and reduce casualties and property losses.
[0003] At present, the traditional approach relies on firefighters to manually enter the fire scene for investigation. However, since manual positioning requires firefighters to check one by one, this process may take a long time, resulting in low efficiency of fire rescue.
[0004] Therefore, there is an urgent need for a fire safety monitoring method, device and electronic equipment for smart buildings. Summary of the invention
[0005] The present application provides a fire safety monitoring method, device and electronic equipment for a smart building, which is convenient for improving the efficiency of fire rescue.
[0006] In a first aspect of the present application, a fire safety monitoring method for a smart building is provided, the method comprising: obtaining actual smoke concentrations monitored by multiple smoke alarms; determining a collection time corresponding to each of the actual smoke concentrations; sorting the multiple collection times in chronological order, and determining an initial time according to the sorting result, the initial time being the earliest time among the multiple collection times; determining, according to the collection time and the initial time, the diffusion time of the fire smoke from the actual fire source location to the detection of the smoke alarm; and determining the actual fire source location based on the diffusion time, the location data of the smoke alarm and the actual smoke concentration.
[0007] By adopting the above technical solution, a more comprehensive smoke diffusion map can be formed by simultaneously monitoring the smoke concentration through multiple smoke alarms and combining their location data. This helps to locate the fire source more accurately, because the fire source usually releases smoke in multiple directions. By recording the collection time when each smoke alarm detects smoke and determining the initial time (i.e., the earliest time when smoke is detected), the starting time and diffusion speed of the fire can be quickly understood. This helps the fire department to respond in time and formulate a rescue plan. Using the collected smoke concentration data, time and location data, a fire source location model based on actual data can be constructed. This model is not affected by human factors and can provide more objective and accurate results. Smoke alarms usually sense the occurrence of fire earlier than people. In this way, the location of the fire source can be determined earlier, thereby buying more time for personnel evacuation and fire fighting. Once the location of the fire source is determined, the fire department can adjust the rescue strategy according to the actual situation, such as selecting the best rescue route, deploying sufficient firefighting equipment and personnel, etc. Accurate fire source location helps to reduce the loss of fire to people, property and the environment. By extinguishing the fire source in time, the fire can be prevented from spreading further and the degree of damage caused by the fire can be reduced. This method can achieve automated and intelligent processing through computer programs, reduce errors and delays in human operations, and improve the efficiency of fire rescue.
[0008] Optionally, determining the actual fire source location based on the diffusion time, the position data of the smoke alarm and the actual smoke concentration specifically includes: determining a target alarm corresponding to the initial moment among the multiple smoke alarms; generating multiple predicted fire source locations according to the target position of the target alarm, wherein the distance between any one of the predicted fire source locations and the target location is less than a preset distance, and one diffusion time corresponds to one predicted fire source location; generating a prediction parameter group according to each predicted fire source location, wherein each prediction parameter group includes a predicted smoke concentration, and one prediction parameter group corresponds to one predicted fire source location; determining a target parameter group among the multiple prediction parameter groups, wherein the difference between the predicted smoke concentration of the target parameter group and the actual smoke concentration meets a preset condition; and determining that the predicted fire source location corresponding to the target parameter group is the actual fire source location.
[0009] By adopting the above technical solution, by collecting and analyzing data from multiple smoke alarms, including the initial moment and location of their detection of smoke, and the actual smoke concentration, this method can provide a fire source location prediction based on actual data. This data-driven method is usually more accurate than traditional, experience-based methods. Considering multiple parameters (such as diffusion time, location data, and actual smoke concentration) to determine the fire source location can provide a more comprehensive understanding of the fire situation. This method can reduce the error caused by a single parameter and improve the reliability of positioning. Based on the location of the target alarm, multiple predicted fire source locations are generated, and the distance from these locations to the target location is less than the preset distance. This method takes into account the uncertainty of smoke diffusion from the fire source and improves the flexibility of fire source location prediction. By generating a set of prediction parameters (including predicted smoke concentration) and comparing it with the actual smoke concentration, the predicted fire source location closest to the actual fire source location can be determined. This parameter verification-based method can further improve the accuracy of fire source location prediction. Once the smoke alarm detects smoke, the system can immediately start analyzing the data and predicting the fire source location. This real-time performance is crucial for fire rescue because it can help fire departments make decisions quickly and take timely actions. Accurate fire source location prediction helps fire departments allocate resources more effectively, such as fire trucks, fire equipment, and rescue personnel. This ensures that there are enough resources at the fire scene to deal with the fire, reducing casualties and property losses. Based on accurate fire source location prediction, fire departments can formulate more scientific rescue strategies, such as selecting the best rescue route, determining priority fire extinguishing areas, etc. This helps improve the effectiveness and efficiency of rescue operations.
[0010] Optionally, the prediction parameter group further includes a unit smoke volume released from the fire source position per unit time and a smoke diffusion coefficient, and the preset parameter group and the predicted fire source position satisfy the following relationship: ; Among them, (X i , Y i ) is the i-th predicted fire source location, C(x i ,y i , T i ) is the predicted smoke density included in the i-th prediction parameter group, Q i is the unit smoke volume included in the i-th prediction parameter group, D i is the smoke diffusion coefficient included in the i-th prediction parameter group, (x i ,y i ) is the location data of the i-th smoke alarm, T i is the i-th diffusion duration.
[0011] By adopting the above technical solution, by introducing unit smoke volume and smoke diffusion coefficient, combined with mathematical models, the smoke concentration can be predicted more scientifically and accurately, and then the location of the fire source can be determined. The various parameters and variables in the formula can comprehensively consider various practical factors, making the prediction more accurate. This method is based on the physical law of smoke diffusion. By calculating the change of smoke concentration through a mathematical model, it can more realistically reflect the smoke diffusion process and avoid relying solely on empirical judgment. Using a formulaic calculation method, a large amount of smoke concentration data can be efficiently processed, and the prediction results can be quickly obtained, saving time and improving rescue efficiency. By continuously updating the smoke alarm data and diffusion model parameters, the prediction results can be adjusted in real time, dynamically responding to fire changes, and providing the latest fire source location in a timely manner. Mathematical models and formula calculations can reduce the errors caused by human judgment and improve the objectivity and consistency of the prediction results. Through this scientific and accurate prediction method, the fire source can be accurately located at the early stage of the fire, and measures can be taken quickly to extinguish the fire, thereby reducing the loss of personnel and property caused by the fire. This method is of great significance for improving the efficiency of fire rescue, reducing personnel risks and enhancing emergency response capabilities. In practical applications, it can greatly improve the scientificity and effectiveness of fire response.
[0012] Optionally, before determining the target parameter group in the plurality of prediction parameter groups, the method further includes: determining the actual smoke concentration corresponding to each of the predicted smoke concentrations according to the diffusion duration; and calculating the residual sum of squares included in the prediction parameter group according to the predicted smoke concentration and the actual smoke concentration, specifically by the following formula: ; Among them, S(θ i ) is the ith residual sum of squares, C(x i ,y i , T i ) is the predicted smoke density included in the i-th prediction parameter group, C i is the actual smoke concentration of the ith instance.
[0013] By adopting the above technical solution, calculating the residual sum of squares can quantify the difference between the predicted smoke concentration and the actual smoke concentration, providing a clear indicator to evaluate the accuracy of the prediction model. By analyzing the residual sum of squares, the deficiencies in the prediction model can be identified, and the model parameters can be further optimized to improve the accuracy of the overall prediction. The residual sum of squares is an error measurement method that can scientifically and objectively quantify the prediction error, making the model evaluation more standardized. By calculating the residual sum of squares for each prediction parameter group, the target parameter group with the smallest prediction error can be effectively screened out, thereby determining the most likely fire source location. The residual sum of squares provides an objective evaluation standard, reduces the influence of human subjective judgment, and improves the reliability and scientificity of decision-making. In practical applications, as more actual data is obtained, the model can be dynamically adjusted, and the prediction results can be optimized in real time by continuously calculating the residual sum of squares to maintain high accuracy.
[0014] Optionally, determining a target parameter group among the multiple prediction parameter groups specifically includes: calculating a function difference between a first residual sum of squares and a second residual sum of squares, the first residual sum of squares being the residual sum of squares corresponding to the first parameter group, the second residual sum of squares being the residual sum of squares corresponding to the second parameter group, the first parameter group being any one of the multiple prediction parameter groups, and the second parameter group being adjacent to the first parameter group; if it is determined that the function difference is less than or equal to a preset threshold, determining that the first parameter group is the target parameter group.
[0015] By adopting the above technical solution, by comparing the residual sum of squares of adjacent parameter groups, the target parameter group with the smallest prediction error can be screened out more accurately, thereby determining the most likely fire source location. Compared with the global comparison of all parameter groups, the difference of the residual sum of squares of adjacent parameter groups can be compared step by step, which can reduce the computational complexity and improve the computational efficiency. By comparing adjacent parameter groups, the over-adjustment of the prediction model can be avoided, and the stability and consistency of the model can be ensured. Through the preset threshold of the function difference, the screening criteria can be flexibly adjusted, the model selection can be optimized according to the specific application requirements, and the applicability of the model can be improved. The comparison of the residual sum of squares difference based on actual data provides an objective, data-driven decision support method, which reduces the influence of subjective factors. During the fire rescue process, the residual sum of squares difference of the parameter group can be updated and compared in real time, and the fire source location model can be dynamically adjusted and optimized to ensure real-time and accuracy. Through step-by-step optimization and screening, the prediction error can be effectively reduced, the accuracy and reliability of the overall prediction can be improved, and the accuracy of fire source location can be ensured.
[0016] Optionally, obtaining the actual smoke concentration monitored by multiple smoke alarms specifically includes: receiving corresponding original smoke concentration data sent by the multiple smoke alarms; preprocessing the original smoke concentration data to obtain the actual smoke concentration, and the preprocessing includes denoising, filtering and normalization.
[0017] By adopting the above technical solutions, the denoising and filtering in the preprocessing step can effectively remove noise and outliers in the data, improve the accuracy of the data, and ensure that the subsequent analysis is based on a reliable data foundation. Normalization processing can convert data of different magnitudes to the same magnitude, improve the consistency of the data, make the data of different smoke alarms comparable, and facilitate comprehensive analysis. The actual smoke concentration data obtained by preprocessing is smoother and more stable, which can effectively improve the stability and accuracy of subsequent model predictions and reduce errors caused by data fluctuations. Preprocessing can improve the signal-to-noise ratio of the data, making useful information more prominent, which is convenient for subsequent data analysis and fire source location. Through denoising and filtering, the false alarm rate caused by noise and mutation data can be reduced, and the reliability of the fire monitoring system can be improved. The preprocessing step can be performed in real time after the data is received, ensuring real-time and rapid response capabilities, which helps to timely discover and locate the fire source. The preprocessed data is more standardized and standardized, which simplifies the subsequent analysis steps and improves the efficiency and accuracy of the analysis. Accurate and stable actual smoke concentration data can provide a reliable basis for subsequent fire source location and decision-making, and improve the scientificity and reliability of decision-making.
[0018] Optionally, the method further includes: inputting the actual fire source location into a preset building model to obtain a target display model; sending the target display model to a user device to display the target display model to a user corresponding to the user device via the user device.
[0019] By adopting the above technical solution, by generating and sending the target display model, key information such as the location of the fire source can be quickly and accurately transmitted to relevant personnel, thereby improving the efficiency of information transmission. The target display model displays the location of the fire source in a visual way on the user device, so that the user can intuitively understand the specific situation and location of the fire source, and improve the efficiency of understanding and decision-making. Users can view the location of the fire source and the surrounding environment in real time through the user device, quickly formulate and adjust the emergency response plan, and improve the emergency response capability. The target display model can be displayed on different devices, supporting remote monitoring and command, so that decision makers can obtain key information anytime and anywhere, and conduct remote command and coordination. By sending the target display model to multiple user devices, different personnel can share the same information, work together, and improve the overall rescue efficiency. The visual target display model can reduce misjudgments and errors in the transmission of text and oral information, ensuring that each relevant person can accurately understand the location of the fire source and the situation on the scene. The generated target display model can be saved as a historical record of fire handling, which is convenient for post-analysis and summary, and improves the experience and ability of future emergency handling.
[0020] In a second aspect of the present application, a fire safety monitoring device for a smart building is provided, the fire safety monitoring device comprising an acquisition module and a processing module, wherein the acquisition module is used to acquire the actual smoke concentration monitored by multiple smoke alarms; the processing module is used to determine the collection time corresponding to each of the actual smoke concentrations; the processing module is also used to sort the multiple collection times in chronological order, and determine the initial time according to the sorting result, the initial time being the earliest time among the multiple collection times; the processing module is also used to determine the diffusion time of the fire smoke from the actual fire source location to the detection of the smoke alarm based on the collection time and the initial time; the processing module is also used to determine the actual fire source location based on the diffusion time, the position data of the smoke alarm and the actual smoke concentration.
[0021] In the third aspect of the present application, an electronic device is provided, which includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs the method described above.
[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, the method described above is executed.
[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By monitoring smoke concentration through multiple smoke alarms at the same time and combining their location data, a more comprehensive smoke diffusion map can be formed. This helps to locate the fire source more accurately, because the fire source usually releases smoke in multiple directions. By recording the collection time when each smoke alarm detects smoke and determining the initial time (that is, the earliest time when smoke is detected), the starting time and diffusion speed of the fire can be quickly understood. This helps the fire department to respond in time and formulate a rescue plan. Using the collected smoke concentration data, time and location data, a fire source location model based on actual data can be constructed. This model is not affected by human factors and can provide more objective and accurate results. Smoke alarms usually sense the occurrence of fires earlier than people. In this way, the location of the fire source can be determined earlier, thereby buying more time for personnel evacuation and fire fighting. Once the location of the fire source is determined, the fire department can adjust the rescue strategy according to the actual situation, such as selecting the best rescue route, deploying sufficient firefighting equipment and personnel, etc. Accurate fire source location helps to reduce the loss of fire to people, property and the environment. By extinguishing the fire source in time, the fire can be prevented from spreading further and the degree of damage caused by the fire can be reduced. This method can realize automatic and intelligent processing through computer programs, reduce errors and delays in human operations, and improve the efficiency of fire rescue; 2. By introducing unit smoke volume and smoke diffusion coefficient, combined with mathematical models, the smoke concentration can be predicted more scientifically and accurately, and then the location of the fire source can be determined. The various parameters and variables in the formula can comprehensively consider various practical factors, making the prediction more accurate. This method is based on the physical law of smoke diffusion. By calculating the change of smoke concentration through a mathematical model, it can more realistically reflect the smoke diffusion process and avoid relying solely on empirical judgment. Using a formulaic calculation method, a large amount of smoke concentration data can be efficiently processed, and the prediction results can be quickly obtained, saving time and improving rescue efficiency. By continuously updating the smoke alarm data and diffusion model parameters, the prediction results can be adjusted in real time, dynamically responding to fire changes, and providing the latest fire source location in a timely manner. Mathematical models and formula calculations can reduce the errors caused by human judgment and improve the objectivity and consistency of the prediction results. Through this scientific and accurate prediction method, the fire source can be accurately located at the early stage of the fire, and measures can be taken quickly to extinguish the fire, thereby reducing the loss of personnel and property caused by the fire. This method is of great significance for improving the efficiency of fire rescue, reducing personnel risks and enhancing emergency response capabilities. In practical applications, it can greatly improve the scientificity and effectiveness of fire response. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] Figure 1 A flow chart of a fire safety monitoring method for a smart building provided in an embodiment of the present application.
[0025] Figure 2Another flowchart of a fire safety monitoring method for a smart building provided in an embodiment of the present application.
[0026] Figure 3 A module schematic diagram of a fire safety monitoring device for a smart building provided in an embodiment of the present application.
[0027] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.
[0028] Explanation of the reference numerals: 31, acquisition module; 32, processing module; 41, processor; 42, communication bus; 43, user interface; 44, network interface; 45, memory. DETAILED DESCRIPTION
[0029] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.
[0030] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.
[0031] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.
[0032] Fire is a very destructive and dangerous disaster, and its causes are varied, such as electrical failure, gas leakage or open flames. In emergency fire rescue, quickly and accurately determining the location of the fire source is a crucial first step. This is because only by identifying the specific location of the fire source can firefighting and rescue operations be effectively carried out, thereby curbing the spread of the fire and minimizing casualties and property losses.
[0033] However, in the current fire rescue practice, we have to face a significant challenge, that is, the traditional method of over-reliance on firefighters to personally enter the fire scene for investigation. Although this traditional manual positioning method is necessary and reasonable to a certain extent, it obviously has many shortcomings. First of all, it consumes a lot of time, because firefighters need to check every corner of the fire scene one by one to find the specific location of the fire source. This point-by-point investigation method is not only inefficient, but also requires a lot of manpower and material resources. Secondly, the manual positioning method also increases the safety risks of firefighters, because the fire scene is often accompanied by high temperature, thick smoke and complex building structures, and accidents may occur if you are not careful. Therefore, this traditional method that relies on manual positioning undoubtedly limits the efficiency of fire rescue to a large extent, making it difficult for rescue work to achieve the expected results.
[0034] In order to solve the above technical problems, the present application provides a fire safety monitoring method for a smart building, referring to Figure 1 , Figure 1 A flow chart of a fire safety monitoring method for a smart building provided in an embodiment of the present application. The fire safety monitoring method is applied to a server and includes steps S110 to S150, which are as follows: S110: Acquire actual smoke concentrations monitored by multiple smoke alarms.
[0035] Specifically, a server refers to a computer system or device that is specifically used to process and store data. In an embodiment of the present application, the server is used to receive and process smoke concentration data from multiple smoke alarms. Obtaining the actual smoke concentration monitored by multiple smoke alarms refers to the server receiving and recording actual smoke concentration data from multiple smoke alarms installed in different locations. Multiple smoke alarms refer to multiple independent smoke detection devices installed in different locations or areas, which can monitor and report the smoke concentration at their respective locations. The actual smoke concentration refers to the smoke concentration value in the real environment detected by each smoke alarm.
[0036] For example, a large shopping mall has multiple smoke alarms installed on different floors and areas. The mall's control center has a server that receives and processes data from all smoke alarms. Smoke alarms are installed on each floor and each area of the mall (such as stores, corridors, parking lots, etc.). In this application, only the monitoring of multiple areas within one floor is considered, so the entire floor is regarded as a plane, and the subsequent calculations only consider the coordinates in the directions of the two coordinate axes, without considering the three-dimensional coordinates, in order to reduce the amount of real-time calculations.
[0037] Assume that a shopping mall has 5 floors, each floor has 10 areas, and a total of 50 smoke alarms. Each smoke alarm monitors the smoke concentration at its location in real time. For example, the smoke concentrations monitored by multiple smoke alarms on the first floor are as follows: the smoke concentration detected by the alarm in area A is 0.02mg / m³; the smoke concentration detected by the alarm in area B is 0.03mg / m³; the smoke concentration detected by the alarm in area C is 0.01mg / m³; the smoke concentration detected by the alarm in area D is 0.05mg / m³; the smoke concentration detected by the alarm in area E is 0.00mg / m³; these smoke alarms send the monitored smoke concentration data to the server in the shopping mall control center through the network (such as Wi-Fi, Ethernet).
[0038] In a possible implementation, obtaining the actual smoke concentration monitored by multiple smoke alarms specifically includes: receiving the corresponding original smoke concentration data sent by the multiple smoke alarms; preprocessing the original smoke concentration data to obtain the actual smoke concentration, the preprocessing including denoising, filtering and normalization.
[0039] Specifically, denoising is used to remove random noise from data to obtain a cleaner and more accurate signal. Filtering is used to reduce instantaneous, unreal mutation values by smoothing data to make the data more stable. Normalization is used to convert values of different ranges to a unified scale to make the data comparable.
[0040] For example, in a large office building, 5 smoke alarms are installed on the first floor, and the server needs to monitor the smoke concentration data on the first floor of the office building. Assume that the alarm in area A on the first floor sends the original smoke concentration data: 0.023mg / m³; the alarm in area B on the first floor sends the original smoke concentration data: 0.015mg / m³; the alarm in area C on the first floor sends the original smoke concentration data: 0.030mg / m³, and so on. The server will receive the original data sent by the 5 alarms. The original data may contain noise. For example, there may be sudden interference in the data of the alarm in area A on the first floor. The actual measured data should be 0.020mg / m³, but due to noise interference, it is measured to be 0.023mg / m³. Through denoising, the data is corrected to 0.020mg / m³.
[0041] Suppose the concentration measured by the alarm in area C on the first floor changes dramatically in a short period of time: 0.030mg / m³->0.050mg / m³->0.028mg / m³. Through filtering, these data are smoothed to 0.030mg / m³ to remove unstable mutation values. Suppose different alarms have different measurement ranges, for example, some alarms have a measurement range of 0-0.100mg / m³, while others have a measurement range of 0-0.050mg / m³. Through normalization, all data are converted to a unified range of 0-1, for example: 0.020mg / m³ of the alarm in area A on the first floor is converted to 0.20; 0.015mg / m³ of the alarm in area B on the first floor is converted to 0.30; 0.030mg / m³ of the alarm in area C on the first floor is converted to 0.60; Through denoising, filtering and normalization, the server obtains more accurate and standardized actual smoke concentration data, which can be further analyzed and applied.
[0042] S120: Determine the collection time corresponding to each actual smoke concentration.
[0043] Specifically, the collection time refers to the specific time point when each smoke concentration data is collected. This time point records the timestamp of the data for subsequent analysis and processing. For example, area A on the first floor: the actual concentration is 0.020 mg / m³, and the corresponding collection time is 2024-06-27, 10:01:15; area B on the first floor: the actual concentration is 0.015 mg / m³, and the corresponding collection time is 2024-06-27, 10:01:17; area C on the first floor: the actual concentration is 0.030 mg / m³, and the corresponding collection time is 2024-06-27, 10:01:20.
[0044] S130, sorting the multiple collection moments in chronological order, and determining an initial moment according to the sorting result, where the initial moment is the earliest moment among the multiple collection moments.
[0045] Specifically, each smoke alarm records the time point of the actual smoke concentration data. The server sorts the data in chronological order, arranging all the acquisition moments from early to late, with the initial moment being the earliest time point among all the acquisition moments. By sorting multiple acquisition moments in chronological order and determining the initial moment, the server can clarify the timeline of the fire event and support more accurate timing analysis and emergency response. This method can help managers quickly identify the location of the fire source and the development of the fire, formulate effective response measures, and reduce the risks and losses caused by the fire. In practical applications, this data processing method can significantly improve the overall efficiency and accuracy of the fire monitoring and emergency management system.
[0046] S140: Determine the diffusion time of the fire smoke from the actual fire source location to the detection of the smoke alarm according to the collection time and the initial time.
[0047] Specifically, each smoke alarm records the time point of smoke concentration data. The initial time refers to the earliest time point among all the collection times, which is usually regarded as the time when the smoke is first detected. The diffusion time refers to the length of time from the actual fire source location to the smoke alarm detection. Among them, the time required for smoke diffusion is determined by calculating the time difference between the collection time and the initial time of each smoke alarm.
[0048] For example, suppose the server receives the following smoke alarm data and its collection time: Area A on the 1st floor: concentration 0.020 mg / m³, collection time 2024-06-27, 10:01:15; Area B on the 1st floor: concentration 0.015 mg / m³, collection time 2024-06-27, 10:01:20; Area C on the 1st floor: concentration 0.030 mg / m³, collection time 2024-06-2 7, 10:01:25; Area D on the 1st floor: concentration 0.025 mg / m³, collection time is 2024-06-27, 10:01:10; Area E on the 1st floor: concentration 0.010 mg / m³, collection time is 2024-06-27, 10:01:30; Based on the above collection time, the server sorts these times and determines the earliest time point as the initial time: The initial time is 2024-06-27, 10: 01:10 (Area D on the 1st floor), the server calculates the time difference between the collection time and the initial time of each alarm, and determines the diffusion duration: Area A on the 1st floor: 2024-06-27, 10:01:15 to 2024-06-27, 10:01:10 = 5 seconds; Area B on the 1st floor: 2024-06-27, 10:01:20 to 2024-06-27, 10:01:10 = 10 seconds; Area C on the 1st floor: 2024-06-27, 10:01:25 to 2024-06-27, 10:01:10 = 15 seconds; Area D on the 1st floor: 2024-06-27, 10:01:10 to 2024-06-27, 10:01:10 = 0 seconds (the earliest smoke detection); Area E on the 1st floor: 2024-06-27, 10:01:30 to 2024-06-27, 10:01:10 = 20 seconds.
[0049] S150: Determine the actual fire source location based on the diffusion time, the location data of the smoke alarm, and the actual smoke concentration.
[0050] Specifically, the diffusion time is the time from the fire source to the time when each smoke alarm detects smoke, which is obtained by subtracting the time difference between the acquisition time and the initial time. The position data is the specific coordinate position of each smoke alarm on the floor. The actual smoke concentration is the pre-processed smoke concentration data, which represents the smoke concentration detected by the alarm.
[0051] For example, multiple smoke alarms are installed on the same floor of a large shopping mall. When a fire occurs at a certain moment, the server receives and records the smoke concentration data, collection time, and location data of each smoke alarm. The server receives data from the following five smoke alarms: Alarm A: location (2,3), concentration 0.020 mg / m³, collection time 2024-06-27, 10:01:15; Alarm B: location (5,7), concentration 0.015 mg / m³, collection time 2024-06-27, 10:01:20; Alarm C: location (8,6), concentration 0.030 mg / m³, collection time 2024-06-27, 10:01:25; Alarm D: location (1,1), concentration 0.025 mg / m³, collection time 2024-06-27, 10:01:10; Alarm E: location (3,8), concentration 0.010 mg / m³, collection time 2024-06-27, 10:01:30. Through sorting, it is determined that the earliest collection time (initial time) is 2024-06-27, 10:01:10 (D alarm).
[0052] The server calculates the diffusion time of each alarm: Alarm A: 2024-06-27, 10:01:15 to 2024-06-27, 10:01:10 = 5 seconds; Alarm B: 2024-06-27, 10:01:20 to 2024-06-27, 10:01:10 = 10 seconds; Alarm C: 2024-06-27, 10:01 :25 to 2024-06-27, 10:01:10=15 seconds; D alarm: 2024-06-27, 10:01:10 to 2024-06-27, 10:01:10=0 seconds (earliest smoke detection); E alarm: 2024-06-27, 10:01:30 to 2024-06-27, 10:01:10=20 seconds.
[0053] Therefore, by monitoring the smoke concentration through multiple smoke alarms at the same time and combining their location data, a more comprehensive smoke diffusion map can be formed. This helps to locate the fire source more accurately, because the fire source usually releases smoke in multiple directions. By recording the collection time when each smoke alarm detects smoke and determining the initial time (that is, the earliest time when smoke is detected), the starting time and diffusion speed of the fire can be quickly understood. This helps the fire department to respond in time and formulate a rescue plan. Using the collected smoke concentration data, time and location data, a fire source location model based on actual data can be constructed. This model is not affected by human factors and can provide more objective and accurate results. Smoke alarms usually sense the occurrence of fires earlier than people. In this way, the location of the fire source can be determined earlier, thereby buying more time for personnel evacuation and fire fighting. Once the location of the fire source is determined, the fire department can adjust the rescue strategy according to the actual situation, such as choosing the best rescue route, deploying sufficient firefighting equipment and personnel, etc. Accurate fire source location helps to reduce the loss of fire to people, property and the environment. By extinguishing the fire source in time, the fire can be prevented from spreading further and the degree of damage caused by the fire can be reduced. This method can achieve automated and intelligent processing through computer programs, reduce errors and delays in human operations, and improve the efficiency of fire rescue.
[0054] In a possible implementation, the actual fire source location is determined based on the diffusion time, the position data of the smoke alarm and the actual smoke concentration, specifically including: determining a target alarm corresponding to the initial moment among multiple smoke alarms; generating multiple predicted fire source locations according to the target position of the target alarm, wherein the distance between any predicted fire source location and the target location is less than a preset distance, and one diffusion time corresponds to one predicted fire source location; generating a prediction parameter group according to each predicted fire source location, wherein each prediction parameter group includes a predicted smoke concentration, and one prediction parameter group corresponds to one predicted fire source location; determining a target parameter group among multiple prediction parameter groups, wherein the difference between the predicted smoke concentration and the actual smoke concentration of the target parameter group meets a preset condition; and determining that the predicted fire source location corresponding to the target parameter group is the actual fire source location.
[0055] Specifically, the target alarm is the alarm that detects smoke the earliest, that is, the alarm corresponding to the initial moment. The target position is the specific coordinate position of the target alarm. The predicted fire source position is to generate multiple possible fire source positions based on the target position, and the distance between these positions and the target position is less than the preset maximum diffusion distance. Each predicted fire source position corresponds to a specific diffusion duration. Each predicted fire source position corresponds to a set of prediction parameters, including predicted smoke concentration, unit smoke volume released from the fire source per unit time, smoke diffusion coefficient, etc. The predicted smoke concentration is the smoke concentration of different predicted fire source positions calculated based on the diffusion model. The target parameter group is a parameter group selected from multiple prediction parameter groups with the smallest difference between the predicted smoke concentration and the actual smoke concentration. The preset condition is that the difference between the predicted concentration and the actual concentration is within a certain threshold range. The actual fire source position is the predicted fire source position corresponding to the target parameter group.
[0056] In a possible implementation, the prediction parameter group also includes a unit smoke volume released from the fire source position per unit time and a smoke diffusion coefficient, and the preset parameter group and the predicted fire source position satisfy the following relationship: ; Among them, (X i , Y i ) is the i-th predicted fire source location, C(x i ,y i , T i ) is the predicted smoke density included in the i-th prediction parameter group, Q i is the unit smoke volume included in the i-th prediction parameter group, D i is the smoke diffusion coefficient included in the i-th prediction parameter group, (x i ,y i ) is the location data of the i-th smoke alarm, T i is the i-th diffusion duration.
[0057] Specifically, the unit smoke volume Q i The amount of smoke released per unit time at each predicted fire source location. Smoke diffusion coefficient D i It is used to describe the diffusion speed and degree of smoke in the air. The denominator in the formula is used for normalization so that the integral of the concentration value in space is equal to the total release. The exponential part in the formula represents the attenuation of concentration with distance. It is based on the Gaussian distribution model (also known as normal distribution) and is used to describe the probability density of smoke diffusion. That is, the farther the distance, the more significant the concentration decay; the longer the time, the wider the diffusion and the lower the concentration.
[0058] For example, from the above example, we can see that the initial time is 2024-06-27, 10:01:10, and the corresponding target alarm is D alarm (position 1,1). Then, with the position of D alarm (1,1) as the center, multiple possible predicted fire source locations are generated. For example: (0.5,0.5), (1,1.5), (1.5,1), etc. Assume that the predicted fire source location is (1,1.5), and assume that: unit smoke volume Q i =0.5, smoke diffusion coefficient D i = 0.1, use the formula to calculate the predicted smoke concentration for each alarm. For alarm A (position 2, 3), the diffusion time is 5 seconds: ; According to the above formula, the predicted smoke concentration is 0.022mg / m³, the actual smoke concentration is 0.020mg / m³, and the difference is 0.002mg / m³. If the difference meets the preset conditions, such as less than 0.005mg / m³, the prediction parameter group is considered valid. Similarly, through multiple calculations and comparisons, the predicted fire source position with the smallest difference is determined to be the actual fire source position. Assuming that after calculation, the difference of the predicted fire source position (1,1.5) is the smallest, the actual fire source position is determined to be (1,1.5).
[0059] In a possible implementation, before determining the target parameter group in the plurality of prediction parameter groups, the method further includes: determining the actual smoke concentration corresponding to each predicted smoke concentration according to the diffusion time; and calculating the residual sum of squares included in the prediction parameter group according to the predicted smoke concentration and the actual smoke concentration, specifically by the following formula: ; Among them, S(θ i ) is the ith residual sum of squares, C(x i ,y i , T i ) is the predicted smoke density included in the i-th prediction parameter group, C i is the actual smoke concentration of the ith instance.
[0060] Specifically, the residual sum of squares S(θ i) is used to evaluate the difference between the predicted value and the actual value. The smaller the residual sum of squares, the smaller the difference between the predicted value and the actual value, and the higher the accuracy of the prediction. By comparing the residual sum of squares of different prediction parameter groups, the optimal prediction parameter group, that is, the target parameter group, can be found. By calculating the residual sum of squares between the predicted concentration and the actual concentration, the accuracy of the prediction can be effectively evaluated. The smaller the residual sum of squares, the more accurate the prediction. This method compares the residual sum of squares of different prediction parameter groups and ultimately determines the optimal prediction parameter group, and the corresponding predicted fire source location is the actual fire source location. This method can improve the accuracy and reliability of fire source location and help respond to fires more quickly and effectively.
[0061] For example, suppose there are three smoke alarms that detect the following concentration data: Alarm A: Location (2,3), actual concentration C A =0.020mg / m³; Alarm B: Position (5,7), Actual concentration C B =0.015mg / m³; Alarm C: Position (8,6), Actual concentration C C =0.030mg / m³. Assume that the predicted smoke concentration calculated by a certain prediction parameter group is as follows: Alarm A: predicted concentration C A '=0.018mg / m³; Alarm B: Predicted concentration C B '=0.016mg / m³; Alarm C: Predicted concentration C C '=0.028mg / m³. The residual sum of squares S(θ i ) is 0.000009, which means the sum of squares of the difference between the predicted concentration and the actual concentration. By calculating the residual sum of squares for different prediction parameter groups, the prediction parameter group with the smallest difference can be found, thereby determining the fire source location closest to the actual situation.
[0062] In a possible implementation, determining a target parameter group among multiple prediction parameter groups specifically includes: calculating a function difference between a first residual sum of squares and a second residual sum of squares, the first residual sum of squares being the residual sum of squares corresponding to the first parameter group, the second residual sum of squares being the residual sum of squares corresponding to the second parameter group, the first parameter group being any one of the multiple prediction parameter groups, and the second parameter group being adjacent to the first parameter group; if it is determined that the function difference is less than or equal to a preset threshold, determining the first parameter group as the target parameter group.
[0063] Specifically, this process is the process of model convergence for the diffusion model. The server selects two adjacent prediction parameter groups, calculates the difference between their corresponding residual sums of squares, and then compares the calculated function difference with the preset threshold. If the function difference is less than or equal to the preset threshold, it is considered that the residual sums of squares of the two parameter groups are close enough, and the i-th parameter group is the target parameter group. Among them, the function difference takes the absolute value of the difference. By comparing the difference in the residual sums of squares of adjacent prediction parameter groups, it can be determined which parameter groups have small enough differences, and further determine the optimal prediction parameter group (ie, the target parameter group). This method can effectively screen out the parameter group with the smallest prediction error, thereby more accurately locating the fire source.
[0064] For example, suppose there are three prediction parameter groups, and the residual sum of squares of each group is as follows: the first prediction parameter group: S(θ1)=0.0005; the second prediction parameter group: S(θ2)=0.0003; the third prediction parameter group: S(θ3)=0.0002; the preset threshold is 0.0002. The function difference between the first and second prediction parameter groups is 0.0002, and the function difference between the second and third prediction parameter groups is 0.0001, so the second prediction parameter group meets the conditions.
[0065] In one possible implementation, refer to Figure 2 , Figure 2 Another flow chart of a fire safety monitoring method for a smart building provided in an embodiment of the present application specifically includes steps S210 to S220, and the above steps are as follows: S210, input the actual fire source location into a preset building model to obtain a target display model; S220, send the target display model to a user device to display the target display model to a user corresponding to the user device through the user device.
[0066] Specifically, the server inputs the determined actual fire source location into the preset building model. The preset building model is a pre-built three-dimensional model of a building, which is used to visualize the internal structure of the building and the location of each room. By combining the actual fire source location with the preset building model, a target display model is generated. The target display model is a visualization model that contains the specific location of the actual fire source location in the building. The server sends the generated target display model to a user device, such as a mobile phone, tablet computer or computer. The user device can also be a portable device for firefighters or a monitoring device in a command center. After receiving the target display model, the user device displays it to the user through an application or special software. Users can see the specific location of the fire source location in the building on the device, helping them to better understand the fire situation and formulate a rescue plan. Among them, users can be fire rescue personnel or building managers, etc.
[0067] For example, suppose that the actual fire source location is determined to be the 5th floor, room 502. The preset building model is a three-dimensional model that includes all floors and rooms. The server inputs the fire source location of the 5th floor, room 502 into the preset building model to generate a target display model. The target display model clearly shows the layout of the 5th floor and marks the fire source location at room 502. The server sends the target display model to the fire captain's tablet and the firefighter's mobile phone. The fire captain opens the application on the tablet and sees the floor plan of the 5th floor. Room 502 is marked in red and displayed as the fire source location. The firefighter also sees the same fire source location mark on the mobile phone, which can quickly locate and formulate a rescue plan. Therefore, by inputting the actual fire source location into the preset building model to generate a target display model and sending it to the user device, the firefighter can intuitively see the specific location of the fire source location in the building. This method helps firefighters locate the fire source more quickly, improve rescue efficiency, and reduce losses caused by fire.
[0068] In one possible implementation, a method for constructing a preset building model is provided. First, a laser scanning technology (such as LiDAR) is used to perform a three-dimensional scan of the interior of the building to generate high-precision point cloud data, and the scan covers all floors, rooms, corridors and emergency exits. Then, the detailed floor plan and structural diagram of the building are collected as a basis for reference and correction of the point cloud data. The server also obtains and records the location and data of all smoke alarms, temperature sensors and other related equipment in the building. Among them, professional software (such as Autodesk Recap or PointCab) is used to process the point cloud data and convert it into a usable three-dimensional model. The point cloud data is filtered and streamlined to remove noise and unnecessary information. Secondly, the point cloud data is compared and merged with the building floor plan and structural diagram to ensure the accuracy of the three-dimensional model. Use three-dimensional modeling software (such as Revit or SketchUp) to import the processed point cloud data. Create a three-dimensional model of the building based on the point cloud data, including each floor, room, corridor and public area, and add elements such as doors, windows, stairs, elevators, etc. of the building, and add load-bearing walls, columns and other structural details according to the structural diagram.
[0069] The location of each smoke alarm and other sensors is marked in the model, and the server associates the sensor data with the corresponding location in the model to ensure that the model can dynamically display the sensor status. Use an IoT platform (such as AWSIoT or Google Cloud IoT) to integrate all sensor data for real-time monitoring and data updates. Finally, use modeling software to render the model to generate high-quality three-dimensional images to ensure that the model can be clearly displayed at different viewing angles and zoom levels. Combine virtual reality (VR) or augmented reality (AR) technology to create dynamic display effects, allowing users to browse immersively through devices (such as VR headsets and tablets).
[0070] For example, a six-story office building can be scanned using LiDAR to generate high-precision point cloud data. Collect the floor plan and structural drawings of the office building, as well as the location and data of all smoke alarms. Use Autodesk Recap to process the point cloud data and convert it into a 3D model. Merge the point cloud data with the floor plan and structural drawings to correct errors. Use Revit to import the point cloud data and create a 3D model of the office building. Add detailed information such as each floor, room, corridor, door, and window. Mark the location of all smoke alarms in the model and associate them with sensor data. Use the AWS IoT platform to integrate sensor data for real-time monitoring. Render the model to generate high-quality 3D images. In addition, a VR application can be developed to allow users to browse the model through a VR headset and click to view the data of each sensor. In addition, the model can be adjusted based on feedback to optimize file size and rendering speed. Therefore, by using laser scanning, point cloud data processing, 3D modeling software, and IoT technology, a high-precision preset building model can be constructed. This method can not only accurately reflect the physical structure of the building, but also display sensor data in real time, providing strong support for fire source location and fire response.
[0071] This application also provides a fire safety monitoring device for a smart building, referring to Figure 2 , Figure 2 A module schematic diagram of a fire safety monitoring device for a smart building provided in an embodiment of the present application. The fire safety monitoring device is a server, and the server includes an acquisition module 31 and a processing module 32, wherein the acquisition module 31 acquires the actual smoke concentration monitored by multiple smoke alarms; the processing module 32 determines the collection time corresponding to each actual smoke concentration; the processing module 32 sorts the multiple collection times in chronological order, and determines the initial time according to the sorting result, and the initial time is the earliest time among the multiple collection times; the processing module 32 determines the diffusion time of the fire smoke from the actual fire source location to the smoke alarm detection according to the collection time and the initial time; the processing module 32 determines the actual fire source location based on the diffusion time, the location data of the smoke alarm and the actual smoke concentration.
[0072] In a possible implementation, the processing module 32 determines the actual fire source location based on the diffusion time, the location data of the smoke alarm and the actual smoke concentration, specifically including: the processing module 32 determines the target alarm corresponding to the initial moment among multiple smoke alarms; the processing module 32 generates multiple predicted fire source locations according to the target position of the target alarm, wherein the distance between any predicted fire source location and the target location is less than a preset distance, and one diffusion time corresponds to one predicted fire source location; the processing module 32 generates a prediction parameter group according to each predicted fire source location, wherein each prediction parameter group includes a predicted smoke concentration, and one prediction parameter group corresponds to one predicted fire source location; the processing module 32 determines a target parameter group among multiple prediction parameter groups, wherein the difference between the predicted smoke concentration and the actual smoke concentration of the target parameter group meets a preset condition; the processing module 32 determines that the predicted fire source location corresponding to the target parameter group is the actual fire source location.
[0073] In a possible implementation, the prediction parameter group also includes a unit smoke volume released from the fire source position per unit time and a smoke diffusion coefficient, and the preset parameter group and the predicted fire source position satisfy the following relationship: ; Among them, (X i , Y i ) is the i-th predicted fire source location, C(x i ,y i , T i ) is the predicted smoke density included in the i-th prediction parameter group, Q i is the unit smoke volume included in the i-th prediction parameter group, D i is the smoke diffusion coefficient included in the i-th prediction parameter group, (x i ,y i ) is the location data of the i-th smoke alarm, T i is the i-th diffusion duration.
[0074] In a possible implementation, before the processing module 32 determines the target parameter group in the multiple prediction parameter groups, the method further includes: the processing module 32 determines the actual smoke concentration corresponding to each predicted smoke concentration according to the diffusion time; the processing module 32 calculates the residual sum of squares included in the prediction parameter group according to the predicted smoke concentration and the actual smoke concentration, specifically by the following formula: ; Among them, S(θ i ) is the ith residual sum of squares, C(x i ,y i , T i ) is the predicted smoke density included in the i-th prediction parameter group, C i is the actual smoke concentration of the ith instance.
[0075] In a possible implementation, the processing module 32 determines a target parameter group among multiple prediction parameter groups, specifically including: the processing module 32 calculates a function difference between a first residual sum of squares and a second residual sum of squares, the first residual sum of squares being the residual sum of squares corresponding to the first parameter group, the second residual sum of squares being the residual sum of squares corresponding to the second parameter group, the first parameter group being any one of the multiple prediction parameter groups, and the second parameter group being adjacent to the first parameter group; if the processing module 32 determines that the function difference is less than or equal to a preset threshold, then the first parameter group is determined to be the target parameter group.
[0076] In a possible implementation, the acquisition module 31 acquires the actual smoke concentration monitored by multiple smoke alarms, specifically including: the acquisition module 31 receives the corresponding original smoke concentration data sent by multiple smoke alarms; the processing module 32 preprocesses the original smoke concentration data to obtain the actual smoke concentration, and the preprocessing includes denoising, filtering and normalization.
[0077] In a possible implementation, the processing module 32 inputs the actual fire source location into a preset building model to obtain a target display model; the processing module 32 sends the target display model to the user device to display the target display model to a user corresponding to the user device through the user device.
[0078] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.
[0079] The present application also provides an electronic device, referring to Figure 4 , Figure 4 The electronic device may include: at least one processor 41 , at least one network interface 44 , a user interface 43 , a memory 45 , and at least one communication bus 42 .
[0080] The communication bus 42 is used to realize the connection and communication between these components.
[0081] The user interface 43 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 43 may also include a standard wired interface and a wireless interface.
[0082] The network interface 44 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).
[0083] Among them, the processor 41 may include one or more processing cores. The processor 41 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 45, and calling data stored in the memory 45. Optionally, the processor 41 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 41 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 41, and it can be implemented separately through a chip.
[0084] Among them, the memory 45 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 45 includes a non-transitory computer-readable storage medium. The memory 45 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 45 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 45 may also be optionally at least one storage device located away from the aforementioned processor 41. As Figure 4 As shown, the memory 45 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of a fire safety monitoring method for a smart building.
[0085] exist Figure 4In the electronic device shown, the user interface 43 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 41 can be used to call an application program for a fire safety monitoring method for a smart building stored in the memory 45. When executed by one or more processors, the electronic device executes one or more methods in the above-mentioned embodiments.
[0086] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.
[0087] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.
[0088] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0089] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.
[0090] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0091] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0092] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.
[0093] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.
Claims
1. A fire safety monitoring method for a smart building, characterized in that: The method comprises: Get the actual smoke concentration monitored by multiple smoke alarms; Determine the collection time corresponding to each actual smoke concentration; Sorting the plurality of collection moments in chronological order, and determining an initial moment according to the sorting result, wherein the initial moment is the earliest moment among the plurality of collection moments; Determine the diffusion time of the fire smoke from the actual fire source location to the detection of the smoke alarm according to the collection time and the initial time; The actual fire source position is determined based on the diffusion time, the position data of the smoke alarm and the actual smoke concentration.
2. The fire safety monitoring method for smart buildings according to claim 1 is characterized in that: The determining the actual fire source location based on the diffusion time, the location data of the smoke alarm and the actual smoke concentration specifically includes: Determining a target alarm corresponding to the initial moment among the plurality of smoke alarms; According to the target position of the target alarm, a plurality of predicted fire source positions are generated, wherein the distance between any one of the predicted fire source positions and the target position is less than a preset distance, and one diffusion time corresponds to one predicted fire source position; Generate a prediction parameter group according to each of the predicted fire source locations, wherein each of the prediction parameter groups includes a predicted smoke concentration, and one prediction parameter group corresponds to one of the predicted fire source locations; Determining a target parameter group among the plurality of prediction parameter groups, wherein a difference between the predicted smoke concentration of the target parameter group and the actual smoke concentration satisfies a preset condition; Determine that the predicted fire source location corresponding to the target parameter group is the actual fire source location.
3. The fire safety monitoring method for a smart building according to claim 2 is characterized in that: The prediction parameter group also includes a unit smoke volume and a smoke diffusion coefficient released from the fire source position per unit time. The preset parameter group and the predicted fire source position satisfy the following relationship: ; Among them, (X i , Y i ) is the i-th predicted fire source location, C(x i ,y i , T i ) is the predicted smoke density included in the i-th prediction parameter group, Q i is the unit smoke volume included in the i-th prediction parameter group, D i is the smoke diffusion coefficient included in the i-th prediction parameter group, (x i ,y i ) is the location data of the i-th smoke alarm, T i is the i-th diffusion duration.
4. The fire safety monitoring method for a smart building according to claim 2, characterized in that: Before determining the target parameter group among the plurality of prediction parameter groups, the method further includes: Determining the actual smoke concentration corresponding to each predicted smoke concentration according to the diffusion time; According to the predicted smoke density and the actual smoke density, the residual sum of squares included in the prediction parameter group is calculated, which is specifically calculated by the following formula: ; Among them, S(θ i ) is the ith residual sum of squares, C(x i ,y i , T i ) is the predicted smoke density included in the i-th prediction parameter group, C i is the actual smoke concentration of the ith instance.
5. The fire safety monitoring method for a smart building according to claim 4 is characterized in that: The determining of a target parameter group among the plurality of prediction parameter groups specifically includes: Calculating a function difference between a first residual sum of squares and a second residual sum of squares, wherein the first residual sum of squares is a residual sum of squares corresponding to a first parameter group, the second residual sum of squares is a residual sum of squares corresponding to a second parameter group, the first parameter group is any one of the plurality of prediction parameter groups, and the second parameter group is adjacent to the first parameter group; If it is determined that the function difference is less than or equal to a preset threshold, the first parameter group is determined to be the target parameter group.
6. The fire safety monitoring method for a smart building according to claim 1, characterized in that: The obtaining of the actual smoke concentration monitored by the multiple smoke alarms specifically includes: Receiving the corresponding original smoke concentration data sent by the plurality of smoke alarms; The original smoke density data is preprocessed to obtain the actual smoke density, wherein the preprocessing includes denoising, filtering and normalization processing.
7. The fire safety monitoring method for a smart building according to claim 1, characterized in that: The method further comprises: Inputting the actual fire source location into a preset building model to obtain a target display model; The target presentation model is sent to a user device, so as to present the target presentation model to a user corresponding to the user device through the user device.
8. A fire safety monitoring device for a smart building, characterized in that: The fire safety monitoring device comprises an acquisition module (31) and a processing module (32), wherein: The acquisition module (31) is used to acquire the actual smoke concentration monitored by multiple smoke alarms; The processing module (32) is used to determine the collection time corresponding to each actual smoke concentration; The processing module (32) is further used to sort the multiple collection moments in chronological order, and determine an initial moment according to the sorting result, wherein the initial moment is the earliest moment among the multiple collection moments; The processing module (32) is further used to determine the diffusion time of the fire smoke from the actual fire source location to the detection of the smoke alarm according to the collection time and the initial time; The processing module (32) is further used to determine the actual fire source location based on the diffusion time, the location data of the smoke alarm and the actual smoke concentration.
9. An electronic device, characterized in that: The electronic device comprises a processor (41), a memory (45), a user interface (43) and a network interface (44), wherein the memory (45) is used to store instructions, the user interface (43) and the network interface (44) are both used to communicate with other devices, and the processor (41) is used to execute the instructions stored in the memory (45) so that the electronic device executes the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.
Citation Information
Patent Citations
Method for constructing migration and propagation evaluation model of radioactive substance
CN104933294A
Converter transformer fire source intensity inversion assessment and temperature field prediction method and system
CN110162876A
Gas leakage source intensity back calculation improved search algorithm
CN111505205A
Fire temperature field reconstruction method and system, computer equipment, medium and terminal
CN114021501A
Monitoring inspection system and leakage early warning method for gas station pipe network
CN116642140A
Cited By
AI-based linkage response and control system
CN119296296A
Building engineering fire alarm method and system
CN119559743A
Intelligent fire-fighting big data analysis method based on cloud service
CN119939192A
A cloud service-based intelligent fire-fighting big data analysis method
CN119939192B
Intelligent building fire monitoring method
CN120808508A
