Virtual smoke chamber environment feature extraction method and application system thereof
Through new structural design and intelligent algorithms, virtual smoke cavity model is constructed, real-time analysis and adaptive learning are solved, and the problems of high cost and poor adaptability of virtual smoke cavity sensing systems in the existing technology are solved, and efficient and flexible smoke detection and monitoring are achieved. .
Patent Information
- Application Number
- CN202410981733.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-12
AI Technical Summary
The existing virtual smoke chamber induction technology has high manufacturing costs, large installation space requirements, poor adaptability, and is susceptible to environmental factors, making it difficult to meet the intelligent needs of high-rise buildings, large public places and smart home scenarios.
A new structural design and intelligent algorithm are used to build a virtual smoke cavity model, and analyse smoke data in real time through deep learning and pattern recognition algorithms, adaptively learn to adjust detection parameters, support remote monitoring and maintenance, and realize the extraction of virtual smoke cavity environment feature.
It reduces hardware complexity and manufacturing costs, improves detection accuracy and response speed, reduces false alarms and missed reports, meets the smoke detection needs in complex environments, simplifies maintenance processes, and improves management efficiency.
Smart Images

Figure CN118940660A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of fire safety monitoring, and in particular to a method for extracting characteristics of a virtual smoke chamber environment and an application system thereof. Background Art
[0002] In modern society, fire prevention is of vital importance. Smoke detection, as an important means of early warning of fire, is increasingly widely used. Smoke is usually one of the prominent features of the early stage of a fire. Through advanced sensor technology, the smoke detection system can keenly capture the presence of smoke particles. For example, in large commercial buildings, factories, residences and other places, smoke detection equipment can monitor the smoke changes in the environment in real time. When the smoke concentration reaches a certain threshold, an alarm is immediately issued to buy precious escape time for people. At the same time, it can also enable the fire department to respond quickly and take effective fire-fighting measures to minimize the losses caused by the fire.
[0003] The existing smoke detection system of virtual smoke cavity sensing technology has the following defects: first, most of the existing smoke detection devices rely on the physical smoke cavity structure to extend the smoke transmission path to enhance the detection sensitivity, but this design increases the manufacturing cost and installation space requirements, and each individual entity can only adapt to one scene, and the adaptability is not good; second, the physical smoke cavity is easily affected by environmental factors, such as dust deposition leading to decreased sensitivity, and regular cleaning and maintenance are cumbersome, and fires cannot be detected in time, reducing the efficiency of fire safety monitoring; third, the demand for real-time and intelligent smoke detection in high-rise buildings, large public places and smart home scenarios is growing, and traditional smoke cavity design is difficult to meet. For this reason, we propose a virtual smoke cavity environment feature extraction method and its application system. Summary of the invention
[0004] The purpose of the present invention is to provide a method for extracting characteristics of a virtual smoke chamber environment and an application system thereof.
[0005] In order to solve the problems raised in the above background technology, the present invention provides the following technical solution: a method for extracting characteristics of a virtual smoke chamber environment, the method comprising the following specific steps:
[0006] Step 1: Construct a virtual smoke cavity model: Use a new structural design and intelligent algorithm to set geometric parameters (shape, size and volume of the smoke cavity) and material properties (reflectivity and absorptivity of the smoke cavity wall) according to the smoke cavity parameters, and use formulas to calculate and verify to ensure that the virtual smoke cavity model can accurately simulate the diffusion, flow and deposition process of smoke in the physical smoke cavity, thereby dynamically simulating the behavior of smoke in the physical smoke cavity. The calculation formula is f (geometric parameters, material properties) = simulation effect;
[0007] Step 2: Real-time analysis of smoke data: Through the intelligent recognition and analysis system with integrated intelligent algorithms, the smoke data in the virtual smoke chamber is collected and analyzed in real time, and the deep learning algorithm and pattern recognition algorithm are used to quickly determine whether the smoke data in the virtual smoke chamber reaches the alarm threshold. Among them, the deep learning algorithm trains the recognition model by learning a large amount of historical data, and the pattern recognition algorithm is used to extract and classify the features of real-time data to improve the detection accuracy and response speed;
[0008] Step 3: Adaptive learning and optimization: The system performs adaptive learning based on historical data. By continuously analyzing historical data, it automatically adjusts the system parameters and thresholds to meet the smoke detection needs in different environments and reduce false alarms and missed alarms. The system can learn the changing patterns of environmental factors (temperature, humidity and airflow changes) and adjust the detection strategy accordingly.
[0009] Step 4: Remote monitoring and maintenance: Use the remote monitoring and maintenance interface to achieve remote connection of the equipment, which is convenient for management and maintenance personnel to conduct real-time monitoring and parameter adjustment through the network. The remote monitoring and maintenance interface adopts advanced communication technology to ensure stable data transmission and real-time response. Management and maintenance personnel can remotely obtain real-time data, system status and alarm information of the virtual smoke chamber environment through the network, and can remotely adjust the system parameters and settings, perform software upgrades and fault diagnosis.
[0010] As a further solution of the present invention: in the step one, in the new structural design, the setting of geometric parameters has been verified through a large number of experiments and simulations to achieve the best simulation effect. The shape of the smoke cavity can be customized according to the specific application scenario. The determination of the size and volume takes into account the diffusion speed of the smoke and the requirements of the detection sensitivity. At the same time, the material properties of the smoke cavity also need to be considered. The reflectivity and absorptivity of the smoke cavity wall will affect the propagation and distribution of the smoke in the smoke cavity. By adjusting these parameters, the virtual smoke cavity model can more accurately simulate the characteristics of the physical smoke cavity. The virtual smoke cavity model uses the Navier-Stokes equation fluid dynamics model to describe the flow behavior of the smoke in the smoke cavity, thereby improving the simulation accuracy.
[0011] As a further solution of the present invention: in the step 1, when the intelligent algorithm constructs the virtual smoke cavity model, the core needs to consider the smoke concentration value. The smoke concentration distribution is described by a Gaussian distribution model. Specifically, the smoke concentration value is calculated by the following formula:
[0012]
[0013] Where: C(x,y,z) represents the smoke concentration value at the position (x,y,z), A represents the peak concentration, (x0,y0,z0) represents the position of the maximum smoke concentration, and σ represents the standard deviation (the degree of dispersion of the smoke concentration distribution);
[0014] By using the Gaussian distribution model to describe the concentration distribution of smoke, the diffusion and distribution of smoke in the virtual smoke chamber can be accurately simulated, thus providing a basis for smoke detection and analysis;
[0015] The particle size and movement speed are simulated using the Monte Carlo method, and factors such as Brownian motion and turbulent diffusion are taken into account. The intelligent algorithm also includes a machine learning algorithm based on a neural network algorithm, which continuously optimizes the performance and accuracy of the model by learning and training historical data.
[0016] As a further solution of the present invention: in the step 2, in the intelligent algorithm integrated in the intelligent recognition and analysis system, the deep learning algorithm adopts a convolutional neural network (CNN) architecture, which can extract the features of smoke data and perform recognition and classification. The pattern recognition algorithm is a decision tree algorithm that combines feature engineering and classifiers, which can extract and classify features of real-time data, thereby improving detection accuracy and response speed.
[0017] As a further solution of the present invention: in the step three, the adaptive learning function automatically adjusts the system parameters and thresholds by continuously analyzing historical data, and adopts an adaptive filtering algorithm to update the system parameters in real time according to changes in environmental factors to adapt to the smoke detection needs in different environments. When the temperature rises, the system will automatically adjust the threshold of the smoke concentration to reduce false alarms. When the humidity changes, the model parameters of the particle movement speed will be adjusted accordingly to improve the accuracy of detection.
[0018] As a further solution of the present invention: In the step four, the remote monitoring and maintenance interface adopts 5G communication technology to ensure stable data transmission and real-time response. Management and maintenance personnel can remotely obtain real-time data of the virtual smoke chamber environment through the network, including smoke concentration, temperature and humidity parameters, as well as system status and alarm information. Through the remote control interface of the mobile app, the system parameters and settings can be remotely adjusted, software upgrades and fault diagnosis can be performed. When a system abnormality is found, maintenance personnel can remotely restart the equipment, update the algorithm and adjust the sensor sensitivity.
[0019] As a further solution of the present invention: the virtual smoke chamber environment feature extraction method also includes data storage and management functions, which can classify and store historical data and real-time data, and adopt MySQL database management system to ensure the security and integrity of data, which is convenient for subsequent data analysis and mining. Through cluster analysis data mining algorithm, potential problems and trends can be discovered to provide a basis for optimization and improvement. By analyzing historical data, the correlation between smoke concentration and environmental factors can be discovered, thereby optimizing detection algorithms and early warning strategies.
[0020] As a further solution of the present invention: the virtual smoke chamber environment feature extraction method is provided with standardized interfaces and protocols of ONVIF and MQTT, which can be seamlessly integrated with other intelligent security systems to realize data sharing and interaction, and work in coordination with fire alarm systems and video surveillance systems to form a complete security protection network. When the virtual smoke chamber detects smoke anomalies, it can promptly trigger the responses of other security systems, thereby improving the collaborative working capability and response speed of the entire security system.
[0021] In addition, the present invention also provides an application system for extracting characteristics of a virtual smoke chamber environment, comprising the following steps: the application system for extracting characteristics of a virtual smoke chamber environment comprises a virtual smoke chamber simulation module, an intelligent recognition and analysis module, an adaptive learning module and a remote monitoring and maintenance module; the virtual smoke chamber simulation module is used to construct a virtual smoke chamber model using a novel structural design and an intelligent algorithm to simulate the behavior of smoke in a physical smoke chamber; the intelligent recognition and analysis module is used to integrate intelligent algorithms to perform real-time analysis of smoke data in the virtual smoke chamber to determine whether an alarm threshold is reached; the adaptive learning module is used to enable the system to self-optimize based on historical data to adapt to specific environmental changes; and the remote monitoring and maintenance module is used to provide remote connection of the equipment so that management and maintenance personnel can perform real-time monitoring and parameter adjustment through the network.
[0022] By adopting the above technical solution, compared with the prior art, the beneficial effects of the present invention are:
[0023] 1. The present invention realizes the digital simulation of the physical smoke cavity by constructing a virtual smoke cavity model using a new structural design and an intelligent algorithm. This simulation method does not require a physical smoke cavity, greatly reduces the hardware complexity, reduces the manufacturing cost of the equipment and the installation space requirement. At the same time, the virtual smoke cavity model can dynamically simulate the behavior of smoke in the physical smoke cavity, more accurately reflect the diffusion, flow and deposition process of smoke, and provide a more reliable basis for smoke detection. Compared with the traditional physical smoke cavity structure, the digital smoke cavity simulation module has higher flexibility and scalability, and can be customized according to different application scenarios and requirements;
[0024] 2. The present invention can analyze the smoke data in the virtual smoke chamber in real time and quickly determine whether the alarm threshold is reached by integrating the intelligent recognition and analysis system of intelligent algorithms. This greatly improves the detection accuracy and response speed, can timely discover fire hazards, buys valuable time for taking effective response measures, and further improves the efficiency of fire safety monitoring;
[0025] 3. The present invention uses the adaptive learning function of the system to enable it to self-optimize according to historical data and gradually adapt to changes in specific environments. This is crucial to reducing false alarms and missed alarms, because changes in environmental factors (such as temperature, humidity, etc.) may affect the accuracy of smoke detection. By learning the laws of environmental changes, the system can automatically adjust detection parameters and thresholds, improve adaptability to different environments, and meet the use requirements of high-rise buildings, large public places and smart home scenarios, ensuring accurate smoke detection in various complex environments, reducing false alarms and missed alarms, and reducing unnecessary maintenance work and resource waste:
[0026] 4. The present invention provides great convenience for management and maintenance personnel by supporting remote connection through equipment. Real-time monitoring and parameter adjustment are performed through the network, which simplifies the maintenance process and improves maintenance efficiency. Management and maintenance personnel can remotely obtain real-time data, system status and alarm information of the virtual smoke chamber environment through the network anytime and anywhere, and promptly discover and solve potential problems. Remote monitoring can also realize centralized management of multiple devices, improving management efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Figure 1 A schematic diagram of the method steps in an embodiment of the present invention;
[0028] Figure 2 Schematic diagram of the system flow in an embodiment of the present invention. DETAILED DESCRIPTION
[0029] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.
[0030] In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.
[0031] Please see attached Figure 1 -Attached Figure 2 The virtual smoke chamber environment feature extraction method of the present invention comprises the following specific steps:
[0032] Step 1: Construct a virtual smoke cavity model: Use a new structural design and intelligent algorithm to set geometric parameters (shape, size and volume of the smoke cavity) and material properties (reflectivity and absorptivity of the smoke cavity wall) according to the smoke cavity parameters, and use formulas to calculate and verify to ensure that the virtual smoke cavity model can accurately simulate the diffusion, flow and deposition process of smoke in the physical smoke cavity, thereby dynamically simulating the behavior of smoke in the physical smoke cavity. The calculation formula is f (geometric parameters, material properties) = simulation effect;
[0033] Step 2: Real-time analysis of smoke data: Through the intelligent recognition and analysis system with integrated intelligent algorithms, the smoke data in the virtual smoke chamber is collected and analyzed in real time, and the deep learning algorithm and pattern recognition algorithm are used to quickly determine whether the smoke data in the virtual smoke chamber reaches the alarm threshold. Among them, the deep learning algorithm trains the recognition model by learning a large amount of historical data, and the pattern recognition algorithm is used to extract and classify the features of real-time data to improve the detection accuracy and response speed;
[0034] Step 3: Adaptive learning and optimization: The system performs adaptive learning based on historical data. By continuously analyzing historical data, it automatically adjusts the system parameters and thresholds to meet the smoke detection needs in different environments and reduce false alarms and missed alarms. The system can learn the changing patterns of environmental factors (temperature, humidity and airflow changes) and adjust the detection strategy accordingly.
[0035] Step 4: Remote monitoring and maintenance: Use the remote monitoring and maintenance interface to achieve remote connection of the equipment, which is convenient for management and maintenance personnel to conduct real-time monitoring and parameter adjustment through the network. The remote monitoring and maintenance interface adopts advanced communication technology to ensure stable data transmission and real-time response. Management and maintenance personnel can remotely obtain real-time data, system status and alarm information of the virtual smoke chamber environment through the network, and can remotely adjust the system parameters and settings, perform software upgrades and fault diagnosis.
[0036] In one embodiment of the present invention: in step one, in the new structural design, the setting of geometric parameters is verified through a large number of experiments and simulations to achieve the best simulation effect. The shape of the smoke cavity can be customized according to the specific application scenario. The determination of the size and volume takes into account the diffusion speed of the smoke and the requirements of detection sensitivity. At the same time, the material properties of the smoke cavity also need to be considered. The reflectivity and absorptivity of the smoke cavity wall will affect the propagation and distribution of the smoke in the smoke cavity. By adjusting these parameters, the virtual smoke cavity model can more accurately simulate the characteristics of the physical smoke cavity, and the virtual smoke cavity model uses the Navier-Stokes equation fluid dynamics model to describe the flow behavior of the smoke in the smoke cavity, thereby improving the simulation accuracy.
[0037] In one embodiment of the present invention: in step 1, when the intelligent algorithm constructs the virtual smoke cavity model, the core needs to consider the smoke concentration value. The smoke concentration distribution is described by a Gaussian distribution model. Specifically, the smoke concentration value is calculated by the following formula:
[0038]
[0039] Where: C(x,y,z) represents the smoke concentration value at the position (x,y,z), A represents the peak concentration, (x0,y0,z0) represents the position of the maximum smoke concentration, and σ represents the standard deviation (the degree of dispersion of the smoke concentration distribution);
[0040] By using the Gaussian distribution model to describe the concentration distribution of smoke, the diffusion and distribution of smoke in the virtual smoke chamber can be accurately simulated, thus providing a basis for smoke detection and analysis;
[0041] The particle size and movement speed are simulated using the Monte Carlo method, and factors such as Brownian motion and turbulent diffusion are taken into account. The intelligent algorithm also includes a machine learning algorithm based on a neural network algorithm, which continuously optimizes the performance and accuracy of the model by learning and training historical data.
[0042] In one embodiment of the present invention: in step 2, in the intelligent algorithm integrated in the intelligent recognition and analysis system, the deep learning algorithm adopts a convolutional neural network (CNN) architecture, which can extract the features of smoke data and perform recognition and classification. The pattern recognition algorithm is a decision tree algorithm that combines feature engineering and classifiers, which can extract features and classify real-time data, thereby improving detection accuracy and response speed.
[0043] In one embodiment of the present invention: In step three, the adaptive learning function automatically adjusts the system parameters and thresholds by continuously analyzing historical data, and adopts an adaptive filtering algorithm to update the system parameters in real time according to changes in environmental factors to adapt to smoke detection needs in different environments. When the temperature rises, the system will automatically adjust the threshold of smoke concentration to reduce false alarms. When the humidity changes, the model parameters of the particle movement speed will be adjusted accordingly to improve the accuracy of detection.
[0044] In one embodiment of the present invention: In step four, the remote monitoring and maintenance interface adopts 5G communication technology to ensure stable data transmission and real-time response. Management and maintenance personnel can remotely obtain real-time data of the virtual smoke chamber environment through the network, including smoke concentration, temperature and humidity parameters, as well as system status and alarm information. Through the remote control interface of the mobile app, the system parameters and settings can be remotely adjusted, software upgrades and fault diagnosis can be performed, and when a system abnormality is found, maintenance personnel can remotely restart the equipment, update the algorithm and adjust the sensor sensitivity.
[0045] In one embodiment of the present invention: the virtual smoke chamber environment feature extraction method also includes data storage and management functions, which can classify and store historical data and real-time data, and use the MySQL database management system to ensure the security and integrity of the data, which is convenient for subsequent data analysis and mining. Through the cluster analysis data mining algorithm, potential problems and trends can be discovered to provide a basis for optimization and improvement. By analyzing historical data, the correlation between smoke concentration and environmental factors can be discovered, thereby optimizing the detection algorithm and early warning strategy.
[0046] In one embodiment of the present invention: the virtual smoke chamber environment feature extraction method is provided with standardized interfaces and protocols of ONVIF and MQTT, which can be seamlessly integrated with other intelligent security systems to achieve data sharing and interaction, and work in conjunction with fire alarm systems and video surveillance systems to form a complete security protection network. When the virtual smoke chamber detects smoke anomalies, it can promptly trigger the response of other security systems, thereby improving the collaborative working capability and response speed of the entire security system.
[0047] Example 1, please refer to the attached Figure 1 In actual applications, the system can be linked with the fire protection system. Once abnormal smoke is detected, it can automatically trigger the start of fire protection equipment. For example, when the system sounds an alarm, it automatically opens the sprinkler system, starts the smoke exhaust equipment, etc., to control the spread of the fire in time. This linkage mechanism can greatly improve the timeliness and effectiveness of fire response and reduce the losses caused by fire.
[0048] Example 2, please refer to the attached Figure 1 When facing different usage scenarios, we can carry out actual scenario testing and verification, collect more data to optimize the system's performance and parameter settings, conduct tests under different building types and environmental conditions, collect a large amount of actual data, analyze the system's performance under various situations, and optimize and adjust the system's algorithms and models based on the test results to improve the system's adaptability and reliability.
[0049] The present invention also provides an application system for extracting characteristics of a virtual smoke chamber environment:
[0050] In one embodiment of the present invention: the application system for extracting virtual smoke chamber environmental features includes a virtual smoke chamber simulation module, an intelligent recognition and analysis module, an adaptive learning module and a remote monitoring and maintenance module. The virtual smoke chamber simulation module is used to construct a virtual smoke chamber model using a new structural design and intelligent algorithm to simulate the behavior of smoke in a physical smoke chamber. The intelligent recognition and analysis module is used to integrate intelligent algorithms to perform real-time analysis of smoke data in the virtual smoke chamber to determine whether an alarm threshold is reached. The adaptive learning module is used to enable the system to self-optimize based on historical data to adapt to specific environmental changes. The remote monitoring and maintenance module is used to provide remote connection for equipment so that management and maintenance personnel can perform real-time monitoring and parameter adjustment through the network.
[0051] Example 3, please refer to the attached Figure 2 The system can set multi-level alarm thresholds and issue different levels of alarms according to different levels of smoke concentration. When the smoke concentration reaches a lower threshold, the system can issue a warning signal to alert relevant personnel. When the smoke concentration further increases to a higher threshold, the system will issue an emergency alarm and initiate corresponding emergency measures. In this way, different response measures can be taken according to actual conditions to improve the accuracy and effectiveness of fire warnings.
[0052] Specifically, by using a new structural design and intelligent algorithm to construct a virtual smoke cavity model, the digital simulation of the physical smoke cavity was successfully achieved. This simulation method does not require a physical smoke cavity, significantly reduces the hardware complexity, reduces the manufacturing cost of the equipment and the requirement for installation space. At the same time, the virtual smoke cavity model can accurately and dynamically simulate the behavior of smoke in the physical smoke cavity, and more accurately present the diffusion, flow and deposition process of smoke, providing a more reliable basis for smoke detection. Compared with the traditional physical smoke cavity structure, the digital smoke cavity simulation module has higher flexibility and scalability, and can be customized according to different application scenarios and needs.
[0053] Specifically, the intelligent recognition and analysis system of the intelligent algorithm integrated in the present invention can perform real-time analysis on the smoke data in the virtual smoke chamber and quickly determine whether the alarm threshold has been reached. This greatly improves the detection accuracy and response speed, and can detect fire hazards in a timely manner, thus gaining valuable time for taking effective response measures and further improving the efficiency of fire safety monitoring.
[0054] Specifically, the adaptive learning function possessed by the present invention enables it to self-optimize based on historical data and gradually adapt to changes in a specific environment. This is crucial for reducing false alarms and missed alarms, because changes in environmental factors (such as temperature, humidity, etc.) may affect the accuracy of smoke detection. By learning the laws of environmental changes, the system can automatically adjust detection parameters and thresholds, enhance adaptability to different environments, and meet the use requirements of high-rise buildings, large public places and smart home scenarios, ensuring accurate smoke detection in various complex environments, reducing false alarms and missed alarms, and avoiding unnecessary maintenance work and waste of resources.
[0055] Specifically, the device of the present invention supports remote connection, which brings great convenience to management and maintenance personnel. Real-time monitoring and parameter adjustment are performed through the network, which simplifies the maintenance process and improves maintenance efficiency. Management and maintenance personnel can remotely obtain real-time data, system status and alarm information of the virtual smoke chamber environment through the network anytime and anywhere, and promptly discover and solve potential problems. Remote monitoring can also realize centralized management of multiple devices, improving management efficiency and accuracy.
[0056] Working principle:
[0057] Firstly, a virtual smoke cavity model is constructed through a new structural design and intelligent algorithm. The geometric parameters and material properties are set according to the smoke cavity parameters, and the calculation and verification are carried out through formulas to ensure that the virtual smoke cavity model can accurately simulate the behavior of smoke in the physical smoke cavity. The setting of geometric parameters and material properties has been verified through a large number of experiments and simulations. The shape of the smoke cavity can be customized. At the same time, considering the requirements of smoke diffusion speed and detection sensitivity, the virtual smoke cavity model adopts the Navier-Stokes equation fluid dynamics model to describe the flow behavior of smoke in the smoke cavity. Then, the intelligent recognition and analysis system with integrated intelligent algorithms collects and analyzes the smoke data in the virtual smoke cavity in real time, and uses deep The learning algorithm and pattern recognition algorithm quickly determine whether the alarm threshold has been reached. The deep learning algorithm trains the recognition model. The pattern recognition algorithm extracts and classifies features of real-time data to improve detection accuracy and response speed. Then, the system performs adaptive learning based on historical data and automatically adjusts the system's parameters and thresholds to meet the smoke detection needs in different environments and reduce false alarms and missed alarms. Finally, the remote monitoring and maintenance interface is used to achieve remote connection of the equipment. Management and maintenance personnel can perform real-time monitoring and parameter adjustment through the network. The remote monitoring and maintenance interface uses advanced communication technology to ensure stable data transmission and real-time response. At this point, the entire workflow is completed.
[0058] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.
[0059] Some aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". The processor may be one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DAPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, or combinations thereof. In addition, various aspects of the present application may be expressed as computer products located in one or more computer-readable media, which include computer-readable program codes. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, tapes ...), optical disks (e.g., compact disks CDs, digital versatile disks DVDs ...), smart cards, and flash memory devices (e.g., cards, sticks, key drives ...).
[0060] A computer-readable medium may include a propagated data signal containing computer program code, such as in baseband or as part of a carrier wave. The propagated signal may have a variety of manifestations, including electromagnetic, optical, etc., or a suitable combination. A computer-readable medium may be any computer-readable medium other than a computer-readable storage medium, which may be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit a program for use. The program code on the computer-readable medium may be propagated through any suitable medium, including radio, cable, fiber optic cable, radio frequency signal, or similar medium, or a combination of any of the above mediums.
[0061] Similarly, it should be noted that in order to simplify the description disclosed in this application, so as to help understand one or more embodiments of the invention, in the above description of the embodiments of the present application, sometimes multiple features are merged into one embodiment, drawings or descriptions thereof. However, this disclosure method does not mean that the features required by the object of the present application are more than the features mentioned in the claims. In fact, the features of the embodiment are less than all the features of the single embodiment disclosed above. In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "approximately", "approximately" or "substantially" in some examples. Unless otherwise specified, "approximately", "approximately" or "substantially" indicate that the number allows a variation of ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of the present application are approximate values, in specific embodiments, such numerical settings are as accurate as possible within the feasible range.
[0062] Although the present invention is disclosed as above in terms of preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art may make possible changes and modifications without departing from the spirit and scope of the present invention. Therefore, any modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention shall fall within the scope of protection defined by the claims of the present invention.
Claims
1. A method for extracting characteristics of a virtual smoke chamber environment, characterized in that: The virtual smoke chamber environment feature extraction method comprises the following specific steps: Step 1: Construct a virtual smoke cavity model: Use a new structural design and intelligent algorithm to set geometric parameters (shape, size and volume of the smoke cavity) and material properties (reflectivity and absorptivity of the smoke cavity wall) according to the smoke cavity parameters, and use formulas to calculate and verify to ensure that the virtual smoke cavity model can accurately simulate the diffusion, flow and deposition process of smoke in the physical smoke cavity, thereby dynamically simulating the behavior of smoke in the physical smoke cavity. The calculation formula is f (geometric parameters, material properties) = simulation effect; Step 2: Real-time analysis of smoke data: Through the intelligent recognition and analysis system with integrated intelligent algorithms, the smoke data in the virtual smoke chamber is collected and analyzed in real time, and the deep learning algorithm and pattern recognition algorithm are used to quickly determine whether the smoke data in the virtual smoke chamber reaches the alarm threshold. Among them, the deep learning algorithm trains the recognition model by learning a large amount of historical data, and the pattern recognition algorithm is used to extract and classify the features of real-time data to improve the detection accuracy and response speed; Step 3: Adaptive learning and optimization: The system performs adaptive learning based on historical data. By continuously analyzing historical data, it automatically adjusts the system parameters and thresholds to meet the smoke detection needs in different environments and reduce false alarms and missed alarms. The system can learn the changing patterns of environmental factors (temperature, humidity and airflow changes) and adjust the detection strategy accordingly. Step 4: Remote monitoring and maintenance: Use the remote monitoring and maintenance interface to achieve remote connection of the equipment, which is convenient for management and maintenance personnel to conduct real-time monitoring and parameter adjustment through the network. The remote monitoring and maintenance interface adopts advanced communication technology to ensure stable data transmission and real-time response. Management and maintenance personnel can remotely obtain real-time data, system status and alarm information of the virtual smoke chamber environment through the network, and can remotely adjust the system parameters and settings, perform software upgrades and fault diagnosis.
2. The method for extracting characteristics of a virtual smoke chamber environment according to claim 1, characterized in that: In the step 1, in the new structural design, the setting of geometric parameters has been verified through a large number of experiments and simulations to achieve the best simulation effect. The shape of the smoke cavity can be customized according to the specific application scenario. The determination of the size and volume takes into account the diffusion speed of the smoke and the requirements of the detection sensitivity. At the same time, the material properties of the smoke cavity also need to be considered. The reflectivity and absorptivity of the smoke cavity wall will affect the propagation and distribution of the smoke in the smoke cavity. By adjusting these parameters, the virtual smoke cavity model can more accurately simulate the characteristics of the physical smoke cavity. The virtual smoke cavity model uses the Navier-Stokes equation fluid dynamics model to describe the flow behavior of the smoke in the smoke cavity, thereby improving the simulation accuracy.
3. The method for extracting characteristics of a virtual smoke chamber environment according to claim 1, characterized in that: In step 1, when the intelligent algorithm constructs the virtual smoke cavity model, the core needs to consider the smoke concentration value. The smoke concentration distribution is described by a Gaussian distribution model. Specifically, the smoke concentration value is calculated by the following formula: Where: C(x,y,z) represents the smoke concentration value at the position (x,y,z), A represents the peak concentration, (x0,y0,z0) represents the position of the maximum smoke concentration, and σ represents the standard deviation (the degree of dispersion of the smoke concentration distribution); By using the Gaussian distribution model to describe the concentration distribution of smoke, the diffusion and distribution of smoke in the virtual smoke chamber can be accurately simulated, thus providing a basis for smoke detection and analysis; The particle size and movement speed are simulated using the Monte Carlo method, and factors such as Brownian motion and turbulent diffusion are taken into account. The intelligent algorithm also includes a machine learning algorithm based on a neural network algorithm, which continuously optimizes the performance and accuracy of the model by learning and training historical data.
4. The method for extracting characteristics of a virtual smoke chamber environment according to claim 1, characterized in that: In the step 2, in the intelligent algorithm integrated in the intelligent recognition and analysis system, the deep learning algorithm adopts the Convolutional Neural Network (CNN) architecture, which can extract the features of smoke data and perform recognition and classification. The pattern recognition algorithm is a decision tree algorithm that combines feature engineering and classifiers, which can extract and classify features of real-time data and improve detection accuracy and response speed.
5. The method for extracting characteristics of a virtual smoke chamber environment according to claim 1, characterized in that: In step three, the adaptive learning function automatically adjusts the system parameters and thresholds by continuously analyzing historical data, and adopts an adaptive filtering algorithm to update the system parameters in real time according to changes in environmental factors to adapt to the smoke detection needs in different environments. When the temperature rises, the system will automatically adjust the smoke concentration threshold to reduce false alarms. When the humidity changes, the model parameters of the particle movement speed will be adjusted accordingly to improve the accuracy of detection.
6. The method for extracting characteristics of a virtual smoke chamber environment according to claim 1, characterized in that: In step 4, the remote monitoring and maintenance interface uses 5G communication technology to ensure stable data transmission and real-time response. Management and maintenance personnel can remotely obtain real-time data of the virtual smoke chamber environment through the network, including smoke concentration, temperature and humidity parameters, as well as system status and alarm information. Through the remote control interface of the mobile app, the system parameters and settings can be remotely adjusted, software upgrades and fault diagnosis can be performed. When a system abnormality is found, maintenance personnel can remotely restart the equipment, update the algorithm and adjust the sensor sensitivity.
7. The method for extracting characteristics of a virtual smoke chamber environment according to claim 1, characterized in that: The virtual smoke chamber environment feature extraction method also includes data storage and management functions, which can classify and store historical data and real-time data, and adopt MySQL database management system to ensure the security and integrity of data, which is convenient for subsequent data analysis and mining. Through cluster analysis data mining algorithm, potential problems and trends can be discovered to provide a basis for optimization and improvement. By analyzing historical data, the correlation between smoke concentration and environmental factors can be discovered, thereby optimizing detection algorithms and early warning strategies.
8. The method for extracting characteristics of a virtual smoke chamber environment according to claim 1, characterized in that: The virtual smoke chamber environment feature extraction method is provided with standardized interfaces and protocols of ONVIF and MQTT, and can be seamlessly integrated with other intelligent security systems to achieve data sharing and interaction, and work in coordination with fire alarm systems and video surveillance systems to form a complete security protection network. When the virtual smoke chamber detects smoke anomalies, it can promptly trigger the responses of other security systems, thereby improving the collaborative working ability and response speed of the entire security system.
9. An application system for extracting virtual smoke chamber environment features applicable to the method for extracting virtual smoke chamber environment features according to any one of claims 1 to 8, characterized in that: The application system for extracting the characteristics of the virtual smoke chamber environment includes a virtual smoke chamber simulation module, an intelligent recognition and analysis module, an adaptive learning module and a remote monitoring and maintenance module. The virtual smoke chamber simulation module is used to construct a virtual smoke chamber model using a new structural design and an intelligent algorithm to simulate the behavior of smoke in a physical smoke chamber. The intelligent recognition and analysis module is used to integrate an intelligent algorithm to perform real-time analysis on the smoke data in the virtual smoke chamber to determine whether an alarm threshold is reached. The adaptive learning module is used to enable the system to self-optimize according to historical data to adapt to specific environmental changes. The remote monitoring and maintenance module is used to provide remote connection for equipment so that management and maintenance personnel can perform real-time monitoring and parameter adjustment through the network.
