Fire extinguishing paste intelligent triggering control method and system based on Internet of Things

Abstract

The invention discloses a fire extinguishing paste intelligent trigger control method and system based on the Internet of Things, and relates to the technical field, and the method comprises the following steps: constructing a fire extinguishing paste matrix of a to-be-detected region, obtaining initial fire signal data, carrying out the DWT decomposition of the initial fire signal data based on a blind source separation method and a wavelet threshold denoising method, and obtaining a fire extinguishing paste matrix; fire signal features of different scales are obtained; performing feature optimization on the fire signal features based on a particle swarm algorithm to obtain a fire signal feature subset; a fire early warning model is constructed for the fire signal feature subset based on a random forest algorithm, and triggering of a fire extinguishing patch is controlled based on a prediction result of the fire early warning model; the fire position is obtained according to the triggered fire extinguishing paste position, the fire extinguishing condition is judged, and the fire extinguishing paste is transferred; according to the invention, through intelligent management and control of the fire extinguishing stickers and optimization of the triggering condition fineness, the problems that the fire extinguishing stickers cannot be scheduled in real time and the triggering conditions are not intelligent or accurate enough are solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology of fire extinguishing patches, and more specifically, to an intelligent triggering control method and system for fire extinguishing patches based on the Internet of Things. Background Art

[0002] With the acceleration of urbanization, the risk of fire is increasing, especially in fire-prone places such as high-rise buildings, industrial parks and storage facilities. Traditional firefighting methods can no longer meet the increasingly complex fire prevention and control needs. In recent years, the rapid development of Internet of Things technology has provided new solutions for fire monitoring and prevention. Through the combination of sensors, networks and cloud platforms, Internet of Things technology enables real-time, automated and remote control of fire monitoring and response.

[0003] A fire extinguishing patch is a fire-fighting device used to prevent and extinguish early-stage fires. It is usually attached to the surface or inside of a device in the form of a patch, and automatically releases fire extinguishing agents through a heat-sensing trigger mechanism to achieve rapid fire extinguishing.

[0004] Although the current fire extinguishing patch has a self-starting fire extinguishing function, the fire extinguishing patch lacks the reference of Internet of Things technology and intelligent management and control, which makes it impossible to accurately locate the fire location and dispatch it in real time, or the fire extinguishing patch may be triggered under unnecessary circumstances, resulting in waste of resources or unnecessary chemical reactions. Secondly, if the triggering conditions are not smart or accurate enough, the fire extinguishing patch may fail to start at the first time of the fire, delaying the fire extinguishing time, thereby increasing the risk of fire spread. In response to the above problems, the present invention proposes a solution. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an intelligent triggering and controlling method and system for fire extinguishing patches based on the Internet of Things, which optimizes the intelligent control of fire extinguishing patches and the precision of triggering conditions to solve the problem that fire extinguishing patches cannot be scheduled in real time and the triggering conditions are not intelligent or precise enough.

[0006] To achieve the above object, the present invention provides the following technical solutions: The method for intelligent triggering and controlling of fire extinguishing stickers based on the Internet of Things constructs a fire extinguishing sticker matrix in the test area, obtains initial fire signal data, performs DWT decomposition on the initial fire signal data based on the blind source separation method and the wavelet threshold denoising method, and obtains fire signal characteristics of different scales; optimizes the fire signal characteristics based on the particle swarm algorithm to obtain a fire signal feature subset; constructs a fire warning model based on the random forest algorithm for the fire signal feature subset, and controls the triggering of the fire extinguishing sticker based on the prediction result of the fire warning model; obtains the fire location according to the position of the fire extinguishing sticker after triggering, judges the fire extinguishing situation and mobilizes the fire extinguishing sticker.

[0007] In a preferred embodiment, a fire extinguishing sticker matrix is ​​constructed in the area to be tested, specifically: obtaining the fire extinguishing sticker position data and the fire extinguishing sticker status data of the area to be tested; constructing the fire extinguishing sticker matrix based on spatial analysis according to the fire extinguishing sticker position data and the fire extinguishing sticker status data; and obtaining the usage of the fire extinguishing stickers in the fire extinguishing sticker matrix through the fire extinguishing sticker status data.

[0008] In a preferred embodiment, initial fire signal data is obtained, and the initial fire signal data is subjected to DWT decomposition based on a blind source separation method and a wavelet threshold denoising method to obtain fire signal features of different scales, specifically: initial fire signal data is obtained, and the initial fire signal data includes air pressure changes, current fluctuations, temperature data, smoke concentration, and gas concentration; based on the blind source separation method, the initial fire signal data is separated to obtain each independent signal data in the initial fire signal data; each independent signal data is subjected to multi-layer decomposition through DWT to obtain a low-frequency approximate coefficient and a high-frequency detail coefficient of each signal data; a noise threshold is obtained by evaluating based on the noise standard deviation, and a hard threshold formula is selected based on the wavelet threshold denoising algorithm to denoise the high-frequency detail coefficient; the denoised high-frequency detail coefficient and the low-frequency approximate coefficient are recombined based on an inverse wavelet transform to obtain fire signal features of different scales.

[0009] In a preferred embodiment, the fire signal features are feature optimized based on a particle swarm algorithm to obtain a fire signal feature subset, specifically: according to fire signal features of different scales, selection, crossover and mutation operations are performed based on a genetic algorithm, and each optimal solution obtained is used as the initial position of each particle in the particle swarm algorithm, wherein each particle represents a set of fire signal features; based on a preset initial velocity range, the initial velocity of the particle is generated by uniform distribution; for each particle, based on a classification model, the fire signal feature it represents is input into the classification model, and the fitness is evaluated by calculating the classification accuracy of the model, that is, the fitness function is a classification accuracy calculation formula of the model; each particle is updated based on the current fitness and the historical best fitness, and the global best position based on a preset position and velocity update formula; when the algorithm runs to the set maximum number of iterations, the algorithm is stopped, and the feature subset corresponding to the global best position of the particle is the optimal fire signal feature subset after optimization by the particle swarm algorithm.

[0010] In a preferred embodiment, each particle is updated based on the current fitness, the historical best fitness, and the global best position based on a preset position and speed update formula, specifically: the historical best fitness of each particle is obtained, and if the fitness of the current particle is better than its historical best fitness, the personal best position of the particle is updated based on the preset position and speed update formula; by comparing the personal best positions of all particles, the particle with the best fitness is found, the solution of the particle is used as the global optimal solution, and the global best position is updated.

[0011] In a preferred embodiment, a fire warning model is constructed based on a random forest algorithm using a subset of fire signal features, and the triggering of a fire extinguishing patch is controlled based on the prediction result of the fire warning model, specifically: historical fire data is obtained, fire thresholds of different fire signal features are obtained based on the historical fire data based on a regression analysis method, and the corresponding fire thresholds are annotated into the fire signal feature subset, wherein the fire signal features include air pressure features, current fluctuation features, temperature features, smoke concentration features, and gas concentration features; the annotated fire signal feature subset is divided into a training set and a test set, and a corresponding number of decision trees are constructed according to the fire signal features in the training set; each decision tree is trained to form an independent decision tree, and an optimal partition point is set by impurity based on the Gini index; the root node is partitioned based on the optimal partition point until the maximum depth of the tree is reached, the partitioning is stopped, and a leaf node is generated; if the proportion of fire samples in the leaf node is greater than the proportion of non-fire samples, the label of the leaf node is fire, otherwise it is non-fire; the generated results of all decision trees are integrated, and the final prediction result is obtained based on an average mechanism; when the prediction result is fire, the triggering of the fire extinguishing patch is controlled to perform fire extinguishing processing.

[0012] In a preferred embodiment, the fire location is obtained according to the position of the fire extinguishing sticker after being triggered, the fire extinguishing situation is judged and the fire extinguishing stickers are mobilized, specifically: after the fire extinguishing sticker is triggered, a prediction is made again according to the fire warning model to determine whether the fire is extinguished; if not, the spread of the fire source is obtained and mobilization rules are formulated according to the distribution of the fire extinguishing stickers in the fire extinguishing sticker matrix; the fire extinguishing sticker matrix is ​​updated in real time according to the mobilization results.

[0013] In a preferred embodiment, the spread of the fire source is obtained and mobilization rules are formulated according to the distribution of the fire extinguishing stickers in the fire extinguishing sticker matrix, specifically: based on graph theory and graph search algorithm, the fire extinguishing area and the fire extinguishing sticker matrix are regarded as a graph, in which each position is set as a node and the neighborhood within a preset range is an edge; the neighborhood is traversed by a breadth-first search method, and according to the spread of the fire source, the nodes closest to the fire source and the fire extinguishing stickers in the direction of the fire source spread are preferentially traversed; by traversing layer by layer, it is determined whether the fire extinguishing sticker can be triggered within a preset time according to the status data of the fire extinguishing sticker; if it cannot be triggered, the traversal continues until a triggerable fire extinguishing sticker with the shortest path to the fire source is found, and the fire extinguishing sticker is controlled to perform fire extinguishing processing.

[0014] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By constructing a fire-fighting sticker matrix, we can optimize resource allocation, improve response speed, and accurately identify high-risk areas, thereby improving fire-fighting efficiency and safety. Secondly, the fire signal is processed using blind source separation and wavelet threshold denoising methods, so that the signal can be accurately analyzed at multiple scales and multiple frequency bands, and clear fire features can be extracted, effectively improving the accuracy and sensitivity of the fire warning system. DWT decomposition can capture subtle changes in fire signals, and combined with noise removal technology, it greatly enhances the robustness of signal processing and ensures that potential fire risks can be identified in real time in complex environments.

[0015] 2. By combining the particle swarm algorithm with the genetic algorithm, the feature selection process of the fire signal is optimized. The particle swarm algorithm can automatically select the most relevant fire signal features, thereby removing redundant and irrelevant features and improving the expression efficiency and recognition accuracy of the signal. Through the initialization process of the genetic algorithm, its global search capability is fully utilized to provide a high-quality initial solution for the particle swarm algorithm, ensuring the convergence of the algorithm and avoiding the problem of local optimal solutions. Ultimately, the optimized feature subset can retain the discriminative information to the maximum extent, thereby improving the accuracy and reliability of the classification and recognition model. The overall solution effectively improves the performance of the fire signal processing system and ensures efficient and accurate fire detection and early warning.

[0016] 3. The random forest algorithm can accurately predict the probability and risk of fire, ensuring that the fire extinguishing sticker is triggered at the early stage of the fire, thereby effectively shortening the response time and controlling the spread of the fire. Secondly, by analyzing the relationship between multiple features, the possibility of false triggering is reduced, avoiding unnecessary waste of resources and equipment loss.

[0017] 4. Dynamically adjust the position of the fire extinguishing stickers through the breadth-first search algorithm, and give priority to mobilizing the fire extinguishing stickers near the fire source and in the direction of diffusion, so as to achieve accurate and efficient fire extinguishing response. This method ensures the rapid mobilization and reasonable allocation of fire extinguishing stickers, improves the efficiency of fire extinguishing, and can timely determine whether the fire extinguishing sticker can be triggered, avoiding waste of resources and misoperation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic flow chart of the method for intelligent triggering and controlling a fire extinguishing patch based on the Internet of Things provided in an embodiment of the present application.

[0019] Figure 2 A schematic diagram of the structure of the fire extinguishing sticker intelligent trigger management and control system based on the Internet of Things provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Embodiment 1, Figure 1 The schematic diagram of the flow chart of the intelligent triggering control method of the fire extinguishing sticker based on the Internet of Things provided in the embodiment of the present application includes the following steps: S1, construct the fire extinguishing sticker matrix of the area to be tested, and obtain the initial fire signal data. The initial fire signal data is decomposed by DWT based on the blind source separation method and wavelet threshold denoising method to obtain fire signal characteristics of different scales.

[0022] The purpose of the fire extinguishing matrix is ​​to optimize and improve the efficiency of fire extinguishing operations, ensure that when a fire occurs, it can respond quickly, accurately, and effectively, and minimize losses. The fire extinguishing matrix provides scientific and systematic decision support for fire extinguishing work by comprehensively considering factors such as fire risks, resource distribution, and fire extinguishing capabilities in different areas. Specifically, there are several key reasons for building a fire extinguishing matrix: Optimize resource allocation: Firefighting resources are often limited, so they need to be reasonably allocated according to the fire risks and resource requirements of different areas. This helps ensure that resources can be invested in where they are most needed at critical moments, thereby improving firefighting efficiency.

[0023] Improve response speed: After a fire occurs, it is crucial to quickly extinguish the fire. The fire extinguishing matrix can identify the fire extinguishing priority and resource requirements of each area, allowing firefighters to respond quickly based on the information displayed in the matrix, shortening the reaction time and improving the speed of fire extinguishing.

[0024] Identify high-risk areas: Some areas may face higher fire risks due to factors such as environment, buildings, and population density. By building a fire extinguishing sticker matrix, high-risk areas can be clearly identified, providing data support for the formulation of fire prevention strategies, resource allocation, and training plans, and making preventive and preparedness work in advance.

[0025] Multiple micro sensors are installed on the fire extinguishing device, including temperature sensors, which are arranged on the surface of the fire extinguishing device, smoke sensors, which are arranged near the vents of the fire extinguishing device, gas sensors, which are arranged on the edge of the fire extinguishing device, air pressure sensors, which are arranged in the center of the fire extinguishing device, and current sensors, which are arranged in the area connected to the circuit. The micro sensor obtains the initial fire signal data in real time and transmits it to the online control system through the communication module for data processing.

[0026] By performing DWT decomposition on the initial fire signal data, early warning of fire has the following advantages: Multi-scale analysis: DWT can analyze signals at different time scales, which is very helpful for capturing subtle changes in fire signals. For example, the signal may change slowly in the early stage of a fire, while higher-frequency fluctuations may occur during the spread of the fire. DWT can effectively extract features at these different scales.

[0027] Time-frequency localization characteristics: DWT has good time-frequency localization characteristics, that is, it can accurately analyze the local changes of signals in time and frequency. This makes it particularly effective in processing non-stationary signals (such as sudden fire signals), and can accurately locate the time of occurrence of fire and its intensity changes.

[0028] Efficient feature extraction: Through DWT decomposition, multi-level and multi-band features can be extracted from fire signals. These features can be used as inputs to the fire warning system, helping the system to better distinguish fire from other interference signals and improve the accuracy and sensitivity of the warning.

[0029] Strong real-time performance: DWT has high computational efficiency and can process and analyze fire signals in real time, and detect potential fire risks in a timely manner. Especially in the early stages of a fire, timely signal recognition and processing are very critical.

[0030] Strong adaptability: DWT has strong adaptability and can be used in combination with other signal processing techniques (such as neural networks, support vector machines, etc.) to further improve the performance and robustness of the fire warning system.

[0031] The fire extinguishing sticker matrix of the area to be tested is constructed as follows: Obtain the fire extinguisher location data and fire extinguisher status data of the area to be tested; Construct a fire extinguishing sticker matrix based on spatial analysis according to the fire extinguishing sticker location data and fire extinguishing sticker status data; And the usage of the fire extinguishing stickers in the fire extinguishing sticker matrix is ​​obtained through the fire extinguishing sticker status data.

[0032] It should be noted that the usage of the fire extinguishing patch can be understood as whether the fire extinguishing patch is used. If it is used, 0 is displayed in the fire extinguishing patch matrix, and if it is not used, 1 is displayed in the fire extinguishing patch matrix. The fire extinguishing patch status data includes the usage status of the fire extinguishing patch, that is, whether it is in use, whether it has been activated, the validity period, the number of triggers, and the usage period.

[0033] The initial fire signal data is obtained, and the initial fire signal data is subjected to DWT decomposition based on a blind source separation method and a wavelet threshold denoising method to obtain fire signal features of different scales, specifically: Acquiring initial fire signal data, the initial fire signal data including air pressure changes, current fluctuations, temperature data, smoke concentration, and gas concentration; Based on the blind source separation method, the initial fire signal data is separated to obtain each independent signal data in the initial fire signal data; Through DWT, each independent signal data is decomposed in multiple layers to obtain the low-frequency approximate coefficient and high-frequency detail coefficient of each signal data; The noise threshold is obtained by evaluating based on the noise standard deviation, and the hard threshold formula is selected based on the wavelet threshold denoising algorithm to denoise the high-frequency detail coefficients; The denoised high-frequency detail coefficients and low-frequency approximate coefficients are recombined based on inverse wavelet transform to obtain fire signal characteristics of different scales.

[0034] The noise threshold is specifically calculated as follows:

[0035] The specific calculation formula of the hard threshold formula is as follows:

[0036] In the formula, is the noise threshold, is the standard deviation of the noise, is the length of the signal, For the High frequency detail coefficient.

[0037] It should be noted that for the high-frequency detail coefficient, when its absolute value is less than the noise threshold, it is set to zero; when it is greater than the noise threshold, the coefficient is retained unchanged. After the signal is decomposed, the high-frequency part is more susceptible to noise interference, especially in the detail coefficient, and the noise usually appears in these high-frequency components. Screening the high-frequency part during denoising can effectively reduce the impact of noise. Denoising can retain the main structure of the signal: the wavelet transform decomposes the signal so that the low-frequency part of the signal retains most of the information, while the high-frequency part is often noise. By removing the noise part, the main structure of the signal is better preserved. Threshold denoising can enhance subsequent feature extraction: in subsequent feature extraction (such as using DWT coefficients for machine learning training), the denoised signal usually provides clearer and more reliable features and enhances the performance of the model. Since unimportant detail information is removed, the reconstructed signal should be smoother than the original signal while retaining most of the useful features. Multi-sensor data may contain mixed signals. For example, signals from different sources (temperature, smoke, gas concentration, etc.) are mixed together during a fire, which is difficult to separate and process independently. The different components of the signal are separated by blind source separation technology. Before DWT processing, blind source separation is performed to ensure that each sensor data source is effectively separated, thereby improving the decomposition accuracy.

[0038] S2, optimizing the fire signal features based on a particle swarm algorithm to obtain a fire signal feature subset.

[0039] By optimizing the features after DWT through the particle swarm algorithm, the frequency bands and feature subsets most relevant to fire signal recognition can be automatically selected, thereby retaining meaningful features, removing redundant or irrelevant parts, and improving the efficiency of signal representation. The optimized feature subset can retain the most discriminative information and improve classification or recognition accuracy.

[0040] The fire signal features are optimized based on the particle swarm algorithm to obtain a fire signal feature subset, specifically: According to the fire signal characteristics of different scales, selection, crossover and mutation operations are performed based on the genetic algorithm, and each optimal solution is used as the initial position of each particle in the particle swarm algorithm, where each particle represents a set of fire signal characteristics; Based on the preset initial velocity range, the initial velocity of particles is generated by uniform distribution; For each particle, based on the classification model, the fire signal characteristics it represents are input into the classification model, and the fitness is evaluated by calculating the classification accuracy of the model, that is, the fitness function is the classification accuracy calculation formula of the model; Each particle is updated based on the current fitness, the best historical fitness, and the global best position based on the preset position and speed update formula; When the algorithm reaches the set maximum number of iterations, the algorithm stops. At this time, the feature subset corresponding to the global optimal position of the particle is the optimal fire signal feature subset after optimization by the particle swarm algorithm.

[0041] The specific calculation formula of the initial velocity of the particle is as follows: in ,

[0042] The classification accuracy calculation formula is as follows:

[0043] In the formula, For particles At the moment The initial velocity, is the preset maximum speed. is the preset minimum speed. is a random number, is the classification accuracy, The number of samples that are fire and are correctly classified as fire, The number of samples that are non-fire and correctly classified as non-fire, The number of non-fire samples that were misclassified as fire, The number of samples that were fire but were misclassified as non-fire.

[0044] Each particle is updated according to the current fitness, the best historical fitness, and the global best position based on the preset position and speed update formula, specifically: Get the historical best fitness of each particle. If the current particle's fitness is better than its historical best fitness, update the particle's personal best position based on the preset position and speed update formula. By comparing the personal best positions of all particles, the particle with the best fitness is found, the solution of this particle is taken as the global optimal solution, and the global best position is updated.

[0045] The speed update formula, the specific calculation formula is as follows:

[0046] The position update formula, the specific calculation formula is as follows:

[0047] In the formula, For the update speed, For particles At the moment The initial velocity, For particles At the moment location, For particles At the moment Personal best position, is the global best position, and for A random number between is the inertia weight, For the updated location, is the individual learning factor, is the group learning factor.

[0048] It should be noted that by combining the selection, crossover and mutation operations of the genetic algorithm to generate the initial particle swarm of the particle swarm algorithm, the global search capability of the genetic algorithm can be fully utilized to provide a high-quality initial solution for the particle swarm algorithm, thereby accelerating the search process and avoiding falling into the local optimal solution at an early stage. The initial solution generated by the genetic algorithm not only has a higher fitness, but also can better guide the particle swarm algorithm to effectively explore in the solution space.

[0049] S3, constructs a fire warning model based on the random forest algorithm using the fire signal feature subset, and controls the triggering of the fire extinguishing sticker based on the prediction results of the fire warning model.

[0050] When the online control system determines that the fire signal is a fire after data processing, the trigger circuit on the fire extinguishing device is quickly activated, puncturing the fire extinguishing microcapsules and mixing with the adhesive to form a fire extinguishing patch for fire extinguishing.

[0051] The fire warning model is constructed through the random forest algorithm, and the triggering of the fire extinguishing sticker is controlled according to the prediction results of the fire warning model, which has the following benefits: Improve response efficiency: With the accurate prediction of the random forest algorithm, the probability and risk of fire can be assessed more accurately. The fire extinguishing sticker can be triggered at the early stage of the fire, respond quickly, effectively reduce the time for the fire to spread, and control the fire.

[0052] Reduce false triggers: Random forests can more accurately determine the probability of fire by analyzing the relationship between multiple features, thereby reducing false triggers caused by misjudgment of environmental changes. This can avoid waste of resources (such as the consumption of fire extinguishing stickers) and excessive human intervention.

[0053] Reduce costs: Through accurate prediction, effective measures can be taken before the fire has completely occurred, thereby reducing the economic losses caused by the fire. This also avoids the frequent triggering of fire extinguishing stickers, thereby saving the cost of equipment and fire extinguishing materials.

[0054] Improve safety: With accurate predictions from the fire warning model, the safety of personnel can be effectively protected, especially in places with a large number of people or key facilities. The accuracy of the model prediction ensures that the fire extinguishing stickers can be activated in time when a fire occurs, preventing the fire from spreading and ensuring life safety.

[0055] Intelligent management: The fire warning system built using the random forest algorithm can perform real-time data analysis and learning to continuously optimize the warning results. This intelligent management can continuously improve the accuracy of the model according to different environments, weather conditions and historical data, and further enhance the reliability of the fire extinguishing sticker trigger.

[0056] Improve the personalization of firefighting strategies: With the accumulation of data, the random forest model can customize personalized firefighting strategies according to different regions and different fire types. The triggered fire extinguishing stickers can respond to different types of fires more specifically and efficiently, reducing the occurrence of misoperation.

[0057] The fire signal feature subset is used to construct a fire warning model based on the random forest algorithm, and the triggering of the fire extinguishing sticker is controlled based on the prediction result of the fire warning model, specifically: Acquire historical fire data, obtain fire thresholds of different fire signal characteristics based on the historical fire data based on a regression analysis method, and mark the corresponding fire thresholds into a fire signal characteristic subset, wherein the fire signal characteristics include air pressure characteristics, current fluctuation characteristics, temperature characteristics, smoke concentration characteristics, and gas concentration characteristics; The annotated fire signal feature subsets are divided into a training set and a test set, and a corresponding number of decision trees are constructed according to the fire signal features in the training set; Train each decision tree to form an independent decision tree, and set the optimal split point based on the impurity of the Gini index; The root node is divided based on the optimal division point until the maximum depth of the tree is reached, the division stops, and the leaf node is generated; If the proportion of fire samples in a leaf node is greater than the proportion of non-fire samples, the label of the leaf node is fire, otherwise it is non-fire; Integrate the generated results of all decision trees and obtain the final prediction result based on the average mechanism; When the prediction result is fire, the fire extinguishing sticker is controlled to be triggered to carry out fire extinguishing.

[0058] The optimal partition point is set by impurity based on the Gini index, specifically: The Gini index is an indicator to measure the purity of a data set. When training a decision tree, the algorithm will traverse all features and calculate the Gini index of each feature at the fire and non-fire dividing point. If the data set can be divided into two relatively pure subsets through the division of a certain feature, then this feature and its dividing point are considered optimal.

[0059] S4, obtaining the fire location according to the location of the fire extinguishing sticker after triggering, judging the fire extinguishing situation and mobilizing the fire extinguishing sticker, specifically: After the fire extinguishing sticker is triggered, the fire warning model is used to make another prediction to determine whether the fire has been extinguished; If the fire is not extinguished, obtain the spread of the fire source and formulate mobilization rules based on the distribution of fire extinguishing stickers in the fire extinguishing sticker matrix; Update the fire-fighting sticker matrix in real time based on the mobilization results; It should be noted that the real-time updating of the fire extinguishing sticker matrix according to the mobilization result can be understood as real-time updating of the elements 0 and 1 represented in the fire extinguishing sticker matrix according to the usage of the fire extinguishing sticker after the mobilization.

[0060] The diffusion of the fire source is obtained and the mobilization rules are formulated according to the distribution of the fire extinguishing stickers in the fire extinguishing sticker matrix, specifically: Based on graph theory and graph search algorithm, the fire extinguishing area and the fire extinguishing sticker matrix are regarded as a graph, where each position is set as a node and the neighborhood within a preset range is an edge; The neighborhood is traversed by the breadth-first search method. According to the spread of the fire source, the nodes closest to the fire source and the fire extinguishing posts in the direction of the fire source spread are traversed first; By traversing layer by layer, judging whether the fire extinguishing sticker can be triggered within the preset time according to the status data of the fire extinguishing sticker; If it cannot be triggered, continue to traverse until a fire extinguishing sticker that can be triggered and has the shortest path to the fire source is found, and control the fire extinguishing sticker to extinguish the fire.

[0061] It should be noted that the judgment of whether the fire extinguishing patch can be triggered within the preset time based on the status data of the fire extinguishing patch can be understood as a judgment based on the validity period, number of triggering times and usage period of the fire extinguishing patch. If the number of triggering times does not exceed the preset safe triggering times and the fire extinguishing patch is within the safe and effective range, the fire extinguishing patch can be triggered.

[0062] Embodiment 2, Figure 2 The schematic diagram of the structure of the fire extinguishing sticker intelligent trigger control system based on the Internet of Things provided in the embodiment of the present application includes a matrix construction and data processing module, a feature optimization module, a fire warning module and a fire extinguishing sticker mobilization module, and there are connections between the modules: The matrix construction and data processing module is used to construct the fire extinguishing sticker matrix of the area to be tested and obtain the initial fire signal data. The initial fire signal data is decomposed by DWT based on the blind source separation method and wavelet threshold denoising method to obtain fire signal characteristics of different scales. A feature optimization module, used for optimizing the fire signal features based on a particle swarm algorithm to obtain a fire signal feature subset; The fire warning module is used to construct a fire warning model based on the random forest algorithm using a subset of fire signal features, and to control the triggering of fire extinguishing stickers based on a dynamic threshold adjustment method; The fire extinguishing sticker mobilization module is used to obtain the fire location according to the position of the fire extinguishing sticker after triggering, judge the fire extinguishing situation and mobilize the fire extinguishing sticker.

[0063] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0064] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0065] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0066] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0067] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0068] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A fire extinguishing sticker intelligent trigger control method based on the Internet of Things, characterized in that: The steps include: Construct a fire extinguishing sticker matrix for the area to be tested, obtain the initial fire signal data, perform DWT decomposition on the initial fire signal data based on the blind source separation method and wavelet threshold denoising method, and obtain fire signal features of different scales; The fire signal features are optimized based on a particle swarm algorithm to obtain a fire signal feature subset; A fire warning model is constructed based on the random forest algorithm using a subset of fire signal features, and the triggering of the fire extinguishing sticker is controlled based on the prediction results of the fire warning model; The fire location is obtained according to the position of the fire extinguishing sticker after being triggered, the fire extinguishing situation is judged and the fire extinguishing sticker is mobilized.

2. The method for intelligent triggering and controlling of fire extinguishing stickers based on the Internet of Things according to claim 1 is characterized in that: The fire extinguishing sticker matrix of the area to be tested is constructed as follows: Obtain the fire extinguisher location data and fire extinguisher status data of the area to be tested; Construct a fire extinguishing sticker matrix based on spatial analysis according to the fire extinguishing sticker location data and fire extinguishing sticker status data; And the usage of the fire extinguishing stickers in the fire extinguishing sticker matrix is ​​obtained through the fire extinguishing sticker status data.

3. The method for intelligent triggering and controlling of fire extinguishing stickers based on the Internet of Things according to claim 1 is characterized in that: The initial fire signal data is obtained, and the initial fire signal data is subjected to DWT decomposition based on a blind source separation method and a wavelet threshold denoising method to obtain fire signal features of different scales, specifically: Acquiring initial fire signal data, the initial fire signal data including air pressure changes, current fluctuations, temperature data, smoke concentration, and gas concentration; Based on the blind source separation method, the initial fire signal data is separated to obtain each independent signal data in the initial fire signal data; Through DWT, each independent signal data is decomposed in multiple layers to obtain the low-frequency approximate coefficient and high-frequency detail coefficient of each signal data; The noise threshold is obtained by evaluating based on the noise standard deviation, and the hard threshold formula is selected based on the wavelet threshold denoising algorithm to denoise the high-frequency detail coefficients; The denoised high-frequency detail coefficients and low-frequency approximate coefficients are recombined based on inverse wavelet transform to obtain fire signal characteristics of different scales.

4. The method for intelligent triggering and controlling of fire extinguishing stickers based on the Internet of Things according to claim 1 is characterized in that: The fire signal feature subset is obtained by optimizing the fire signal feature based on the particle swarm algorithm, specifically: According to the fire signal characteristics of different scales, selection, crossover and mutation operations are performed based on the genetic algorithm, and each optimal solution is used as the initial position of each particle in the particle swarm algorithm, where each particle represents a set of fire signal characteristics; Based on the preset initial velocity range, the initial velocity of particles is generated by uniform distribution; For each particle, based on the classification model, the fire signal characteristics it represents are input into the classification model, and the fitness is evaluated by calculating the classification accuracy of the model, that is, the fitness function is the classification accuracy calculation formula of the model; Each particle is updated based on the current fitness, the best historical fitness, and the global best position based on the preset position and speed update formula; When the algorithm reaches the set maximum number of iterations, the algorithm stops. At this time, the feature subset corresponding to the global optimal position of the particle is the optimal fire signal feature subset after optimization by the particle swarm algorithm.

5. The method for intelligent triggering and controlling of fire extinguishing stickers based on the Internet of Things according to claim 4 is characterized in that: Each particle is updated according to the current fitness, the best historical fitness, and the global best position based on the preset position and speed update formula, specifically: Get the historical best fitness of each particle. If the current particle's fitness is better than its historical best fitness, update the particle's personal best position based on the preset position and speed update formula. By comparing the personal best positions of all particles, the particle with the best fitness is found, the solution of this particle is taken as the global optimal solution, and the global best position is updated.

6. The method for intelligent triggering and controlling of fire extinguishing stickers based on the Internet of Things according to claim 1 is characterized in that: The fire signal feature subset is used to construct a fire warning model based on the random forest algorithm, and the triggering of the fire extinguishing sticker is controlled based on the prediction result of the fire warning model, specifically: Acquire historical fire data, obtain fire thresholds of different fire signal characteristics based on the historical fire data based on a regression analysis method, and mark the corresponding fire thresholds into a fire signal characteristic subset, wherein the fire signal characteristics include air pressure characteristics, current fluctuation characteristics, temperature characteristics, smoke concentration characteristics, and gas concentration characteristics; The annotated fire signal feature subsets are divided into a training set and a test set, and a corresponding number of decision trees are constructed according to the fire signal features in the training set; Train each decision tree to form an independent decision tree, and set the optimal split point based on the impurity of the Gini index; The root node is divided based on the optimal division point until the maximum depth of the tree is reached, the division stops, and the leaf node is generated; If the proportion of fire samples in a leaf node is greater than the proportion of non-fire samples, the label of the leaf node is fire, otherwise it is non-fire; Integrate the generated results of all decision trees and obtain the final prediction result based on the average mechanism; When the prediction result is fire, the fire extinguishing sticker is controlled to be triggered to carry out fire extinguishing.

7. The method for intelligent triggering and controlling of fire extinguishing stickers based on the Internet of Things according to claim 1 is characterized in that: The fire location is obtained according to the position of the fire extinguishing sticker after the trigger, the fire extinguishing situation is judged and the fire extinguishing sticker is mobilized, specifically: After the fire extinguishing sticker is triggered, the fire warning model is used to make another prediction to determine whether the fire has been extinguished; If the fire is not extinguished, obtain the spread of the fire source and formulate mobilization rules based on the distribution of fire extinguishing stickers in the fire extinguishing sticker matrix; The fire extinguishing sticker matrix is ​​updated in real time according to the mobilization results.

8. The method for intelligent triggering and controlling of fire extinguishing stickers based on the Internet of Things according to claim 7 is characterized in that: The diffusion of the fire source is obtained and the mobilization rules are formulated according to the distribution of the fire extinguishing stickers in the fire extinguishing sticker matrix, specifically: Based on graph theory and graph search algorithm, the fire extinguishing area and the fire extinguishing sticker matrix are regarded as a graph, where each position is set as a node and the neighborhood within a preset range is an edge; The neighborhood is traversed by the breadth-first search method. According to the spread of the fire source, the nodes closest to the fire source and the fire extinguishing posts in the direction of the fire source spread are traversed first; By traversing layer by layer, judging whether the fire extinguishing sticker can be triggered within the preset time according to the status data of the fire extinguishing sticker; If it cannot be triggered, continue to traverse until a fire extinguishing sticker that can be triggered and has the shortest path to the fire source is found, and control the fire extinguishing sticker to extinguish the fire.

9. The method for intelligent triggering and controlling of fire extinguishing stickers based on the Internet of Things according to claim 4 is characterized in that: The specific calculation formula of the initial velocity of the particle is as follows: in , The classification accuracy calculation formula is as follows: In the formula, For particles At the moment The initial velocity, is the preset maximum speed. is the preset minimum speed. is a random number, is the classification accuracy, is the number of samples that are fire and are correctly classified as fire, The number of samples that are non-fire and correctly classified as non-fire, The number of non-fire samples that were misclassified as fire, The number of samples that were fire but were misclassified as non-fire.

10. A system using the method for intelligent triggering and controlling a fire extinguishing sticker based on the Internet of Things as claimed in any one of claims 1 to 9, characterized in that: It includes matrix construction and data processing module, feature optimization module, fire warning module and fire extinguishing sticker mobilization module. There are connections between the modules: The matrix construction and data processing module is used to construct the fire extinguishing sticker matrix of the area to be tested and obtain the initial fire signal data. The initial fire signal data is decomposed by DWT based on the blind source separation method and wavelet threshold denoising method to obtain fire signal characteristics of different scales. A feature optimization module, used for optimizing the fire signal features based on a particle swarm algorithm to obtain a fire signal feature subset; The fire warning module is used to construct a fire warning model based on the random forest algorithm using a subset of fire signal features, and to control the triggering of fire extinguishing stickers based on a dynamic threshold adjustment method; The fire extinguishing sticker mobilization module is used to obtain the fire location according to the position of the fire extinguishing sticker after triggering, judge the fire extinguishing situation and mobilize the fire extinguishing sticker.

Images