Intelligent fire-fighting smoke sensing alarm method and system based on Internet of Things

Abstract

The invention relates to the technical field of flue gas alarm, in particular to an intelligent fire-fighting flue gas sensing alarm method and system based on the Internet of Things, and the method comprises the following steps: installing a spectral analysis sensor in a key area of a building, capturing a spectral signal, collecting flue gas spectral data according to a preset time interval, and the spectrum data is transmitted to a cloud platform through the Internet of Things network node, the data format is unified, and a spectrum data set is generated. According to the invention, by capturing and analyzing the spectral characteristic curve of the flue gas, different types of flue gas can be distinguished, fire flue gas and non-fire flue gas can be efficiently distinguished, the false alarm phenomenon is reduced, the sensitivity of the sensor and the alarm threshold value are dynamically adjusted in combination with real-time environmental data, high reliability can still be maintained in a complex and changeable environment, and the system is suitable for popularization and application. And meanwhile, multi-equipment response can be synchronously triggered, mechanisms such as a fire-fighting nozzle and smoke-proof exhaust equipment can be quickly started, fire alarm signals are transmitted to related departments in real time, the response time is shortened, and the linkage effect of fire emergency treatment is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of smoke alarm technology, and in particular to an intelligent fire smoke sensing alarm method and system based on the Internet of Things. Background Art

[0002] The field of smoke alarm technology involves the development and implementation of devices and systems for detecting smoke, toxic gases, and other fire-related indicators. Its core goal is to improve safety by detecting smoke and other fire signs early, thereby initiating timely alarms and countermeasures. Smoke alarm systems can be based on various sensing technologies, such as photoelectric (which uses light scattering to detect smoke particles) and ionic (which detects smoke through changes in ions in the air). With technological advancements, modern smoke alarm systems also integrate the Internet of Things (IoT) to enable real-time data transmission, remote monitoring, and intelligent response, enhancing system effectiveness and user interaction.

[0003] Smart fire smoke sensing and alarm systems are primarily designed to enhance the functionality of traditional smoke detection and alarm systems through intelligent technology. Leveraging IoT technology, they can collect environmental data in real time, connect to cloud platforms for data analysis, and promptly alert users to potential fire risks. Furthermore, they can interact with other smart home devices, such as automatically activating air purifiers and shutting down ventilation systems, to reduce fire damage. Their primary applications include fire prevention and early response in residential, commercial, and industrial areas, improving the speed and efficiency of fire response and significantly enhancing the safety and protection of people and property.

[0004] Existing technologies mostly rely on a single sensor type to detect changes in smoke particles or ions. They lack the ability to accurately identify smoke types in complex environments, and there is a high false alarm rate when distinguishing between non-fire smoke such as tobacco smoke and cooking smoke and fire smoke, making it difficult to ensure accurate alarms. In terms of environmental variable processing, traditional equipment fails to dynamically adapt to environmental changes such as wind speed and humidity, resulting in reduced detection performance in scenarios with strong airflow or high humidity. Data transmission mostly relies on local storage and processing, lacks a unified remote data integration and analysis mechanism, and the real-time nature of information is poor, which limits the coverage and response speed of fire monitoring. Alarm systems are usually triggered by a single device and lack the ability to respond to multiple devices in a coordinated manner, making it difficult to quickly activate a comprehensive firefighting mechanism. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the existing technology and propose an intelligent fire smoke sensing alarm method and system based on the Internet of Things.

[0006] In order to achieve the above objectives, the present invention adopts the following technical solution: a smart fire smoke sensing alarm method based on the Internet of Things, comprising the following steps: S1: Install spectral analysis sensors in key areas of the building to capture spectral signals, collect smoke spectral data at preset time intervals, and transmit them to the cloud platform through IoT network nodes to unify the data format and generate spectral data sets; S2: Based on the spectral data set, analyze the spectral characteristic curve of the flue gas, calibrate the key absorption peak position, match and classify the spectral peak with the standard range according to the standard spectral range of the flue gas type, and determine the flue gas type based on the matching result to generate a flue gas classification result; S3: Based on the smoke classification results, combined with the real-time wind speed and humidity data collected by the environmental monitoring sensor, the impact of wind speed and humidity on smoke propagation is analyzed, and the environmental variables are combined with the sensitivity parameters of the smoke sensor to calculate a new sensitivity threshold and generate adjusted sensor parameters; S4: Based on the adjusted sensor parameters, after detecting the type of fire smoke, activating the preset response device, transmitting the fire alarm signal to the fire sprinkler and triggering the sprinkler water supply mechanism, and simultaneously sending the fire alarm signal to the smoke exhaust equipment to generate a fire alarm response signal; S5: Based on the fire alarm response signal, a real-time fire alarm notification is sent to the fire department's receiving terminal through the Internet of Things gateway, the fire alarm time, type and triggering device data are uploaded, and all smoke monitoring and response processes are recorded to generate emergency communication and data records.

[0007] As a further solution of the present invention, the spectral data set includes smoke spectral characteristic values, timestamp data and sensor deployment location records; the smoke classification results include fire smoke category identification, non-fire smoke category identification and spectral absorption peak position information; the adjusted sensor parameters include updated sensitivity thresholds and dynamic alarm trigger values; the fire alarm response signals include fire sprinkler start-up signals, smoke and exhaust control signals and fire alarm status identifications; the emergency communications and data records include fire alarm event notification data, equipment trigger records and fire alarm event time series logs.

[0008] As a further solution of the present invention, spectral analysis sensors are installed in key areas of the building to capture spectral signals, collect smoke spectral data at preset time intervals, and transmit them to the cloud platform through the Internet of Things network nodes. The data format is unified and the specific steps for generating spectral data sets are as follows: S101: Install spectral analysis sensors in key areas of the building to capture spectral signals. Segmented sampling of smoke spectral signals is performed by adjusting the sampling frequency and spectral band range. The collected data is transmitted to the IoT network node in the form of digital signals in conjunction with the sensor interface protocol to generate the original data set. S102: Based on the original data set, duplicate data is directly compared, screened, and deleted, different field type data is uniformly coded, and field mapping rules are set for consistency calibration to obtain a standardized data set; S103: Based on the standardized data set, the data is segmented and transmitted to the cloud database through a batch transmission mechanism, and the data is tagged with acquisition time, geographic location, and spectral characteristics for structured and hierarchical storage to generate a spectral data set.

[0009] As a further embodiment of the present invention, based on the spectral data set, the spectral characteristic curve of the flue gas is analyzed, the key absorption peak positions are calibrated, the spectral peaks are matched and classified according to the standard spectral range of the flue gas type, and the flue gas type is determined based on the matching results. The specific steps for generating the flue gas classification result are as follows: S201: Based on the spectral data set, reading the light intensity values ​​in the spectral data point by point and constructing a continuous spectral curve, performing peak detection on the spectral curve to identify the local maximum area, calculating the peak center position, and recording the corresponding light intensity value, combining curve fitting to confirm the outline and position of the key peak, and generating spectral characteristic peak data; S202: Based on the spectral characteristic peak data, perform interval matching on the peak position by comparing with the standard spectral range, extract absorption peak parameters that meet the range conditions, and assign a unique identification code to each calibrated absorption peak to generate key absorption peak calibration data; S203: Based on the key absorption peak calibration data, calculate the similarity score between the calibration peak parameters and the standard spectrum data of the smoke type, associate the peak characteristics with the corresponding smoke type, perform smoke type matching and classification, and generate a smoke classification result.

[0010] As a further embodiment of the present invention, the similarity score is calculated according to the formula: ; Calculate, where represents the similarity score, Represents the peak parameter value of the flue gas sample at the key absorption peak, Represents the peak parameter value in the standard spectrum data corresponding to the flue gas type, Represents the total energy value of the absorption peak obtained in the actual test, Represents the preset standard absorption peak energy value.

[0011] As a further solution of the present invention, based on the smoke classification results and combined with real-time wind speed and humidity data collected by environmental monitoring sensors, the influence of wind speed and humidity on smoke propagation is analyzed, and the environmental variables are combined with the sensitivity parameters of the smoke sensor to calculate a new sensitivity threshold. The specific steps for generating adjusted sensor parameters are as follows: S301: Collect real-time wind speed and humidity data through environmental monitoring sensors, group the wind speed data into time series and extract the wind speed mean of each group of data, perform interval statistics on the humidity data and analyze the frequency distribution characteristics, and simultaneously integrate the data to generate environmental variable impact data; S302: Based on the smoke classification results and the environmental variable impact data, respectively calculating the correlation between the wind speed mean, humidity frequency distribution characteristics, and smoke diffusion parameters, comparing the effects of wind speed and humidity on the smoke diffusion parameters, and performing a joint impact analysis of wind speed and humidity through normalization to generate environmental impact analysis data; S303: Based on the environmental impact analysis data, the sensor sensitivity parameters are jointly adjusted. The combined impact of wind speed and humidity is weighted and calculated with the current sensor sensitivity parameters to calculate a new threshold. The calculation results are grouped and archived according to parameter type and recorded to generate adjusted sensor parameters.

[0012] As a further solution of the present invention, the new threshold is according to the formula: ; Calculate, where represents the new threshold, represents the measured value of wind speed, Represents the measured value of relative humidity.

[0013] As a further embodiment of the present invention, based on the adjusted sensor parameters, after detecting the type of fire smoke, a preset response device is activated, a fire alarm signal is transmitted to the fire sprinkler, and the sprinkler water supply mechanism is triggered, and a fire alarm signal is simultaneously sent to the smoke exhaust device. The specific steps for generating the fire alarm response signal are as follows: S401: Based on the adjusted sensor parameters, smoke type detection is performed by receiving the spectral characteristic signal of the smoke sensor in real time and comparing it point by point with the new threshold, extracting smoke type data that matches the new threshold condition, and generating a fire alarm trigger signal; S402: Based on the fire alarm trigger signal, a preset response device is activated, a signal is transmitted to a fire sprinkler control unit to start a sprinkler water supply mechanism, a signal is simultaneously sent to a smoke and exhaust device to activate an exhaust mode, and a fire equipment response status record is generated; S403: Based on the fire equipment response status record, the fire equipment response status data is transmitted to the central fire control platform, the trigger time and the response equipment number are recorded, the equipment operation status is monitored in real time, and a fire alarm response signal is generated.

[0014] As a further solution of the present invention, based on the fire alarm response signal, a real-time fire alarm notification is sent to the fire department's receiving terminal via the IoT gateway, the fire alarm time, type, and triggering device data are uploaded, and all smoke monitoring and response processes are recorded. The specific steps for generating emergency communication and data records are as follows: S501: Based on the fire alarm response signal, the fire alarm signal is received through the IoT gateway, the trigger time, type, and device number are extracted and converted into structured data, combined into a standard data packet according to data priority, and sent to the fire department receiving terminal to generate fire alarm notification data; S502: Based on the fire alarm notification data, the fire alarm trigger time, type, and device number are mapped to the platform data table format item by item through the network interface and uploaded. After the upload is completed, the transmission status is recorded in real time and the transmission result is verified to obtain the fire alarm information upload record; S503: Based on the fire alarm information upload record, the smoke monitoring and response process is recorded, and the key feature data of the sensor's historical monitoring and the equipment action trigger record are extracted, integrated according to the time series, and the response events are annotated with data tags and stored to generate emergency communications and data records.

[0015] An intelligent fire smoke sensing alarm system based on the Internet of Things, comprising: The spectral signal capture module installs spectral analysis sensors in key areas of the building to capture spectral signals, directly compares and filters out duplicate data, and transmits the data in segments to the cloud database through a batch transmission mechanism for structured and hierarchical storage to generate a spectral data set. Based on the spectral data set, the spectral data analysis module reads the light intensity values ​​in the spectral data point by point and constructs a continuous spectral curve. It then performs interval matching of the peak positions by comparing them with the standard spectral range, calculates the similarity score between the calibrated peak parameters and the standard spectral data of the flue gas type, performs smoke type matching and classification, and generates a smoke classification result. The environmental data analysis module collects real-time wind speed and humidity data through the environmental monitoring sensor, calculates the correlation between the wind speed mean, humidity frequency distribution characteristics and smoke diffusion parameters, performs a weighted operation on the combined impact of wind speed and humidity and the current sensor sensitivity parameter to calculate a new threshold, and generates adjusted sensor parameters; The smoke monitoring response module receives the spectral characteristic signal of the smoke sensor in real time and compares it with the new threshold point by point based on the adjusted sensor parameters, activates the preset response device, and generates a fire protection equipment response status record; The data transmission and recording module transmits the fire equipment response status data to the central fire control platform based on the fire equipment response status record, records the trigger time and the responding equipment number, extracts and converts it into structured data, and sends it to the fire department receiving terminal to generate fire alarm notification data; Based on the fire alarm notification data, the information integration and reporting module maps the fire alarm trigger time, type and equipment number to the platform data table format item by item through the network interface and uploads it, records the smoke monitoring and response process, and extracts the key feature data of the sensor's historical monitoring and equipment action trigger records, integrates them according to the time series, and generates emergency communication and data records.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by capturing and analyzing the spectral characteristic curves of smoke, different types of smoke can be distinguished, fire smoke and non-fire smoke can be efficiently distinguished, false alarms can be reduced, and the sensor sensitivity and alarm threshold can be dynamically adjusted in combination with real-time environmental data. High reliability can be maintained in complex and changing environments. At the same time, multiple devices can be triggered to respond synchronously, fire sprinklers, smoke exhaust equipment and other mechanisms can be quickly activated, and fire alarm signals can be transmitted to relevant departments in real time, shortening response time and optimizing the linkage effect of fire emergency response. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 Schematic diagram of the steps of the present invention; Figure 2 is a flow chart of the steps of S1 of the present invention; Figure 3 This is a flow chart of the steps of S2 of the present invention; Figure 4 This is a flow chart of the steps of S3 of the present invention; Figure 5 This is a flow chart of the steps of S4 of the present invention; Figure 6 This is a flow chart of the steps of S5 of the present invention; Figure 7 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0019] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined.

[0020] See also Figure 1 , a smart fire smoke sensing alarm method based on the Internet of Things, comprising the following steps: S1: Install spectral analysis sensors in key areas of the building to capture spectral signals, collect smoke spectral data at preset time intervals, and transmit them to the cloud platform through IoT network nodes to unify the data format and generate spectral data sets; S2: Based on the spectral data set, analyze the spectral characteristic curve of the flue gas, calibrate the key absorption peak position, match and classify the spectral peak with the standard range according to the flue gas type, and determine the flue gas type based on the matching results to generate the flue gas classification result; S3: Based on the smoke classification results and combined with the real-time wind speed and humidity data collected by environmental monitoring sensors, the impact of wind speed and humidity on smoke propagation is analyzed. The environmental variables are combined with the sensitivity parameters of the smoke sensor to calculate the new sensitivity threshold and generate the adjusted sensor parameters. S4: Based on the adjusted sensor parameters, after detecting the type of fire smoke, the preset response device is activated, the fire alarm signal is transmitted to the fire sprinkler and the sprinkler water supply mechanism is triggered. The fire alarm signal is simultaneously sent to the smoke exhaust equipment to generate a fire alarm response signal; S5: Based on the fire alarm response signal, real-time fire alarm notification is sent to the fire department's receiving terminal through the IoT gateway, the fire alarm time, type and triggering device data are uploaded, and all smoke monitoring and response processes are recorded to generate emergency communication and data records.

[0021] The spectral dataset includes smoke spectral characteristic values, timestamp data, and sensor deployment location records. The smoke classification results include fire smoke category identification, non-fire smoke category identification, and spectral absorption peak position information. The adjusted sensor parameters include updated sensitivity thresholds and dynamic alarm trigger values. Fire alarm response signals include fire sprinkler activation signals, smoke exhaust control signals, and fire alarm status identification. Emergency communications and data records include fire alarm event notification data, equipment trigger records, and fire alarm event time series logs.

[0022] See also Figure 2 , the specific steps of S1 are: S101: Install spectral analysis sensors in key areas of the building to capture spectral signals. Segmented sampling of smoke spectral signals is performed by adjusting the sampling frequency and spectral band range. The collected data is transmitted to the IoT network node in the form of digital signals in conjunction with the sensor interface protocol to generate the original data set. The installation of spectral analysis sensors in key areas of buildings involves selecting the appropriate sensor type, accurately determining the installation location, and calibrating the sensor. The sensor type must be able to accurately capture the spectral signals in the flue gas to more accurately monitor air quality. The selection of the installation location should be based on maximizing the efficiency of signal capture. The calibration process ensures that the data output by the device accurately reflects the actual spectral conditions in the environment. By adjusting the sampling frequency and spectral band, the device's detection sensitivity and accuracy for different chemical components can be optimized. The data is further transmitted in the form of digital signals through a protocol to ensure accurate data transmission and efficient subsequent processing.

[0023] S102: Based on the original data set, duplicate data is directly compared, screened, and deleted, different field type data is uniformly coded, and field mapping rules are set for consistency calibration to obtain a standardized data set; Based on the original data set, the first step is to perform data cleaning and delete duplicate data. This process involves directly comparing the integrity and uniqueness of each piece of data. After data cleaning, the next step is to encode the different fields in the data and unify the data format to enhance the consistency and availability of the data set. Field mapping ensures that each field in the data set can accurately correspond to the corresponding field in the database by setting specific conversion rules. This process not only improves data processing efficiency, but also reduces possible errors in data parsing. The final standardized data set is structured and consistent, which improves the reliability of the data and the accuracy of subsequent analysis.

[0024] S103: Based on the standardized data set, the data is segmented and transmitted to the cloud database through a batch transmission mechanism. The data is tagged with acquisition time, geographic location, and spectral characteristics, and structured and hierarchical storage is performed to generate a spectral data set. Using standardized data sets, implementing batch data upload and cloud storage involves segmenting the data and transmitting it securely to the cloud database over the network. Each data segment is assigned a timestamp, geographic location tag, and spectral feature tag. The tags provide rich contextual information for the data, which facilitates subsequent data analysis and application. The structured storage of the cloud database is optimized according to the type and purpose of the data to ensure the speed and accuracy of data retrieval. The process fully utilizes the elasticity and scalability of cloud computing. The generated spectral data set provides accurate and real-time data support for subsequent analysis and decision-making.

[0025] See also Figure 3 , the specific steps of S2 are: S201: Based on the spectral data set, the light intensity values ​​in the spectral data are read point by point and a continuous spectral curve is constructed. Peak detection is performed on the spectral curve to identify the local maximum area, the peak center position is calculated, and the corresponding light intensity value is recorded. The contour and position of the key peak are confirmed by curve fitting to generate spectral characteristic peak data; By reading the light intensity value in the spectral data point by point and constructing a continuous spectral curve, according to the formula , calculate the spectral characteristic peak data. Where, represents the characteristic peak of the spectrum, Representative The light intensity value of the data point, Representative The wavelength weight of the data point. Assume that there is data points, the light intensity value of each point is , the wavelength weight of each point It can be set according to the correlation strength between wavelength and spectral characteristics. For example, , and has the following intensity values ​​and wavelength weights: , Spectral characteristic peak The calculation process is: ; ; This result shows that the influence of light intensity and wavelength can be comprehensively considered by weighted summation, so that the characteristic peak value can be accurately calculated, providing precise numerical support for subsequent spectral analysis.

[0026] S202: Based on the spectral characteristic peak data, the peak position is interval-matched by comparing with the standard spectral range, the absorption peak parameters that meet the range conditions are extracted, and a unique identification code is assigned to each calibrated absorption peak to generate key absorption peak calibration data; Based on the spectral characteristic peak data, the processing at this stage involves comparing the peak position with the standard spectral range to ensure that the extracted peak conforms to the preset standard spectral range. This comparison process requires a high-precision matching algorithm to ensure accurate identification of the peak position. Each successfully matched peak will be assigned a unique identification code. The identification code creates an index in the database to facilitate subsequent query and analysis. The generated key absorption peak calibration data provides a key reference standard for subsequent analysis and application, increasing the traceability and scientific nature of data processing.

[0027] S203: Based on the key absorption peak calibration data, calculate the similarity score between the calibration peak parameters and the standard spectrum data of the smoke type, associate the peak characteristics with the corresponding smoke type, perform smoke type matching and classification, and generate a smoke classification result; Similarity score, according to the formula: ; Calculate, where represents the similarity score, Represents the peak parameter value of the flue gas sample at the key absorption peak, Represents the peak parameter value in the standard spectrum data corresponding to the flue gas type, Represents the total energy value of the absorption peak obtained in the actual test, Represents the preset standard absorption peak energy value.

[0028] In actual operation, The light intensity at a specific wavelength can be measured by spectroscopic analysis of a flue gas sample using a spectrometer. For example, the light intensity at a wavelength of 650nm is 120 units.

[0029] parameter This value represents the peak parameter in the standard spectrum data corresponding to the flue gas type. This value is standardized based on historical data and is generally a constant value at the same wavelength. For example, the standard peak value at a wavelength of 650nm is set to 100 units.

[0030] parameter This is the total energy of the absorption peak obtained during the actual test, which can be calculated by integrating the spectral data. When testing flue gas samples, the total energy of the absorption peak is set to 5000 units.

[0031] parameter Represents the pre-set standard absorption peak energy, also determined based on the standardization process and average value, assumed to be 4500 units.

[0032] First calculate and The product of , that is: ; calculate and The absolute value of the difference, that is: ; Find the square root of the above difference, which is: ; Finally, calculate the similarity score, using the previous results: ; The results show that the similarity score This score reflects the degree of match between a flue gas sample and a predetermined standard, with higher values ​​indicating greater similarity. Based on this score, the type of flue gas can be further determined. If the score reaches a certain threshold, it is identified as a specific type of flue gas, supporting environmental monitoring and control decision-making processes.

[0033] See also Figure 4 , the specific steps of S3 are: S301: Collect real-time wind speed and humidity data through environmental monitoring sensors, group the wind speed data into time series and extract the wind speed mean of each group of data, perform interval statistics on the humidity data and analyze the frequency distribution characteristics, and simultaneously integrate the data to generate environmental variable impact data; The process of collecting real-time wind speed and humidity data through environmental monitoring sensors involves the selection and configuration of high-precision sensors. The sensors periodically send the acquired data to the central processing unit. These data are first grouped into time series. Each group includes wind speed data within a certain time window. By calculating the mean wind speed of each group of data, the statistical characteristics of the wind speed within that time period can be effectively reflected. At the same time, the humidity data is processed through interval statistics to analyze the frequency of humidity occurrence in each interval. This process is extremely critical for understanding and predicting changes in environmental conditions. The simultaneous data integration work ensures the integrity and consistency of the data. The generated environmental variable impact data provides real-time and accurate basic data for subsequent analysis.

[0034] S302: Based on the smoke classification results and environmental variable impact data, the correlation between the wind speed mean, humidity frequency distribution characteristics, and smoke diffusion parameters is calculated, the effects of wind speed and humidity on smoke diffusion parameters are compared, and the combined impact of wind speed and humidity is analyzed through normalization to generate environmental impact analysis data; In the above content, by calculating the correlation between the wind speed mean, humidity frequency distribution characteristics and smoke diffusion parameters, according to the formula , calculate the environmental impact analysis data. Where, represents the correlation coefficient, and Represent the sample values ​​of wind speed and humidity respectively, and is the corresponding sample mean, and is the sample standard deviation, is the sample size. Assume that Sample points, wind speed sample value Meters / second, humidity sample value %, and the sample means of wind speed and humidity are m / s, %, sample standard deviation m / s, % Correlation coefficient The calculation process is: ; The results show that wind speed and humidity have a high correlation with smoke diffusion parameters, providing an accurate basis for quantitative analysis and helping to better understand the impact of environmental variables on smoke diffusion.

[0035] S303: Based on the environmental impact analysis data, the sensor sensitivity parameters are adjusted. The combined impact of wind speed and humidity is weighted and calculated with the current sensor sensitivity parameters to calculate a new threshold. The calculation results are grouped and archived by parameter type, and recorded to generate adjusted sensor parameters. The new threshold is as follows: ; Calculate, where represents the new threshold, represents the measured value of wind speed, Represents the measured value of relative humidity.

[0036] wind speed and relative humidity It is the data actually measured by environmental monitoring equipment. Measured at 10m / s, relative humidity The measured value is 80% (or 0.8 to suit the calculation). It is obtained by standard sensors in the weather station and sent to the central processing unit via data transmission technology.

[0037] Calculating wind speed and relative humidity The product of: ; Calculate the sum and square of the difference between wind speed and humidity: ; ; Compute the square root of the difference, and handle the absolute value internally: ; Divide the sum by the square root of the difference: ; Add the results together to get the new threshold: ; The results show that in an environment with a wind speed of 10 m / s and a humidity of 80%, the new sensor threshold should be adjusted to 9.083. This represents the sensitivity threshold that should be set for the sensor under given environmental conditions to ensure that it accurately responds to environmental changes and makes appropriate adjustments or reactions. In this way, sensor parameter adjustments can more accurately match actual changes in environmental conditions, enhancing stability and reliability.

[0038] See also Figure 5 , the specific steps of S4 are: S401: Based on the adjusted sensor parameters, smoke type detection is performed. The spectral characteristic signal of the smoke sensor is received in real time and compared point by point with the new threshold. The smoke type data that matches the new threshold condition is extracted and a fire alarm trigger signal is generated. Adjusted sensor parameters play a key role in smoke type detection. First, the sensor receives real-time spectral signature signals from the smoke. These signals contain key chemical composition information; each signal point represents the intensity of light at a specific wavelength, reflecting the specific type of smoke. Each received spectral signal is compared point by point against a pre-set threshold. This comparison is performed using a high-precision algorithm to ensure a precise match for every data point. When the sensor's signal intensity exceeds the threshold, the system identifies the smoke type corresponding to that spectral signature and triggers the corresponding fire alarm. Furthermore, the system records all smoke type data matching the new threshold conditions, which is subsequently used to generate a detailed fire alarm trigger log. This process not only ensures the fire alarm system's responsiveness but also significantly improves the accuracy of fire detection. It provides reliable data support for safety monitoring and emergency response, significantly enhancing the efficiency and reliability of the fire prevention system and ensuring swift and accurate action when a fire occurs.

[0039] S402: Based on the fire alarm trigger signal, the preset response device is activated, the sprinkler water supply mechanism is started by transmitting the signal to the fire sprinkler control unit, and the signal is simultaneously sent to the smoke exhaust equipment to activate the exhaust mode, and a fire equipment response status record is generated; Based on the fire alarm trigger signal, the core task at this stage is to effectively transmit the signal to the fire sprinkler control unit and activate the sprinkler water supply mechanism to respond to the fire. Specifically, after the fire alarm trigger signal is generated by the sensor, it is immediately transmitted to the fire protection system's central control unit via a wired or wireless network. The central control unit quickly analyzes the signal, confirms its validity, and then sends the command to each associated fire sprinkler control unit. Upon receiving the activation command, the control unit triggers the sprinkler's opening mechanism, thereby activating the water supply. Simultaneously, the signal is transmitted to the smoke and exhaust ventilation system. Upon receiving the activation signal, the smoke and exhaust ventilation equipment automatically turns on the exhaust fan according to the design settings, increasing the exhaust volume and rapidly discharging smoke and hazardous gases. This series of actions ensures that preliminary fire extinguishing and smoke control measures can be implemented at the earliest stage of a fire, reducing potential losses and damage caused by the fire. The generated record of the fire protection equipment's response status provides detailed operational data for future analysis and evaluation.

[0040] S403: Based on the fire equipment response status record, transmit the fire equipment response status data to the central fire control platform, record the trigger time and the responding equipment number, monitor the equipment operation status in real time, and generate a fire alarm response signal; After fire equipment response status records are generated, data processing and transmission become critical follow-up steps. Each fire equipment response and its status are recorded in real time, including the specific trigger time, responding equipment number, and operational status. This information is then transmitted to the central fire control platform, which serves as the information aggregation and monitoring center for the entire fire protection system. Via a high-speed data communication network, response data is rapidly uploaded to the platform, ensuring immediacy and accuracy. The platform's monitoring software organizes and displays the received data, providing real-time updates on the equipment's operating status and response status. Furthermore, the platform includes data analysis capabilities, which aggregate and analyze historical data to identify potential system vulnerabilities or equipment failures, further guiding the maintenance and upgrade of fire protection equipment. This complete chain, from equipment response to data monitoring, not only improves the fire protection system's responsiveness and safety management efficiency, but also supports rapid decision-making in emergency situations, enhancing overall safety assurance.

[0041] See also Figure 6 , the specific steps of S5 are: S501: Based on the fire alarm response signal, the fire alarm signal is received through the IoT gateway, the trigger time, type, and device number are extracted and converted into structured data, combined into a standard data packet according to the data priority, and sent to the fire department receiving terminal to generate fire alarm notification data; The IoT gateway plays a critical role as a data transfer station in the fire alarm response signal reception process. First, the gateway receives fire alarm signals from sensors, including key information such as trigger time, fire alarm type, and device number. This data is converted into a structured format in real time to ensure accurate and efficient subsequent processing. The system then prioritizes the data based on its urgency and assembles it into standardized data packets. This data packet contains all necessary fire alarm information, ensuring that the fire department's receiving terminal can quickly access and process it. The data packets are transmitted over a secure network channel, with strict security protocols implemented at each step to ensure the security and integrity of the information during transmission. The resulting fire alarm notification data not only provides the fire department with real-time fire alerts but also, through accurate information recording, provides the foundational data for subsequent investigations and analysis, significantly improving the efficiency and effectiveness of emergency response.

[0042] S502: Based on the fire alarm notification data, the fire alarm trigger time, type, and device number are mapped to the platform data table format item by item through the network interface and uploaded. After the upload is completed, the transmission status is recorded in real time and the transmission result is verified to obtain the fire alarm information upload record; Based on the fire alarm notification data, the entire data upload and recording process involves several key steps. First, the fire alarm trigger time, type and device number are extracted item by item from the received data and formatted with the data table of the central platform to ensure that all uploaded data is compatible with the storage format of the platform. After the data mapping is completed, the system uploads the information to the central monitoring platform through the network interface. This upload process is equipped with advanced data encryption and security verification measures to ensure the security and reliability of data transmission. After the upload is completed, the system not only records the status of each transmission, but also verifies the transmission results to ensure the accuracy and completeness of the data. The generated fire alarm information upload record not only provides the fire department with key fire alarm processing data, but also ensures the transparency and traceability of the data processing process, and enhances the response capability and management efficiency in emergency situations.

[0043] S503: Based on the fire alarm information upload record, the smoke monitoring and response process is recorded. By extracting the key feature data of the sensor's historical monitoring and the equipment action trigger record, integrating them according to the time series, and annotating the response event data with data tags and storing them, an emergency communication and data record is generated; In the process of generating emergency communications and data records, integrating and labeling historical monitoring data becomes a core task. Key features are extracted from the historical monitoring data of the sensors, including smoke composition, concentration and its changing trends. The data is integrated in time series to ensure the timeliness and continuity of the information. At the same time, the action trigger records of all relevant equipment are also captured and recorded, such as the start time and duration of response measures such as water spraying and smoke exhaust. The data is tagged by the system for rapid identification and access in subsequent analysis and investigation. Ultimately, all information is stored in a secure database, providing important data support for future safety analysis, equipment maintenance and upgrade decisions, ensuring the continuous optimization of the system and improving the accuracy of emergency response.

[0044] See also Figure 7 , a smart fire smoke sensing alarm system based on the Internet of Things, including: The spectral signal capture module installs spectral analysis sensors in key areas of the building to capture spectral signals, directly compares and filters out duplicate data, and transmits the data in segments to the cloud database through a batch transmission mechanism for structured and hierarchical storage to generate a spectral data set. The spectral data analysis module, based on the spectral data set, reads the light intensity values ​​in the spectral data point by point and constructs a continuous spectral curve. It then matches the peak position intervals by comparing it with the standard spectral range, calculates the similarity score between the calibrated peak parameters and the standard spectral data of the flue gas type, performs smoke type matching and classification, and generates a smoke classification result. The environmental data analysis module collects real-time wind speed and humidity data through environmental monitoring sensors, calculates the correlation between the wind speed mean, humidity frequency distribution characteristics, and smoke diffusion parameters, and performs a weighted operation on the combined impact of wind speed and humidity and the current sensor sensitivity parameters to calculate a new threshold and generate adjusted sensor parameters; The smoke monitoring response module receives the spectral characteristic signal of the smoke sensor in real time and compares it with the new threshold point by point based on the adjusted sensor parameters, activates the preset response device, and generates a record of the fire equipment response status; The data transmission and recording module transmits the fire equipment response status data to the central fire control platform based on the fire equipment response status record, records the trigger time and the responding equipment number, extracts and converts it into structured data, and sends it to the fire department receiving terminal to generate fire alarm notification data; The information integration and reporting module is based on fire alarm notification data. It maps the fire alarm trigger time, type and equipment number to the platform data table format and uploads them item by item through the network interface, records the smoke monitoring and response process, and extracts the key feature data of the sensor's historical monitoring and equipment action trigger records, integrates them according to time series, and generates emergency communication and data records.

[0045] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A smart fire smoke sensing alarm method based on the Internet of Things, characterized in that: The following steps are involved: Spectral analysis sensors are installed in key areas of the building to capture spectral signals, collect smoke spectral data at preset time intervals, and transmit them to the cloud platform through IoT network nodes to unify the data format and generate spectral data sets; Based on the spectral data set, the spectral characteristic curve of the flue gas is analyzed, the key absorption peak positions are calibrated, the spectral peaks are matched and classified with the standard spectral range according to the flue gas type, and the flue gas type is determined based on the matching results to generate a flue gas classification result; Based on the smoke classification results, combined with the real-time wind speed and humidity data collected by the environmental monitoring sensor, the influence of wind speed and humidity on smoke propagation is analyzed, and the environmental variables are combined with the sensitivity parameters of the smoke sensor to calculate a new sensitivity threshold and generate adjusted sensor parameters; Based on the adjusted sensor parameters, after detecting the type of fire smoke, the preset response device is activated, the fire alarm signal is transmitted to the fire sprinkler and the sprinkler water supply mechanism is triggered, and the fire alarm signal is simultaneously sent to the smoke exhaust equipment to generate a fire alarm response signal; Based on the fire alarm response signal, a real-time fire alarm notification is sent to the fire department's receiving terminal through the Internet of Things gateway, the fire alarm time, type and triggering device data are uploaded, and all smoke monitoring and response processes are recorded to generate emergency communications and data records.

2. The smart fire smoke sensing alarm method based on the Internet of Things according to claim 1 is characterized in that: The spectral dataset includes smoke spectral characteristic values, timestamp data and sensor deployment location records; the smoke classification results include fire smoke category identification, non-fire smoke category identification and spectral absorption peak position information; the adjusted sensor parameters include updated sensitivity thresholds and dynamic alarm trigger values; the fire alarm response signals include fire sprinkler activation signals, smoke exhaust control signals and fire alarm status identifications; the emergency communications and data records include fire alarm event notification data, equipment trigger records and fire alarm event time series logs.

3. The smart fire smoke sensing alarm method based on the Internet of Things according to claim 1 is characterized in that: Spectral analysis sensors are installed in key areas of the building to capture spectral signals. Smoke spectral data is collected at preset time intervals and transmitted to the cloud platform through IoT network nodes. The data format is unified and the specific steps to generate the spectral data set are as follows: Spectral analysis sensors are installed in key areas of the building to capture spectral signals. Smoke spectral signals are sampled in segments by adjusting the sampling frequency and spectral band range. The collected data is transmitted to the IoT network node in the form of digital signals in conjunction with the sensor interface protocol to generate the original data set. Based on the original data set, duplicate data is directly compared, screened and deleted, different field type data is uniformly coded, and field mapping rules are set for consistency calibration to obtain a standardized data set; Based on the standardized data set, the data is segmented and transmitted to the cloud database through a batch transmission mechanism. The data is labeled with acquisition time, geographic location, and spectral characteristics for structured and hierarchical storage to generate a spectral data set.

4. The smart fire smoke sensing alarm method based on the Internet of Things according to claim 1 is characterized in that: Based on the spectral data set, the spectral characteristic curve of the flue gas is analyzed, the key absorption peak positions are calibrated, and the spectral peaks are matched and classified according to the standard spectral range of the flue gas type. The flue gas type is determined based on the matching results. The specific steps for generating the flue gas classification result are as follows: Based on the spectral data set, the light intensity values ​​in the spectral data are read point by point and a continuous spectral curve is constructed. Peak detection is performed on the spectral curve to identify the local maximum area, the peak center position is calculated, and the corresponding light intensity value is recorded. The profile and position of the key peak are confirmed by curve fitting to generate spectral characteristic peak data; Based on the spectral characteristic peak data, the peak position is interval matched by comparing the standard spectral range, the absorption peak parameters that meet the range conditions are extracted, and a unique identification code is assigned to each calibrated absorption peak to generate key absorption peak calibration data; Based on the key absorption peak calibration data, the similarity score between the calibration peak parameters and the standard spectrum data of the smoke type is calculated, the peak characteristics are associated with the corresponding smoke type, the smoke type is matched and classified, and the smoke classification result is generated.

5. The smart fire smoke sensing alarm method based on the Internet of Things according to claim 4 is characterized in that: The similarity score is calculated according to the formula: ； Calculate, where represents the similarity score, Represents the peak parameter value of the flue gas sample at the key absorption peak, Represents the peak parameter value in the standard spectrum data corresponding to the flue gas type, Represents the total energy value of the absorption peak obtained in the actual test, Represents the preset standard absorption peak energy value.

6. The smart fire smoke sensing alarm method based on the Internet of Things according to claim 1 is characterized in that: Based on the smoke classification results, combined with the real-time wind speed and humidity data collected by the environmental monitoring sensor, the impact of wind speed and humidity on smoke propagation is analyzed. The environmental variables are combined with the sensitivity parameters of the smoke sensor to calculate the new sensitivity threshold. The specific steps for generating the adjusted sensor parameters are as follows: Real-time wind speed and humidity data are collected through environmental monitoring sensors. Time series of wind speed data are grouped and the mean wind speed of each group of data is extracted. Interval statistics of humidity data are performed and frequency distribution characteristics are analyzed. Simultaneously, data are unified and integrated to generate environmental variable impact data. Based on the smoke classification results and the environmental variable impact data, respectively calculating the correlation between the wind speed mean, humidity frequency distribution characteristics, and smoke diffusion parameters, comparing the effects of wind speed and humidity on smoke diffusion parameters, and performing a joint impact analysis of wind speed and humidity through normalization to generate environmental impact analysis data; Based on the environmental impact analysis data, the sensor sensitivity parameters are jointly adjusted, the combined impact of wind speed and humidity is weighted and calculated with the current sensor sensitivity parameters to calculate a new threshold value, the calculation results are grouped and archived according to parameter type and recorded to generate adjusted sensor parameters.

7. The smart fire smoke sensing alarm method based on the Internet of Things according to claim 6 is characterized in that: The new threshold is according to the formula: ； Calculate, where represents the new threshold, represents the measured value of wind speed, Represents the measured value of relative humidity.

8. The method for intelligent fire smoke sensing alarm based on the Internet of Things according to claim 1 is characterized in that: Based on the adjusted sensor parameters, after detecting the type of fire smoke, the preset response device is activated, the fire alarm signal is transmitted to the fire sprinkler and the sprinkler water supply mechanism is triggered, and the fire alarm signal is simultaneously sent to the smoke exhaust equipment. The specific steps for generating the fire alarm response signal are as follows: Based on the adjusted sensor parameters, smoke type detection is performed by receiving the spectral characteristic signal of the smoke sensor in real time and comparing it point by point with the new threshold, extracting smoke type data that matches the new threshold condition, and generating a fire alarm trigger signal; Based on the fire alarm trigger signal, the preset response device is activated, the sprinkler water supply mechanism is started by transmitting the signal to the fire sprinkler control unit, the signal is simultaneously sent to the smoke exhaust equipment and the exhaust mode is activated, and a fire equipment response status record is generated; Based on the fire equipment response status record, the fire equipment response status data is transmitted to the central fire control platform, the trigger time and the response equipment number are recorded, the equipment operation status is monitored in real time, and a fire alarm response signal is generated.

9. The smart fire smoke sensing alarm method based on the Internet of Things according to claim 1 is characterized in that: Based on the fire alarm response signal, a real-time fire alarm notification is sent to the fire department's receiving terminal through the IoT gateway, the fire alarm time, type and triggering device data are uploaded, and all smoke monitoring and response processes are recorded. The specific steps for generating emergency communication and data records are as follows: Based on the fire alarm response signal, the fire alarm signal is received through the Internet of Things gateway, the trigger time, type and device number are extracted and converted into structured data, combined into a standard data packet according to the data priority and sent to the fire department receiving terminal to generate fire alarm notification data; Based on the fire alarm notification data, the fire alarm trigger time, type and device number are mapped to the platform data table format item by item through the network interface and uploaded. After the upload is completed, the transmission status is recorded in real time and the transmission result is verified to obtain the fire alarm information upload record; Based on the fire alarm information upload record, the smoke monitoring and response process is recorded. By extracting the key feature data of the sensor's historical monitoring and the equipment action trigger record, integrating them according to the time series, and annotating the response events with data tags for storage, emergency communications and data records are generated.

10. An intelligent fire smoke sensing alarm system based on the Internet of Things, characterized in that: The smart fire smoke sensing alarm method based on the Internet of Things according to any one of claims 1 to 9, wherein the system comprises: The spectral signal capture module installs spectral analysis sensors in key areas of the building to capture spectral signals, directly compares and filters out duplicate data, and transmits the data in segments to the cloud database through a batch transmission mechanism for structured and hierarchical storage to generate a spectral data set. Based on the spectral data set, the spectral data analysis module reads the light intensity values ​​in the spectral data point by point and constructs a continuous spectral curve. It then performs interval matching of the peak positions by comparing them with the standard spectral range, calculates the similarity score between the calibrated peak parameters and the standard spectral data of the flue gas type, performs smoke type matching and classification, and generates a smoke classification result. The environmental data analysis module collects real-time wind speed and humidity data through the environmental monitoring sensor, calculates the correlation between the wind speed mean, humidity frequency distribution characteristics and smoke diffusion parameters, performs a weighted operation on the combined impact of wind speed and humidity and the current sensor sensitivity parameter to calculate a new threshold, and generates adjusted sensor parameters; The smoke monitoring response module receives the spectral characteristic signal of the smoke sensor in real time and compares it with the new threshold point by point based on the adjusted sensor parameters, activates the preset response device, and generates a fire protection equipment response status record; The data transmission and recording module transmits the fire equipment response status data to the central fire control platform based on the fire equipment response status record, records the trigger time and the responding equipment number, extracts and converts it into structured data, and sends it to the fire department receiving terminal to generate fire alarm notification data; Based on the fire alarm notification data, the information integration and reporting module maps the fire alarm trigger time, type and equipment number to the platform data table format item by item through the network interface and uploads it, records the smoke monitoring and response process, and extracts the key feature data of the sensor's historical monitoring and equipment action trigger records, integrates them according to the time series, and generates emergency communication and data records.

Images