Fire resisting shutter alarm control system and method based on Internet of Things

Abstract

The invention provides a fire resisting shutter alarm control system and method based on the Internet of Things. The system comprises a spectrum and vibration monitoring module, a structure vibration analysis module, a fire behavior threshold setting and control module, a personnel detection and shutter control module and a multi-layer alarm and linkage module. Through real-time monitoring and intelligent judgment, the system can quickly identify the existence of personnel when a fire occurs, so that accidental injury is avoided. Meanwhile, the mechanism effectively reduces the confusion degree under the fire hazard condition, and improves the personnel evacuation efficiency. Compared with a traditional fire resisting shutter system, the flexibility and adaptability of the system are enhanced by achieving intelligent monitoring and response.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent fire safety, and in particular relates to a fireproof roller shutter alarm control system and method based on the Internet of Things. Background Art

[0002] Fireproof roller shutter is an important device used in the field of intelligent fire safety, which is designed to effectively block the spread of fire and protect life and property. Its working principle is to automatically pull down the roller shutter to form a fire barrier by sensing the fire signal or the alarm of the smoke detector. This process can significantly shorten the evacuation time and improve the emergency response capability.

[0003] Fire shutters have several notable features. First, their automation allows them to be linked to the fire alarm system and quickly lowered when a fire occurs. Second, fire shutters are made of high-temperature resistant materials, which can effectively block flames and heat and slow the spread of fire. In addition, modern fire shutters can also be combined with intelligent building management systems to achieve real-time monitoring and management of fire safety status. Finally, the design of fire shutters takes into account architectural aesthetics and can be integrated with various architectural styles, making them both practical and beautiful.

[0004] In actual applications, fire shutters are widely used in crowded places such as shopping malls, hospitals, and schools, as well as high-risk areas such as industrial plants, storage and logistics centers, and even special functional areas such as underground garages and machine rooms. Through the reasonable application of fire shutters, the fire safety performance of buildings can be significantly improved, and the safety of people and property can be effectively protected.

[0005] Traditional fire shutters generally rely on smoke detectors or heat sensors to determine the fire situation, but they do not have the ability to monitor whether there are people inside the shutter in real time. This means that even when a fire occurs, the system cannot confirm whether there are people trapped inside the shutter. After the fire alarm, the fire shutter will automatically close to prevent the fire from spreading. However, if there are people inside the shutter at this time, the sudden closing of the shutter may cause people to be trapped or even cause casualties.

[0006] At the same time, in traditional systems, once a fire occurs, the shutters are usually closed immediately, and this operation does not take into account the personnel situation or safety conditions in the current area. This operation mode does not have the flexibility to respond to different fire scenarios. In some cases, the fire may occur in one part of the building, while other areas are not affected. If the fire shutters are always closed, it may affect the normal flow of people and evacuation process, causing unnecessary confusion. Summary of the invention

[0007] The purpose of the present invention is to provide a fire shutter alarm control system based on the Internet of Things, aiming to solve the technical problems existing in the prior art identified in the background technology.

[0008] The present invention is implemented in this way: a fire shutter alarm control system based on the Internet of Things, the system comprising: The spectrum and vibration monitoring module is used to monitor the spectrum data in the environment and the real-time vibration data of the building structure in real time, and analyze whether there are flame characteristics. If so, it identifies the warning area where the flame characteristics appear; The structural vibration analysis module is used to monitor the vibration data of the warning area in real time, and analyze the structural vibration changes by combining all the real-time vibration data collected, and analyze the severity and trend of the fire by combining the spectral data and vibration changes; The fire threshold setting and control module is used to set the fire threshold. Based on the analysis results of the fire severity and trend, when the analysis results exceed the fire threshold, an automatic closing command is sent to the fire shutter in the warning area; The personnel detection and roller shutter control module is used to monitor the early warning status of the fireproof roller shutters near the fire area and detect whether there are personnel in the roller shutters. If the presence of personnel is detected, the roller shutter closing operation is terminated and an alarm is issued; The multi-level alarm and linkage module is used to conduct multi-level alarms through sound alarms, light signals, and mobile phone notifications, and connect to the fire protection system to automatically send fire alarm information.

[0009] As a further solution of the present invention, the spectrum and vibration monitoring module includes: A spectral data acquisition unit is used to continuously and real-time acquire spectral data in the environment, and pre-process the acquired spectral data to extract effective characteristic signals; A vibration data collection and baseline recording unit, used to continuously collect vibration data of the building structure in real time through a vibration sensor, and record baseline vibration data of the building structure; The flame feature matching and judgment unit is used to match the extracted spectral features with the predefined flame feature model to determine whether there is a flame. If the matching degree exceeds a set threshold, it is confirmed that there is a flame feature; The warning area positioning and marking unit is used to determine the specific warning area where the flame characteristics appear through the position of the spectral sensor and mark it.

[0010] As a further solution of the present invention, the structural vibration analysis module includes: The sensor activation and frequency enhancement unit is used to activate the vibration sensors in the warning area and enhance the collection frequency of the vibration sensors in the area, so as to collect the vibration data of the building structure in the warning area in real time; An abnormal vibration identification unit is used to extract vibration signals from the vibration data of the warning area, combine and compare the recorded baseline vibration data of the building structure, identify the abnormal vibration of the current building structure, and analyze the correlation between the abnormal vibration and the current fire situation; The severity assessment unit is used to combine the analysis results of the vibration data with the previous spectral data to assess the severity of the fire, predict the development trend of the fire, and determine whether the fire will expand further.

[0011] As a further solution of the present invention, the fire threshold setting and control module includes: The multi-dimensional time series data sorting unit is used to arrange the combined data of different types in time series to form multi-dimensional time series data, and to fuse and analyze the vibration data, spectrum data and temperature data to generate a comprehensive feature vector; The fire analysis model building unit is used to build a fire analysis model, extract the vibration data features, spectral data features and temperature data features at the current moment in real time, and predict the development trend of the fire; The fire development trend analysis unit is used to analyze the fire development trend based on the output prediction results and determine whether the fire will expand further.

[0012] Another object of the present invention is to provide a fire shutter alarm control method based on the Internet of Things, the method comprising: Real-time monitoring of spectral data in the environment and real-time vibration data of the building structure, and analysis of whether there are flame features, if so, identification of warning areas where flame features appear; Real-time monitoring of vibration data in the warning area, and combined with all collected real-time vibration data, analysis of structural vibration changes, and combined with spectral data and vibration changes to analyze the severity and trend of the fire; Set fire thresholds. Based on the analysis results of fire severity and trends, when the analysis results exceed the fire thresholds, send automatic closing instructions to the fire shutters in the warning area. Monitor the early warning status of fire shutters near the fire area and detect whether there are people inside the shutters. If the presence of people is detected, the shutter closing operation will be terminated and an alarm will be issued; It provides multi-level alarms through sound alarms, light signals, and mobile phone notifications, and connects to the fire protection system to automatically send fire alarm information.

[0013] As a further solution of the present invention, the real-time monitoring of the spectral data in the environment and the real-time vibration data of the building structure, and analyzing whether there is a flame feature, and if so, identifying the warning area where the flame feature appears, specifically includes: Continuously collect spectral data in the environment in real time, pre-process the collected spectral data, and extract effective characteristic signals; The vibration data of the building structure is continuously collected in real time through the vibration sensor, and the baseline vibration data of the building structure is recorded; The extracted spectral features are matched with the pre-defined flame feature model to determine whether there is a flame. If the matching degree exceeds the set threshold, the flame feature is confirmed to exist. Through the location of the spectral sensor, the specific warning area where the flame characteristics appear is determined and marked.

[0014] As a further solution of the present invention, the real-time monitoring of the vibration data of the warning area, and combining all the collected real-time vibration data to analyze the structural vibration changes, and combining the spectral data and vibration changes to analyze the severity and trend of the fire, specifically includes: Activate the vibration sensors in the warning area and increase the collection frequency of the vibration sensors in the area to collect the vibration data of the building structure in the warning area in real time; Extract vibration signals from the vibration data of the warning area, combine and compare the recorded baseline vibration data of the building structure, identify the abnormal vibration of the current building structure, and analyze the correlation between the abnormal vibration and the current fire situation; The analysis results of the vibration data are combined with the previous spectral data to assess the severity of the fire, predict the development trend of the fire, and determine whether the fire will expand further.

[0015] As a further solution of the present invention, the evaluation of the severity of the fire and the prediction of the development trend of the fire to determine whether the fire will further expand specifically include: Arrange the combined data of different types in time series to form multi-dimensional time series data, and fuse and analyze the vibration data, spectrum data and temperature data to generate a comprehensive feature vector; Establish a fire analysis model to extract the vibration data features, spectral data features and temperature data features at the current moment in real time to predict the development trend of the fire; Based on the output prediction results, analyze the development trend of the fire and determine whether the fire will expand further.

[0016] As a further solution of the present invention, the setting of the fire threshold is based on the analysis results of the fire severity and trend. When the analysis results exceed the fire threshold, an automatic closing instruction is sent to the fire shutter in the warning area, which specifically includes: Set a fire severity threshold to determine whether the current fire exceeds the severity threshold. If so, the current fire is considered severe and has a tendency to expand. Based on the fire severity and trend analysis results, a control command for the automatic closing of the fire shutter is generated and sent, and at the same time, it is confirmed that the fire shutter control system has received the closing command and started to execute it.

[0017] As a further solution of the present invention, the fire shutters near the fire area are monitored for early warning status, and whether there are people in the shutters is monitored. If the presence of people is detected, the shutter closing operation is terminated and a warning is issued, which specifically includes: Obtain the real-time status data of the fire shutter, including the current position and switch status, and whether the shutter door in the current area is in the warning state; Obtain video data and sensor data in the roller shutter area in the early warning state, and monitor in real time whether there are people in the fire shutter; If the presence of a person is detected, the current closing operation instruction of the fire shutter is terminated; Get the current position of the fire shutter to determine whether people can enter or exit. If not, send a shutter callback command; A warning notification is sent to the area inside the fire curtain, and the fire curtain closing operation instruction is issued again after the person inside the fire curtain leaves.

[0018] The beneficial effects of the present invention are: Through real-time monitoring and intelligent judgment, the system can quickly identify the presence of people when a fire occurs, thereby avoiding accidental injuries. At the same time, this mechanism effectively reduces the degree of chaos in a fire situation and improves the efficiency of personnel evacuation. Compared with traditional fire shutter systems, the system's flexibility and adaptability are enhanced by realizing intelligent monitoring and response.

[0019] In addition, it also reflects multi-level security. The system not only focuses on the direct threat posed by fire, but also fully considers the situation of personnel. Through video monitoring and sensor data, it can understand the situation inside the roller shutter in real time, ensuring that every step of the operation is based on accurate information. This comprehensive monitoring and control strategy not only improves the protective effect of the fireproof roller shutter, but also provides more reliable protection for the safety of personnel in fire, and ultimately achieves a higher level of fire safety management. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A structural block diagram of a fire shutter alarm control system based on the Internet of Things provided by an embodiment of the present invention; Figure 2 A structural block diagram of a spectrum and vibration monitoring module provided in an embodiment of the present invention; Figure 3 A structural block diagram of a structural vibration analysis module provided by an embodiment of the present invention; Figure 4 A structural block diagram of a fire threshold setting and control module provided in an embodiment of the present invention; Figure 5 A flow chart of a fire shutter alarm control method based on the Internet of Things provided in an embodiment of the present invention; Figure 6 A flowchart for real-time monitoring of spectral data in an environment and real-time vibration data of a building structure, and analyzing whether there are flame characteristics, provided by an embodiment of the present invention; Figure 7 A flow chart for analyzing structural vibration changes by combining all collected real-time vibration data provided by an embodiment of the present invention; Figure 8 A flow chart of sending an automatic closing instruction to a fire shutter in a warning area provided by an embodiment of the present invention; Fig. 9 A flow chart of monitoring the early warning status of fireproof roller shutters adjacent to a fire area provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with 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.

[0022] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0023] Figure 1 The structural block diagram of the fire shutter alarm control system based on the Internet of Things provided by the embodiment of the present invention is as follows: Figure 1 As shown, a fire shutter alarm control system based on the Internet of Things, the system includes: The spectrum and vibration monitoring module 100 is used to monitor the spectrum data in the environment and the real-time vibration data of the building structure in real time, and analyze whether there are flame characteristics, and if so, identify the warning area where the flame characteristics appear; The structural vibration analysis module 200 is used to monitor the vibration data of the warning area in real time, and analyze the structural vibration changes in combination with all the real-time vibration data collected, and analyze the severity and trend of the fire in combination with the spectral data and vibration changes; The fire threshold setting and control module 300 is used to set the fire threshold, based on the analysis results of the fire severity and trend, and send an automatic closing instruction to the fire shutter in the warning area when the analysis results exceed the fire threshold; The personnel detection and rolling shutter control module 400 is used to monitor the early warning status of the fireproof rolling shutters near the fire area and detect whether there are personnel in the rolling shutters. If the presence of personnel is detected, the rolling shutter closing operation is terminated and an alarm is issued; The multi-level alarm and linkage module 500 is used to perform multi-level alarms by means of sound alarms, light signals, and mobile phone notifications, and connect to the fire protection system to automatically send fire alarm information.

[0024] like Figure 2 As shown, the spectrum and vibration monitoring module includes: The spectral data acquisition unit 110 is used to continuously and real-time acquire spectral data in the environment, and pre-process the acquired spectral data to extract effective characteristic signals; A vibration data collection and baseline recording unit 120, for continuously collecting vibration data of the building structure in real time through a vibration sensor, and recording baseline vibration data of the building structure; The flame feature matching and judgment unit 130 is used to match the extracted spectral features with a predefined flame feature model to determine whether there is a flame. If the matching degree exceeds a set threshold, it is confirmed that there is a flame feature. The warning area positioning and marking unit 140 is used to determine the specific warning area where the flame feature appears through the position of the spectrum sensor and mark it.

[0025] like Figure 3 As shown, the structural vibration analysis module includes: The sensor activation and frequency enhancement unit 210 is used to activate the vibration sensors in the warning area and enhance the collection frequency of the vibration sensors in the area, so as to collect the vibration data of the building structure in the warning area in real time; The abnormal vibration identification unit 220 is used to extract the vibration signal from the vibration data of the warning area, combine and compare the baseline vibration data of the recorded building structure, identify the abnormal vibration of the current building structure, and analyze the correlation between the abnormal vibration and the current fire situation; The severity assessment unit 230 is used to combine the analysis results of the vibration data with the previous spectral data to assess the severity of the fire, predict the development trend of the fire, and determine whether the fire will further expand.

[0026] like Figure 4 As shown, the fire threshold setting and control module includes: The multi-dimensional time series data sorting unit 310 is used to arrange the combined different types of data in time series to form multi-dimensional time series data, and to fuse and analyze the vibration data, spectrum data and temperature data to generate a comprehensive feature vector; The fire analysis model building unit 320 is used to build a fire analysis model, extract the vibration data features, spectral data features and temperature data features at the current moment in real time, and predict the development trend of the fire; The fire development trend analysis unit 330 is used to analyze the fire development trend according to the output prediction results and determine whether the fire will further expand.

[0027] Figure 5 A flowchart of a fire shutter alarm control method based on the Internet of Things provided in an embodiment of the present invention is shown in FIG. Figure 5 As shown, a fire shutter alarm control method based on the Internet of Things includes: S100, real-time monitoring of spectral data in the environment and real-time vibration data of the building structure, and analyzing whether there are flame features, and if so, identifying the warning area where the flame features appear; In this step, the system can continuously collect data in a wide spectral range through a highly sensitive spectral sensor, which provides the necessary raw information for identifying flame characteristics. After denoising, effective spectral feature signals are extracted, allowing the system to more accurately identify potential flame characteristics in complex environments. This combination of real-time data collection and processing can ensure a quick response in the early stages of a fire, thereby reducing the risk of fire losses.

[0028] Monitoring vibration data is equally important. Using highly sensitive vibration sensors, the system can record baseline vibration data of the building structure in real time and compare it with subsequent vibration information collected. By combining spectral features with vibration data, the system can conduct a more comprehensive analysis to determine the severity and development trend of the fire. This multi-dimensional data fusion can not only improve the accuracy of identification, but also significantly reduce the possibility of false alarms and missed alarms, making the warning more reliable.

[0029] In addition, the system further enhances the ability to identify flames by matching the extracted spectral features with predefined flame feature models. If the matching degree exceeds the set threshold, the system can accurately confirm the presence of flames and locate the specific warning area. This precise area marking makes subsequent response measures more efficient and ensures the timeliness of fire response.

[0030] like Figure 6 As shown, the real-time monitoring of the spectral data in the environment and the real-time vibration data of the building structure, and analyzing whether there are flame features, if so, identifying the warning area where the flame features appear, specifically includes: S110, continuously collecting spectral data in the environment in real time, and preprocessing the collected spectral data to extract effective characteristic signals; S120, continuously collecting vibration data of the building structure in real time through a vibration sensor, and recording baseline vibration data of the building structure; S130, matching the extracted spectral features with a predefined flame feature model to determine whether there is a flame, and if the matching degree exceeds a set threshold, it is confirmed that there is a flame feature; S140, determining the specific warning area where the flame characteristics appear through the position of the spectral sensor, and marking it.

[0031] Specifically, the extracted spectral features are matched with the predefined flame feature model to determine whether there is a flame. If the matching degree exceeds the set threshold, it is confirmed that there is a flame feature. The specific steps are as follows: Based on the collected spectral data, the number of sampling points of the spectral signal is obtained; For each sampling point of the spectral signal, the light intensity, spectrum power and wavelength are obtained; At each sampling point of the spectral signal, the spectral feature contribution is calculated by light intensity, spectrum power and wavelength; Assign sampling point weights to each sampling point of the spectral signal based on the flame characteristic model; Based on the spectral feature contribution and the sampling point weight of the spectral signal, a weighted feature contribution is obtained; All weighted feature contributions are accumulated to obtain the matching degree of the spectral signal; The presence of flame is determined based on the matching degree of the spectral signal, thereby confirming the presence of flame characteristics.

[0032] S200, real-time monitoring of vibration data in the warning area, and combined with all collected real-time vibration data, analysis of structural vibration changes, and combined with spectral data and vibration changes to analyze the severity and trend of the fire; In this step, the vibration sensors in the warning area are activated and their collection frequency is increased to ensure that the collected building structure vibration data has higher timeliness and accuracy. This high-frequency data collection enables the system to capture any subtle vibration changes in real time, providing sufficient raw data for subsequent analysis.

[0033] After collecting the vibration data of the warning area, the system will extract the vibration signal from it and compare it with the previously recorded baseline vibration data. The baseline data reflects the vibration characteristics of the building structure under normal conditions, and any significant deviation may indicate potential safety hazards. Through comparative analysis, the system can identify abnormal vibrations of the current building structure and further analyze the correlation between these abnormal vibrations and the current fire situation. This process not only helps identify structural changes under the influence of fire, but also provides a basis for evaluating the impact of fire on building safety.

[0034] Combining the extracted vibration data analysis results with the previously collected spectral data, the system can conduct a more comprehensive fire assessment. Spectral data provides direct evidence of flame characteristics, while vibration data provides indirect evidence for analyzing the fire. Through this comprehensive analysis, the system can assess the severity of the fire, predict the development trend of the fire, and determine whether the fire is likely to expand further. This multi-dimensional data cross-analysis makes fire response measures more accurate and timely.

[0035] Through real-time monitoring and high-frequency data collection, the system can quickly identify abnormal conditions in the early stages of a fire and respond in a timely manner. In addition, the combined analysis of vibration data and spectral data not only improves the accuracy of fire assessment, but also greatly enhances the ability to predict the development trend of fires. This in-depth analysis capability provides a scientific basis for subsequent automated responses, ensuring that effective response measures can be taken quickly when a fire occurs to protect the safety of personnel and the integrity of the building.

[0036] like Figure 7 As shown, the real-time monitoring of the vibration data of the warning area, combined with all the real-time vibration data collected, analyzes the structural vibration changes, and combines the spectral data and vibration changes to analyze the severity and trend of the fire, specifically including: S210, activating vibration sensors in the warning area, and increasing the collection frequency of the vibration sensors in the area, to collect vibration data of the building structure in the warning area in real time; S220, extracting a vibration signal from the vibration data of the warning area, combining and comparing the recorded baseline vibration data of the building structure, identifying abnormal vibration of the current building structure, and analyzing the correlation between the abnormal vibration and the current fire situation; S230, combining the analysis results of the vibration data with the previous spectral data, evaluating the severity of the fire, and predicting the development trend of the fire to determine whether the fire will further expand.

[0037] Specifically, extract the vibration signal from the vibration data of the warning area, combine and compare the baseline vibration data of the recorded building structure, identify the abnormal vibration of the current building structure, and analyze the correlation between the abnormal vibration and the current fire situation. The specific steps are as follows: The total number of sampling points of the aggregated vibration signal; For each sampling point of the vibration signal, a vibration amplitude value and a baseline vibration amplitude value corresponding to the vibration amplitude value are obtained; Calculate the difference between the vibration amplitude value and the baseline vibration amplitude value to obtain the vibration amplitude difference; Amplifying the difference in vibration amplitudes to obtain an amplified vibration amplitude difference; All the amplified vibration amplitude differences are accumulated to obtain the sum of squared deviations; The square root of the squared deviation is taken to obtain the abnormal value of the vibration signal; The abnormal values ​​of the vibration signal are used to identify the abnormal vibration of the current building structure and analyze the correlation between the abnormal vibration and the current fire situation.

[0038] Specifically, different types of data are arranged in time series to form a structured multidimensional data set. This approach ensures that various types of data can be analyzed collaboratively within the same time frame, thereby enhancing the ability to monitor changes in fire conditions. By extracting the frequency and amplitude changes of vibrations, the intensity changes of specific wavelengths of the spectrum, and the real-time trend of temperature changes, the system can generate a comprehensive feature vector that fully reflects the current environmental status and potential fire risks.

[0039] In order to improve the intelligence and automation level of fire assessment, a fire analysis model was further established. The model can accept the comprehensive feature vector extracted in real time as input and predict the development trend of the fire. Based on historical data training, the model has the ability to self-learn and adapt, and can respond quickly in the early stages of the fire and identify signs of the fire in time. The feature vector extracted in real time not only provides the model with the latest environmental information, but also enables the system to perform well in complex data processing, thereby achieving more accurate fire prediction.

[0040] In this embodiment, the evaluation of the severity of the fire and the prediction of the development trend of the fire to determine whether the fire will further expand specifically include: Arrange the combined data of different types in time series to form multi-dimensional time series data, and fuse and analyze the vibration data, spectrum data and temperature data to generate a comprehensive feature vector; Establish a fire analysis model to extract the vibration data features, spectral data features and temperature data features at the current moment in real time to predict the development trend of the fire; Based on the output prediction results, analyze the development trend of the fire and determine whether the fire will expand further.

[0041] Specifically, the combined data of different types are arranged in time series to form multi-dimensional time series data, and the vibration data, spectrum data and temperature data are fused and analyzed to generate a comprehensive feature vector. The specific steps are as follows: Perform nonlinear transformation operation on the temperature data to obtain transformed temperature data; Performing a nonlinear transformation operation on the matching degree of the spectral signal to obtain the matching degree of the transformed spectral signal; Performing an exponential transformation operation on the abnormal value of the vibration signal to obtain a transformed abnormal value of the vibration signal; The transformed temperature data, the transformed spectral signal matching degree and the transformed vibration signal abnormal value are respectively standardized to obtain standardized temperature data, standardized spectral signal matching degree and standardized vibration signal abnormal value; The interaction term is obtained by multiplying the standardized temperature data, the standardized spectral signal matching degree, and the standardized vibration signal anomaly value; The transformed temperature data, the transformed spectral signal matching degree, the transformed vibration signal anomaly value and the interaction term are added together to obtain the comprehensive feature vector of the fire situation.

[0042] S300, setting a fire threshold, based on the analysis results of the fire severity and trend, when the analysis results exceed the fire threshold, sending an automatic closing instruction to the fire shutter in the warning area; In this step, the system first needs to set a scientific and reasonable fire severity threshold, which should be formulated based on historical data, building type, usage scenario and relevant standards. Through real-time monitoring and analysis, the system can quickly determine whether the current fire exceeds this threshold. If the analysis results show that the fire has reached a serious level and has a tendency to expand, the system will initiate the preset response procedure.

[0043] After confirming that the fire exceeds the threshold, a control command for the fire shutter to close automatically will be generated, and the command will be sent to the fire shutter control system in the warning area through the Internet of Things technology. This process not only includes the generation and sending of commands, but also ensures that the control system accurately receives the closing command and starts to execute it, so as to ensure that the shutter can close the fire source in a timely and effective manner to prevent the fire from spreading. This efficient control mechanism can minimize the threat of fire to buildings and the people inside, and protect personal safety and property safety.

[0044] By setting scientific and reasonable thresholds, the system can respond to the development of the fire in real time and take quick action without human intervention, thus reducing the reaction time. This automated decision-making process not only improves the efficiency of fire response, but also reduces the possibility of human error. In addition, based on the analysis of fire severity and trends, the system can predict the development of the fire, so as to take corresponding preventive measures before the potential risk increases, further improving the level of fire safety.

[0045] According to different environments and fire types, the threshold and response strategy can be flexibly adjusted to ensure that fire risks can be effectively dealt with in various situations. At the same time, the connection between the system and other alarm mechanisms (such as sound alarms, light signals and mobile phone notifications) forms a multi-level early warning system, providing more comprehensive safety protection for personnel. By comprehensively utilizing data analysis and automatic control technology, this step in the fire shutter alarm control method not only improves the reliability and intelligence of the overall system, but also provides more solid protection for people's lives and property safety.

[0046] like Figure 8 As shown, the setting of the fire threshold is based on the analysis results of the fire severity and trend. When the analysis results exceed the fire threshold, an automatic closing instruction is sent to the fire shutter in the warning area, specifically including: S310, setting a fire severity threshold, determining whether the current fire exceeds the severity threshold, if so, the current fire is considered severe and has a tendency to expand; S320, based on the fire severity and trend analysis results, generate and send a control instruction for the automatic closing of the fireproof roller shutter, and confirm that the fireproof roller shutter control system has received the closing instruction and started to execute it.

[0047] Specifically, according to the fire severity and trend analysis results, a control instruction for the automatic closing of the fire shutter is generated and sent, and at the same time, it is confirmed that the fire shutter control system receives the closing instruction and starts to execute it. The specific steps for generating the closing instruction are as follows: Obtaining an activation coefficient of the automatic closing instruction based on the automatic closing instruction; The comprehensive feature vector of the fire condition is judged based on the fire severity threshold; If the fire comprehensive feature vector exceeds the fire severity threshold, it is determined that the current fire is in a state that requires response; The judgment result is combined with the activation coefficient of the automatic closing instruction to calculate the intensity value of the closing instruction; The fire shutter control system receives the intensity value of the closing command and starts to execute it.

[0048] S400, monitoring the early warning status of the fireproof rolling shutters near the fire area, and monitoring whether there are people in the rolling shutters. If the presence of people is detected, the closing operation of the rolling shutters is terminated and an alarm is issued; The core functions of this step include obtaining real-time status data of the fire shutter, such as the current position and switch status, and determining whether the area is in a warning state. This real-time monitoring mechanism provides basic data for subsequent decision-making, ensuring that the system can respond to changes in the fire situation in a timely manner.

[0049] The system also needs to obtain video data and sensor data in the roller shutter area in the early warning state to monitor in real time whether there are people in the roller shutter. When the system detects that there are people in the area, it will immediately terminate the closing operation instruction of the fire shutter. This design fully considers the safety of people in fire situations and ensures that people will not be troubled or injured by the closing of the roller shutter in an emergency.

[0050] In addition, it also includes the judgment of the position of the fire shutter to determine whether to allow people to enter or exit. If the current shutter position is not suitable for people to evacuate, the system will send a shutter callback command to ensure that people can escape smoothly. At the same time, in order to enhance safety, the system will send a warning notification to the area within the fire shutter to remind people to evacuate in time. When the people in the shutter area successfully leave, the system will issue a command to close the fire shutter again to effectively prevent the spread of fire.

[0051] Through real-time monitoring and intelligent judgment, the system can quickly identify the presence of people when a fire occurs, thereby avoiding accidental injuries. At the same time, this mechanism effectively reduces the degree of chaos in a fire situation and improves the efficiency of personnel evacuation. Compared with traditional fire shutter systems, the system's flexibility and adaptability are enhanced by realizing intelligent monitoring and response.

[0052] In addition, it also reflects multi-level security. The system not only focuses on the direct threat posed by fire, but also fully considers the situation of personnel. Through video monitoring and sensor data, it can understand the situation inside the roller shutter in real time, ensuring that every step of the operation is based on accurate information. This comprehensive monitoring and control strategy not only improves the protective effect of the fireproof roller shutter, but also provides more reliable protection for the safety of personnel in fire, and ultimately achieves a higher level of fire safety management.

[0053] like Fig. 9 As shown, the fire shutters near the fire area are monitored for early warning status, and whether there are people in the shutters is monitored. If the presence of people is detected, the shutter closing operation is terminated and an alarm is issued, which specifically includes: S410, obtaining real-time status data of the fire shutter, including the current position and switch status, and obtaining whether the shutter door in the current area is in a warning state; S420, obtaining video data and sensor data in the roller shutter area in the early warning state, and monitoring in real time whether there is a person in the fire roller shutter; S430, if the presence of a person is detected, the current closing operation instruction of the fireproof roller shutter is terminated; S440, obtaining the current position of the fire shutter, determining whether people can enter or exit, and if not, sending a shutter callback command; S450, sending a warning notification to the area inside the fire curtain, and issuing a fire curtain closing operation instruction again after the person inside the fire curtain leaves.

[0054] S500 provides multi-level alarms through sound alarms, light signals, and mobile phone notifications, and connects to the fire protection system to automatically send fire alarm information.

[0055] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0056] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0057] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0058] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0059] 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 and improvements 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 shutter alarm control method based on the Internet of Things, characterized in that: The method comprises the following steps: Real-time monitoring of spectral data in the environment and real-time vibration data of the building structure, and analysis of whether there are flame features, if so, identification of warning areas where flame features appear; Real-time monitoring of vibration data in the warning area, and combined with all collected real-time vibration data, analysis of structural vibration changes, and combined with spectral data and vibration changes to analyze the severity and trend of the fire; Set fire thresholds. Based on the analysis results of fire severity and trends, when the analysis results exceed the fire thresholds, send automatic closing instructions to the fire shutters in the warning area. Monitor the early warning status of fire shutters near the fire area and detect whether there are people inside the shutters. If the presence of people is detected, the shutter closing operation will be terminated and an alarm will be issued; Multi-level alarms are provided through sound alarms, light signals, and mobile phone notifications, and the fire protection system is connected to automatically send fire alarm information; The real-time monitoring of the spectral data in the environment and the real-time vibration data of the building structure, and analyzing whether there are flame features, and if so, identifying the warning area where the flame features appear, specifically includes: Continuously collect spectral data in the environment in real time, pre-process the collected spectral data, and extract effective characteristic signals; The vibration data of the building structure is continuously collected in real time through the vibration sensor, and the baseline vibration data of the building structure is recorded; The extracted spectral features are matched with the pre-defined flame feature model to determine whether there is a flame. If the matching degree exceeds the set threshold, the flame feature is confirmed to exist. Through the location of the spectral sensor, the specific warning area where the flame characteristics appear is determined and marked.

2. The fire shutter alarm control method based on the Internet of Things according to claim 1 is characterized in that: The extracted spectral features are matched with the pre-defined flame feature model to determine whether there is a flame. If the matching degree exceeds the set threshold, the flame feature is confirmed to exist. The specific steps are as follows: Based on the collected spectral data, the number of sampling points of the spectral signal is obtained; For each sampling point of the spectral signal, the light intensity, spectrum power and wavelength are obtained; At each sampling point of the spectral signal, the spectral feature contribution is calculated by light intensity, spectrum power and wavelength; Assign sampling point weights to each sampling point of the spectral signal based on the flame characteristic model; Based on the spectral feature contribution and the sampling point weight of the spectral signal, a weighted feature contribution is obtained; All weighted feature contributions are accumulated to obtain the matching degree of the spectral signal; The presence of flame is determined based on the matching degree of the spectral signal, thereby confirming the presence of flame characteristics.

3. The fire shutter alarm control method based on the Internet of Things according to claim 2 is characterized in that: The real-time monitoring of the vibration data of the warning area, combined with all the collected real-time vibration data, analyzes the structural vibration changes, and combines the spectral data and vibration changes to analyze the severity and trend of the fire, specifically including: Activate the vibration sensors in the warning area and increase the collection frequency of the vibration sensors in the area to collect the vibration data of the building structure in the warning area in real time; Extract vibration signals from the vibration data of the warning area, combine and compare the recorded baseline vibration data of the building structure, identify the abnormal vibration of the current building structure, and analyze the correlation between the abnormal vibration and the current fire situation; The analysis results of the vibration data are combined with the previous spectral data to assess the severity of the fire, predict the development trend of the fire, and determine whether the fire will expand further.

4. The fire shutter alarm control method based on the Internet of Things according to claim 3 is characterized in that: Extract vibration signals from the vibration data of the warning area, combine and compare the baseline vibration data of the recorded building structure, identify the abnormal vibration of the current building structure, and analyze the correlation between the abnormal vibration and the current fire situation. The specific steps are as follows: The total number of sampling points of the aggregated vibration signal; For each sampling point of the vibration signal, a vibration amplitude value and a baseline vibration amplitude value corresponding to the vibration amplitude value are obtained; Calculate the difference between the vibration amplitude value and the baseline vibration amplitude value to obtain the vibration amplitude difference; Amplifying the difference in vibration amplitudes to obtain an amplified vibration amplitude difference; All the amplified vibration amplitude differences are accumulated to obtain the sum of squared deviations; The square root of the squared deviation is taken to obtain the abnormal value of the vibration signal; The abnormal values ​​of the vibration signal are used to identify the abnormal vibration of the current building structure and analyze the correlation between the abnormal vibration and the current fire situation.

5. The method for controlling fire shutter alarm based on Internet of Things according to claim 4 is characterized in that: The assessment of the severity of the fire and the prediction of its development trend to determine whether the fire will further expand include: Arrange the combined data of different types in time series to form multi-dimensional time series data, and fuse and analyze the vibration data, spectrum data and temperature data to generate a comprehensive feature vector; Establish a fire analysis model to extract the vibration data features, spectral data features and temperature data features at the current moment in real time to predict the development trend of the fire; Based on the output prediction results, analyze the development trend of the fire and determine whether the fire will expand further.

6. The method for controlling fire shutter alarm based on Internet of Things according to claim 5 is characterized in that: Arrange the combined data of different types in time series to form multi-dimensional time series data, and fuse and analyze the vibration data, spectrum data and temperature data to generate a comprehensive feature vector. The specific steps are as follows: Perform nonlinear transformation operation on the temperature data to obtain transformed temperature data; Performing a nonlinear transformation operation on the matching degree of the spectral signal to obtain the matching degree of the transformed spectral signal; Performing an exponential transformation operation on the abnormal value of the vibration signal to obtain a transformed abnormal value of the vibration signal; The transformed temperature data, the transformed spectral signal matching degree and the transformed vibration signal abnormal value are respectively standardized to obtain standardized temperature data, standardized spectral signal matching degree and standardized vibration signal abnormal value; The interaction term is obtained by multiplying the standardized temperature data, the standardized spectral signal matching degree, and the standardized vibration signal anomaly value; The transformed temperature data, the transformed spectral signal matching degree, the transformed vibration signal anomaly value and the interaction term are added together to obtain the comprehensive feature vector of the fire situation.

7. The method for controlling fire shutter alarm based on Internet of Things according to claim 6 is characterized in that: The setting of the fire threshold is based on the analysis results of the fire severity and trend. When the analysis results exceed the fire threshold, an automatic closing instruction is sent to the fire shutter in the warning area, specifically including: Set a fire severity threshold to determine whether the current fire exceeds the severity threshold. If so, the current fire is considered severe and has a tendency to expand. Based on the fire severity and trend analysis results, a control command for the automatic closing of the fire shutter is generated and sent, and at the same time, it is confirmed that the fire shutter control system has received the closing command and started to execute it.

8. The method for controlling fire shutter alarm based on Internet of Things according to claim 7 is characterized in that: According to the fire severity and trend analysis results, a control command for the automatic closing of the fire shutter is generated and sent, and at the same time, it is confirmed that the fire shutter control system receives the closing command and starts to execute it. The specific steps for generating the closing command are as follows: Obtaining an activation coefficient of the automatic closing instruction based on the automatic closing instruction; The comprehensive feature vector of the fire condition is judged based on the fire severity threshold; If the fire comprehensive feature vector exceeds the fire severity threshold, it is determined that the current fire is in a state that requires response; The judgment result is combined with the activation coefficient of the automatic closing instruction to calculate the intensity value of the closing instruction; The fire shutter control system receives the intensity value of the closing command and starts to execute it.

9. The method for controlling fire shutter alarm based on Internet of Things according to claim 8, characterized in that: The fire shutters near the fire area are monitored for early warning status, and whether there are people in the shutters is monitored. If the presence of people is detected, the shutter closing operation is terminated and an alarm is issued, which specifically includes: Obtain the real-time status data of the fire shutter, including the current position and switch status, and whether the shutter door in the current area is in the warning state; Obtain video data and sensor data in the roller shutter area in the early warning state, and monitor in real time whether there are people inside the fire shutter; If the presence of a person is detected, the current closing operation instruction of the fire shutter is terminated; Get the current position of the fire shutter to determine whether people can enter or exit. If not, send a shutter callback command; A warning notification is sent to the area inside the fire curtain, and the fire curtain closing operation instruction is issued again after the person inside the fire curtain leaves.

10. A fire shutter alarm control system based on the Internet of Things, characterized in that: The system applies the fire shutter alarm control method based on the Internet of Things as described in any one of claims 1 to 9 above, and the system includes: The spectrum and vibration monitoring module is used to monitor the spectrum data in the environment and the real-time vibration data of the building structure in real time, and analyze whether there are flame characteristics. If so, it identifies the warning area where the flame characteristics appear; The structural vibration analysis module is used to monitor the vibration data of the warning area in real time, and analyze the structural vibration changes by combining all the real-time vibration data collected, and analyze the severity and trend of the fire by combining the spectral data and vibration changes; The fire threshold setting and control module is used to set the fire threshold. Based on the analysis results of the fire severity and trend, when the analysis results exceed the fire threshold, an automatic closing command is sent to the fire shutter in the warning area; The personnel detection and roller shutter control module is used to monitor the early warning status of the fireproof roller shutters near the fire area and detect whether there are personnel in the roller shutters. If the presence of personnel is detected, the roller shutter closing operation is terminated and an alarm is issued; The multi-level alarm and linkage module is used to conduct multi-level alarms through sound alarms, light signals, and mobile phone notifications, and connect to the fire protection system to automatically send fire alarm information.

Images