Intelligent fire-fighting early warning and emergency response system based on Internet of Things

Abstract

The invention discloses an intelligent fire-fighting early warning and emergency response system based on the Internet of Things, and relates to the technical field of fire fighting of the Internet of Things, and the system comprises an acquisition self-inspection module, an edge dynamic calibration module, an on-chain storage module, a contract verification module and a collaborative traceability module. According to the invention, data acquisition accuracy is improved, data integrity and authenticity are ensured, and a solid foundation is provided for services and decisions; safe and orderly sharing of data is realized, department business requirements are met, and a safety defense line is built; efficient cooperative emergency disposal of multiple departments is promoted, quick traceability check can be realized, and the root of the problem can be positioned; the fire-fighting early warning timeliness and the emergency response cooperation efficiency are greatly improved, a whole-process closed-loop fire-fighting safety management system is constructed, and improvement of the modernized fire-fighting safety management level is supported.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) fire protection technology, specifically to an IoT-based intelligent fire early warning and emergency response system. Background Technology

[0002] With accelerated urbanization and increasingly complex building functions, the prevention and control of fire and other fire safety hazards are becoming increasingly difficult, and traditional fire monitoring models are no longer sufficient to meet the needs of modern safety management. The rapid development of technologies such as the Internet of Things (IoT) and blockchain has provided new solutions for the field of intelligent fire protection. Deploying sensors to collect fire monitoring data and achieving intelligent fire early warning and emergency response has become an industry trend. Currently, the accuracy, transmission security, and multi-departmental collaboration efficiency of fire monitoring data directly affect the effectiveness of fire prevention and control. Therefore, how to build an efficient, reliable, and collaborative intelligent fire early warning and emergency response system has become a key issue in improving fire safety assurance capabilities.

[0003] Existing technologies have many shortcomings in fire early warning and emergency response. Sensor-collected data is susceptible to environmental interference and equipment condition, lacks dynamic calibration mechanisms, resulting in insufficient data accuracy and difficulty in accurately reflecting actual fire conditions. Data storage often employs a centralized architecture, posing a risk of data modification, and the transmission link lacks end-to-end reliable verification, compromising data reliability. Inadequate data sharing mechanisms among multiple departments and unclear access permissions lead to delayed information transmission and low collaboration efficiency during emergency responses. The lack of end-to-end data traceability in fault scenarios hinders rapid identification of the root cause, impacting subsequent rectification and accountability. These problems severely restrict the accuracy of early warning and the timeliness of emergency response in intelligent fire protection systems.

[0004] In summary, existing fire early warning and emergency response technologies have significant shortcomings in data calibration, reliable storage, collaborative response, and traceability verification, failing to meet the high-precision, high-reliability, and high-efficiency requirements of modern fire safety management. Therefore, there is an urgent need to design an IoT-based intelligent fire early warning and emergency response system. This system should improve the accuracy and reliability of fire monitoring data, enhance the timeliness of fire warnings and the coordination of emergency responses by optimizing data acquisition and calibration mechanisms, constructing an on-chain reliable storage architecture, improving multi-departmental collaboration mechanisms, and enhancing end-to-end traceability capabilities, thereby providing more reliable technical support for fire safety. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing technologies and provide an IoT-based intelligent fire early warning and emergency response system. This system can capture data and health status information through sensors integrating collection, self-inspection, identification, and communication functions, and use an edge dynamic calibration mechanism to correct data and improve accuracy. The on-chain storage module uses a consensus mechanism and hash encryption to ensure data integrity and authenticity. The contract verification module verifies the entire data process, assigns status identifiers, and achieves secure sharing. The collaborative traceability module monitors in real time, triggers early warnings, promotes efficient collaboration among multiple departments, and improves the efficiency of fire early warning and emergency response.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an intelligent fire early warning and emergency response system based on the Internet of Things, the system comprising: a data acquisition and self-testing module, an edge dynamic calibration module, an on-chain storage module, a contract verification module, and a collaborative traceability module; The data acquisition and self-test module is used to collect fire monitoring data through tagged sensors deployed at the fire monitoring site, and simultaneously perform sensor health self-tests and generate health status labels. The edge dynamic calibration module receives the collected fire monitoring data and sensor health status indicators, performs calibration through a multi-dimensional fusion dynamic calibration algorithm, generates calibration parameters, and feeds the calibration parameters back to the acquisition self-test module. At the same time, the calibrated fire monitoring data, health status indicators, and calibration parameters are transmitted to the on-chain storage module. The on-chain storage module receives calibrated fire monitoring data, health status indicators and calibration parameters, records data transmission link logs, performs multi-node data synchronization storage through a consensus mechanism, and sends a data ready signal to the contract verification module after storage is completed. The contract verification module: after receiving the data ready signal, extracts the calibrated fire monitoring data, health status identifier, calibration parameters and transmission link logs, performs data credibility verification using a full-link trusted verification algorithm, adds status identifiers to the fire monitoring data and binds calibration parameters and health status identifiers, configures access permissions for multiple departments and opens data access. The collaborative tracing module: through configured access permissions for multiple departments, it displays fire monitoring data and triggers an early warning when the data exceeds a preset threshold, enabling collaborative responses from multiple departments. In fault scenarios, it can retrieve data from the entire chain to perform tracing and verification.

[0007] Furthermore, the self-test module includes four types of main monitoring sensors—temperature, smoke concentration, CO concentration, and humidity—as well as corresponding neighborhood sensors. Each type of identifiable sensor integrates a data acquisition unit, a unique identifier chip, a self-test unit, and a communication unit. The data acquisition unit collects temperature, smoke concentration, CO concentration, and humidity data for the corresponding monitoring area. Neighborhood sensors are of the same type as the main monitoring sensors and are deployed within the same monitoring sub-area, collecting environmental monitoring data consistent with that of the main monitoring sensors. The unique identifier chip stores the sensor's device number, installation location, and calibration cycle information. The self-test unit monitors the sensor's power supply status, data acquisition accuracy, and communication link stability in real time and generates a health status identifier. The communication unit transmits the collected fire monitoring data, health status identifier, and unique identifier information to the edge dynamic calibration module.

[0008] Furthermore, the edge dynamic calibration module performs calibration using a multi-dimensional fusion dynamic calibration algorithm. The specific steps for generating calibration parameters are as follows: Fire monitoring data and sensor health status identifiers transmitted from the acquisition and self-test module are received via the IoT communication interface; the received data is parsed and its integrity is verified; the verified fire monitoring data and corresponding health status identifiers are selected; the multi-dimensional fusion dynamic calibration algorithm is invoked, and the verified fire monitoring data, sensor health status identifiers, and preset neighboring sensor weights are substituted into the algorithm for calculation. The preset neighboring sensor weights are confidence coefficients assigned to each neighboring sensor within the same monitoring sub-area, determined based on historical acquisition accuracy and real-time health status, and whose weights sum to 1, to obtain the calibrated fire monitoring data; the fusion weight coefficient and health status correction coefficient from the calculation process are extracted as calibration parameters, and the calibration parameters are fed back to the acquisition and self-test module via the IoT communication interface.

[0009] Furthermore, the calculation formula for the multi-dimensional fusion dynamic calibration algorithm in the edge dynamic calibration module is as follows: ,in, This represents the final calibration data of the j-th sensor within the i-th monitoring area at time t. To collect the raw data of the j-th sensor in the i-th monitoring area transmitted by the self-test module at time t; The adjustment coefficient for cross-sensor data fusion; This represents the total number of valid neighboring sensors that are located within the same monitoring sub-region as the j-th sensor. Let be the confidence weight of the k-th neighboring sensor; This represents the raw data collected at time t from the k-th neighboring sensor within the i-th monitoring area. The average value of the data collected by the k-th neighboring sensor within the time period T; The correction coefficients are determined based on the health status identifiers generated by the self-test module. By combining weighted fusion calculation of neighboring sensor data with differentiated correction of sensor health status, the deviation relationship between the historical average of neighboring sensors and real-time acquired data within the same monitoring area is utilized to compensate for environmental interference in the raw acquired data of a single sensor. Based on the sensor health status identifier, the corresponding correction coefficients are matched to perform targeted corrections on sensor data with health statuses that are pending calibration or abnormal, effectively reducing the acquisition errors caused by individual sensor malfunctions and environmental disturbances, and outputting more accurate and reliable fire monitoring data.

[0010] Furthermore, the consensus mechanism in the on-chain storage module includes proposal node election, data consistency verification, node voting confirmation, and storage result uploading to the chain. The specific process of multi-node data synchronization storage through the consensus mechanism is as follows: the on-chain storage module first hashes and encrypts the data to be stored and the link log to generate a unique data fingerprint, and then broadcasts the data fingerprint to all storage nodes in the blockchain network. Each storage node performs consistency verification on the data fingerprint and the corresponding original data. Nodes that pass the verification store the data locally and send back confirmation information. When the number of nodes sending back confirmation information reaches more than 2 / 3 of the total number of nodes in the blockchain network, the multi-node synchronization storage of the data is completed. After storage is completed, a data ready signal is sent to the contract verification module.

[0011] Furthermore, the contract verification module employs a full-link trusted verification algorithm to perform data credibility verification. The specific steps for adding status identifiers and binding calibration parameters and health status identifiers to the fire monitoring data are as follows: Extracting the calibrated fire monitoring data, health status identifiers, calibration parameters, and transmission link logs transmitted from the on-chain storage module; sequentially verifying the integrity of node signatures in the transmission link logs, the validity of sensor health status identifiers, and the matching degree between calibration parameters and the original collected data using the full-link trusted verification algorithm; and adding trusted, pending verification, and untrusted status identifiers to the fire monitoring data based on the verification results. When the value is ≥0.9, the data is considered reliable; when 0.6 ≤ When the value is less than 0.9, the data is considered to be pending review. When the value is less than 0.6, the data is deemed unreliable. The fire monitoring data with added status identifiers are then bound to the corresponding calibration parameters and health status identifiers to generate a unique data association identifier.

[0012] Furthermore, the formula for the end-to-end trusted verification algorithm in the contract verification module is as follows: ,in, This is the comprehensive score for end-to-end trusted verification. This represents the total number of dimensions for end-to-end verification. Let be the weight coefficient of the i-th verification dimension; The state score for the i-th verification dimension; Let be the consistency verification coefficient for the i-th verification dimension. By quantifying three influencing factors—transmission link integrity, sensor health effectiveness, and calibration parameter matching degree—and highlighting the role of link verification in data credibility based on differentiated weight allocation, a consistency verification coefficient is introduced to correct the single-dimensional score deviation and accurately output the comprehensive credibility score of the entire data link.

[0013] Furthermore, the multi-department access permissions in the contract verification module include those of fire supervision departments, emergency management departments, operation and maintenance management departments, and third-party audit departments. The fire supervision department has the right to read and write all data, the emergency management department has the right to prioritize reading early warning data, the operation and maintenance management department has the right to read sensor status data and modify calibration parameters, and the third-party audit department has the right to read data only for a specified period. Data access services matching the permissions are opened to the corresponding departments through a preset encrypted interface. The preset encrypted interface is a standardized interface that achieves secure data transmission matching permissions through an encrypted communication protocol when opening data access to the corresponding departments.

[0014] Furthermore, the collaborative tracing module displays fire monitoring data and triggers warnings when the data exceeds preset thresholds, enabling multi-department collaborative responses. Specifically, it acquires fire monitoring data through configured multi-department access permissions and displays the data categorized by monitoring area and monitoring type. It compares the acquired fire monitoring data in real-time with fire warning thresholds of 65°C, smoke concentration threshold of 0.15%, and CO concentration threshold of 35ppm. When any monitoring data exceeds the corresponding threshold, a warning is generated. The warning is simultaneously pushed to fire supervision departments, emergency management departments, and operation and maintenance management departments. A multi-department collaborative response process is initiated, pushing the location data of the fire risk area to the fire supervision department, the personnel evacuation route planning data to the emergency management department, and the device number and location information of the faulty sensor to the operation and maintenance management department.

[0015] Compared with existing technologies, this IoT-based intelligent fire early warning and emergency response system has the following advantages: I. This invention deploys sensors integrating acquisition, self-testing, identification, and communication functions in the acquisition stage to simultaneously capture monitoring data and sensor health status information. Combined with the multi-dimensional fusion calibration mechanism of the edge dynamic calibration module, the raw data is dynamically corrected, effectively avoiding the adverse effects of environmental interference and equipment operating status fluctuations, and significantly improving the accuracy of data acquisition. At the same time, the on-chain storage module uses a consensus mechanism to achieve multi-node data synchronous storage, and uses hash encryption technology to generate a unique data fingerprint, fully recording the entire data transmission log. From the storage architecture level, it blocks the possibility of data modification, ensuring the integrity and authenticity of data from acquisition to storage, and providing a solid data foundation for subsequent business applications and decision-making.

[0016] Second, this invention utilizes a full-link trusted verification mechanism in the contract verification module to comprehensively verify all relevant information throughout the data process and assign clear status identifiers. Combined with differentiated multi-department access permission settings, it achieves secure and orderly data sharing, meeting the specific business needs of different departments while strengthening data security defenses. The collaborative tracing module monitors data dynamics in real time, promptly triggering early warnings and pushing customized data support to corresponding departments, promoting efficient multi-departmental collaboration in emergency response. Simultaneously, in fault scenarios, it can quickly retrieve full-link data for tracing and verification, accurately locating the root cause of the problem and providing a clear basis for subsequent rectification, optimization, and responsibility determination. This series of designs significantly improves the timeliness of fire warnings and the collaborative efficiency of emergency response, constructing a closed-loop fire safety management system that powerfully supports the improvement of modern fire safety management.

[0017] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a block diagram showing the modular components of an IoT-based intelligent fire early warning and emergency response system. Figure 2 A flowchart of an IoT-based intelligent fire early warning and emergency response system; Figure 3This is a schematic diagram of data transmission for a contract verification module in an IoT-based intelligent fire early warning and emergency response system. Detailed Implementation

[0020] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structure, features and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0021] Example 1 Identified sensors are deployed at key locations in various functional areas of the commercial complex. Temperature, smoke concentration, CO concentration, and humidity sensors are installed as primary monitoring sensors above the stoves in the catering area, at the ventilation openings of the underground parking lot, and near the power distribution boxes in the equipment room. Each primary monitoring sensor has a corresponding neighboring sensor of the same type, and the distance between them within the same monitoring sub-area does not exceed 5 meters. The unique identification chip of each sensor stores the device number (Catering Area B1-008), the specific installation location, and the monthly calibration cycle information to ensure the traceability of sensor identity and the orderly conduct of calibration work. The data acquisition unit collects raw data of temperature, smoke concentration, CO concentration, and humidity in the area in real time, achieving full-area coverage monitoring of key fire protection indicators. The self-testing unit simultaneously checks the power supply status, data acquisition accuracy, and communication link stability of the sensors. Sensors that meet all indicators generate a health status label, sensors with slight fluctuations in power supply voltage that do not affect data acquisition generate a minor abnormal status label, and sensors that cannot transmit data generate a fault status label, promptly identifying potential sensor malfunctions and avoiding invalid data interference. The communication unit transmits all raw fire monitoring data, corresponding health status indicators, and unique sensor identification information to the edge dynamic calibration module in real time, ensuring the timeliness and integrity of data transmission.

[0022] The edge dynamic calibration module receives all data transmitted by the acquisition and self-test module through the IoT communication interface. It first parses the data, verifying the integrity of each sensor's data fields to ensure no missing or mismatched data. After integrity verification, it filters out valid data and corresponding health status indicators. Then, it calls the multi-dimensional fusion dynamic calibration algorithm, with the following formula: ,in, This represents the final calibration data of the j-th sensor within the i-th monitoring area at time t. To collect the raw data of the j-th sensor in the i-th monitoring area transmitted by the self-test module at time t; The adjustment coefficient for cross-sensor data fusion; This represents the total number of valid neighboring sensors that are located within the same monitoring sub-region as the j-th sensor. Let be the confidence weight of the k-th neighboring sensor; This represents the raw data collected at time t from the k-th neighboring sensor within the i-th monitoring area. The average value of the data collected by the k-th neighboring sensor within the time period T; The correction coefficients are determined based on the health status identifiers generated by the data acquisition and self-testing module. Valid raw data, corresponding health status identifiers, and preset neighboring sensor confidence weights are substituted into the calculations to improve data accuracy and obtain calibrated fire monitoring data. Then, the fusion weight coefficients and health status correction coefficients generated during the calculation process are extracted as calibration parameters and fed back to the data acquisition and self-testing module via the IoT communication interface, providing a basis for optimizing sensor acquisition parameters. Simultaneously, the calibrated fire monitoring data, the health status identifiers of each sensor, and the calibration parameters are transmitted to the on-chain storage module to ensure accurate data sources for subsequent data processing.

[0023] After receiving data, the on-chain storage module first records a detailed log of the entire transmission chain from the data acquisition and self-testing module, through processing by the edge dynamic calibration module, to its own transmission. This log includes the reception time, number of bytes transmitted, and transmission status for each node, providing evidence for data traceability. Subsequently, multi-node data synchronization storage is executed according to the consensus mechanism. First, the calibrated fire monitoring data, health status identifiers, calibration parameters, and transmission chain logs are hashed and encrypted to generate a unique data fingerprint, ensuring the data is immutable. Then, the data fingerprint is broadcast to all storage nodes in the blockchain network. Each storage node receives the fingerprint and performs a consistency check against the corresponding original data to verify whether the data has been modified, ensuring data authenticity. Nodes that pass the verification store the data in their local database and send a confirmation message to the on-chain storage module. When the number of nodes sending confirmation messages reaches more than 2 / 3 of the total number of nodes in the blockchain network, multi-node synchronization storage is completed, ensuring secure and reliable data storage. The on-chain storage module then sends a data ready signal to the contract verification module, initiating the subsequent data verification process.

[0024] After receiving the data ready signal, the contract verification module retrieves the relevant data from the on-chain storage module and initiates the end-to-end trusted verification algorithm to verify the data's trustworthiness. The formula is as follows: ,in, This is the comprehensive score for end-to-end trusted verification. This represents the total number of dimensions for end-to-end verification. Let be the weight coefficient of the i-th verification dimension; The state score for the i-th verification dimension; This is the consistency verification coefficient for the i-th verification dimension, ensuring data availability and reliability. During verification, the integrity of the signatures of each node in the transmission link log is verified sequentially to ensure the link transmission has not been modified. The validity of the sensor health status identifier is verified to eliminate interference from faulty sensor data. The matching degree between calibration parameters and the original collected data is verified to ensure the calibration process is compliant. A comprehensive score is calculated based on the verification results. Data with a comprehensive score ≥ 0.9 is marked with a trusted status identifier; data with a comprehensive score between 0.6 and 0.9 is marked with a pending verification status identifier; and data with a comprehensive score < 0.6 is marked with an untrusted status identifier, thus clarifying the data trustworthiness level. The fire monitoring data with added status identifiers is then bound to the corresponding calibration parameters and health status identifiers to generate a unique data association identifier, facilitating data traceability and association. Simultaneously, access permissions for multiple departments are configured: the fire supervision department has full data read / write permissions, the emergency management department has priority access to early warning data, the operation and maintenance management department has permissions to read sensor status data and modify calibration parameters, and the third-party auditing department has read-only permissions for the past month's data within a specified period. Data access services matching each department's permissions are provided through a pre-set encrypted interface, ensuring both data sharing and data security. Figure 3 As shown.

[0025] The collaborative tracing module obtains contract-verified fire monitoring data through permission configuration and displays it on the system's visualization platform according to the classification of floor-functional area-monitoring indicator, allowing various departments to monitor in real time and quickly locate the area and type of data. When the calibrated temperature data of the main monitoring sensor in the catering area reaches 67℃, exceeding the preset threshold of 65℃, and the corresponding smoke concentration data is 0.17%, exceeding the preset threshold of 0.15%, the system immediately triggers a level-one fire alarm, capturing fire risk signals at the first moment. The collaborative tracing module simultaneously pushes the alarm information to the fire supervision department, emergency management department, and operation and maintenance management department, ensuring that relevant departments are promptly informed of the risk situation. It also initiates a multi-department collaborative response process, pushing precise location data of the fire risk area to the fire supervision department to facilitate rapid arrival at the scene, pushing evacuation route planning data for the area and surrounding floors to the emergency management department to ensure safe evacuation, and pushing the device number, installation location, and health status indicator of the main sensor and neighboring sensors in the area to the operation and maintenance management department to facilitate timely troubleshooting of equipment problems. Figure 1 As shown. When it is necessary to verify the accuracy of this early warning data, the entire chain of data can be retrieved through the collaborative tracing module to perform tracing verification, confirm the authenticity of the data and the compliance of the process, and provide a basis for incident handling and responsibility determination.

[0026] Example 2 Identified sensors are deployed in the production workshops, raw material storage tank areas, and equipment rooms of each factory building. Each type of area is equipped with a temperature sensor, smoke concentration sensor, CO concentration sensor, and humidity sensor as the main monitoring sensor. Each main monitoring sensor is paired with two neighboring sensors of the same type, all deployed within the same monitoring sub-area. Neighboring sensors are set up within a 3-meter radius of the main CO concentration sensor in the raw material storage tank area. Each identified sensor has a unique identification chip storing its device number (e.g., D5-012 for storage tank area #5), its specific installation location, and a calibration cycle of once every two weeks. This ensures the high-frequency calibration requirements of sensors in a chemical environment and guarantees unique and traceable identification. The data acquisition unit collects raw data on temperature, smoke concentration, CO concentration, and humidity in real time, accurately capturing fire risk indicators in the chemical production and storage process. The self-testing unit simultaneously checks the power supply stability, data acquisition accuracy, and communication link connection status of the sensors. Sensors meeting all indicators generate a health status indicator; sensors with slight accuracy deviations generate a calibration pending status indicator; and sensors completely unable to communicate generate a fault status indicator, promptly detecting sensor anomalies and preventing data distortion in a chemical environment. The communication unit transmits all raw fire monitoring data, health status indicators, and unique sensor identification information to the edge dynamic calibration module in real time, ensuring that the data is promptly transmitted to the next processing stage.

[0027] After receiving the transmitted data via the IoT communication interface, the edge dynamic calibration module first parses the data, verifies the integrity of each sensor's data to ensure that key indicators are not missing, and then filters out valid data and corresponding health status indicators after integrity verification. Next, it calls a multi-dimensional fusion dynamic calibration algorithm, substituting the valid raw data, corresponding health status indicators, and preset neighboring sensor confidence weights into the calculations to correct the impact of the complex chemical environment on data acquisition, obtaining calibrated fire monitoring data. Then, it extracts the fusion weight coefficients and health status correction coefficients generated during the calculation process as calibration parameters, feeding them back to the acquisition self-test module via the IoT communication interface to support sensor acquisition parameter adjustments. Simultaneously, it transmits the calibrated fire monitoring data, the health status indicators of each sensor, and the calibration parameters to the on-chain storage module, providing accurate basic data for subsequent data storage and verification.

[0028] After receiving data, the on-chain storage module first records a detailed log of the entire transmission chain from the data acquisition and self-testing module, through processing by the edge dynamic calibration module, to its own transmission. This log includes the device number of each node, data reception time, and transmission verification results, providing a basis for full-process data traceability. Subsequently, multi-node data synchronization storage is executed according to the consensus mechanism. First, the calibrated fire monitoring data, health status identifiers, calibration parameters, and transmission chain logs are hashed and encrypted to generate a unique data fingerprint, preventing data modification during storage. Then, the data fingerprint is broadcast to all storage nodes in the blockchain network. Each storage node receives the fingerprint and performs consistency verification against the corresponding original data to check if the data has been modified during transmission, ensuring data authenticity. Nodes that pass verification store the data in their local database and send a confirmation message to the on-chain storage module. When the number of nodes sending confirmation messages reaches more than 2 / 3 of the total number of nodes in the blockchain network, multi-node synchronization storage is completed, ensuring data storage security and resistance to loss. The on-chain storage module then sends a data ready signal to the contract verification module, initiating the data verification process.

[0029] After receiving the data ready signal, the contract verification module retrieves relevant data from the on-chain storage module and initiates a full-link trusted verification algorithm to verify data credibility, ensuring data availability and reliability in chemical engineering scenarios. During verification, the integrity of the signatures of each node in the transmission link log is checked sequentially to ensure the link has not been illegally accessed. The validity of the sensor health status identifier is verified, data from calibrated sensors is specially labeled, the matching degree between calibration parameters and the original collected data is verified, and the calculation logic of the calibration parameters is checked to ensure data processing compliance. A comprehensive score is calculated based on the verification results. Data with a comprehensive score ≥ 0.9 is marked with a trusted status identifier, data with a comprehensive score between 0.6 and 0.9 is marked with a pending review status identifier, and data with a comprehensive score < 0.6 is marked with an untrusted status identifier, thus clarifying the data's credibility. The fire monitoring data with added status identifiers will then be bound to the corresponding calibration parameters and health status identifiers to generate a unique data association identifier, facilitating data association and traceability. At the same time, access permissions for multiple departments will be configured: the fire supervision department will have full data read and write permissions, the emergency management department will have priority access to early warning data, the operation and maintenance management department will have access to sensor status data and calibration parameter modification permissions, and the third-party audit department will have read-only access to data for the past three months within a specified period. Data access services matching the permissions of each department will be opened through a preset encrypted interface, taking into account both data sharing and security control.

[0030] The collaborative tracing module obtains contract-verified fire monitoring data through permission configuration and displays it on the system platform according to the classification of plant number, area type, and monitoring indicators, facilitating quick data retrieval by various departments. When the calibrated CO concentration data of the storage tank area in Plant 5 reaches 39 ppm, exceeding the preset threshold of 35 ppm, the system immediately triggers a level-two fire alarm to promptly detect the risk of toxic gas leakage. The collaborative tracing module simultaneously pushes the alarm information to the fire supervision department, emergency management department, and operation and maintenance management department, ensuring that relevant departments grasp the risk situation as soon as possible. Subsequently, a multi-department collaborative response process is initiated, pushing precise location data of the CO exceeding the standard area to the fire supervision department to help quickly locate the risk point, pushing personnel evacuation route planning data for the plant and adjacent plants to the emergency management department to ensure safe evacuation of personnel, and pushing the equipment number, installation location, and health status indicators of the main sensor and neighboring sensors in the area to the operation and maintenance management department to facilitate timely troubleshooting of equipment problems, such as... Figure 2 As shown. When data is found to be questionable during the handling process, or when it is necessary to check whether the sensor is faulty, the collaborative traceability module can retrieve data from the entire chain to perform traceability verification, clarify the data source and processing flow, provide strong evidence for fault investigation and responsibility determination, and adapt to the strict safety traceability requirements in chemical scenarios.

[0031] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. An intelligent fire early warning and emergency response system based on the Internet of Things, characterized in that, The system includes: a data acquisition and self-testing module, an edge dynamic calibration module, an on-chain storage module, a contract verification module, and a collaborative traceability module; The data acquisition and self-test module is used to collect fire monitoring data through tagged sensors deployed at the fire monitoring site, and simultaneously perform sensor health self-tests and generate health status labels. The edge dynamic calibration module receives the collected fire monitoring data and sensor health status indicators, performs calibration through a multi-dimensional fusion dynamic calibration algorithm, generates calibration parameters, and feeds the calibration parameters back to the acquisition self-test module. At the same time, the calibrated fire monitoring data, health status indicators, and calibration parameters are transmitted to the on-chain storage module. The on-chain storage module receives calibrated fire monitoring data, health status indicators and calibration parameters, records data transmission link logs, performs multi-node data synchronization storage through a consensus mechanism, and sends a data ready signal to the contract verification module after storage is completed. The contract verification module: after receiving the data ready signal, extracts the calibrated fire monitoring data, health status identifier, calibration parameters and transmission link logs, performs data credibility verification using a full-link trusted verification algorithm, adds status identifiers to the fire monitoring data and binds calibration parameters and health status identifiers, configures access permissions for multiple departments and opens data access. The collaborative tracing module: through configured access permissions for multiple departments, it displays fire monitoring data and triggers an early warning when the data exceeds a preset threshold, enabling collaborative responses from multiple departments. In fault scenarios, it can retrieve data from the entire chain to perform tracing and verification.

2. The intelligent fire early warning and emergency response system based on the Internet of Things according to claim 1, characterized in that, The self-test module includes four types of main monitoring sensors: temperature, smoke concentration, CO concentration, and humidity, as well as corresponding neighborhood sensors. Each type of identifiable sensor integrates a data acquisition unit, a unique identification chip, a self-test unit, and a communication unit. The data acquisition unit is used to collect temperature, smoke concentration, CO concentration, and humidity data for the corresponding monitoring area. The neighborhood sensors are of the same type as the main monitoring sensors and are deployed in the same monitoring sub-area to collect environmental monitoring data consistent with that of the main monitoring sensors. The unique identification chip is used to store the sensor's device number, installation location, and calibration cycle information. The self-test unit is used to detect the power supply status, data acquisition accuracy, and communication link stability of the sensor in real time and generate a health status identifier; the communication unit is used to transmit the collected fire monitoring data, health status identifier, and unique identifier information to the edge dynamic calibration module.

3. The intelligent fire early warning and emergency response system based on the Internet of Things according to claim 1, characterized in that, The edge dynamic calibration module performs calibration using a multi-dimensional fusion dynamic calibration algorithm. The specific steps for generating calibration parameters are as follows: receiving fire monitoring data and sensor health status identifiers transmitted by the acquisition and self-test module through the IoT communication interface; parsing and verifying the integrity of the received data; filtering out the fire monitoring data and corresponding health status identifiers that have passed the verification; calling the multi-dimensional fusion dynamic calibration algorithm; substituting the verified fire monitoring data, sensor health status identifiers, and preset neighboring sensor weights into the algorithm to calculate and obtain the calibrated fire monitoring data. The fusion weight coefficient and health status correction coefficient in the calculation process are extracted as calibration parameters, and the calibration parameters are fed back to the data acquisition and self-test module through the IoT communication interface.

4. The intelligent fire early warning and emergency response system based on the Internet of Things according to claim 3, characterized in that, The calculation formula for the multi-dimensional fusion dynamic calibration algorithm in the edge dynamic calibration module is as follows: ,in, This represents the final calibration data of the j-th sensor within the i-th monitoring area at time t. To collect the raw data of the j-th sensor in the i-th monitoring area transmitted by the self-test module at time t; The adjustment coefficient for cross-sensor data fusion; This represents the total number of valid neighboring sensors that are located within the same monitoring sub-region as the j-th sensor. Let be the confidence weight of the k-th neighboring sensor; This represents the raw data collected at time t from the k-th neighboring sensor within the i-th monitoring area. The average value of the data collected by the k-th neighboring sensor within the time period T; This is the correction coefficient determined based on the health status identifier generated by the data collection and self-testing module.

5. The intelligent fire early warning and emergency response system based on the Internet of Things according to claim 1, characterized in that, The consensus mechanism in the on-chain storage module includes proposal node election, data consistency verification, node voting confirmation, and storage result uploading to the chain. The specific process of multi-node data synchronization storage through the consensus mechanism is as follows: The on-chain storage module first hashes and encrypts the data to be stored and the link log to generate a unique data fingerprint, and then broadcasts the data fingerprint to all storage nodes in the blockchain network. Each storage node performs consistency verification on the data fingerprint and the corresponding original data. Nodes that pass the verification store the data locally and send back confirmation information. When the number of nodes that send back confirmation information reaches more than 2 / 3 of the total number of nodes in the blockchain network, the multi-node synchronization storage of the data is completed. After storage is completed, a data ready signal is sent to the contract verification module.

6. The intelligent fire early warning and emergency response system based on the Internet of Things according to claim 1, characterized in that, The contract verification module uses a full-link trusted verification algorithm to perform data trustworthiness verification. The specific steps for adding status identifiers and binding calibration parameters and health status identifiers to fire monitoring data are as follows: extract the calibrated fire monitoring data, health status identifiers, calibration parameters, and transmission link logs transmitted from the on-chain storage module; and verify the integrity of node signatures in the transmission link logs, the validity of sensor health status identifiers, and the matching degree between calibration parameters and original collected data in sequence through the full-link trusted verification algorithm. Based on the verification results, add status labels to the fire monitoring data as reliable, pending verification, or unreliable; The fire monitoring data with added status identifiers are bound to the corresponding calibration parameters and health status identifiers to generate a unique data association identifier.

7. The intelligent fire early warning and emergency response system based on the Internet of Things according to claim 6, characterized in that, The formula for the end-to-end trusted verification algorithm in the contract verification module is as follows: ,in, This is the comprehensive score for end-to-end trusted verification. This represents the total number of dimensions for end-to-end verification. Let be the weight coefficient of the i-th verification dimension; The state score for the i-th verification dimension; Let be the consistency verification coefficient for the i-th verification dimension.

8. The intelligent fire early warning and emergency response system based on the Internet of Things according to claim 1, characterized in that, The contract verification module includes access permissions for multiple departments, including fire supervision departments, emergency management departments, operation and maintenance management departments, and third-party audit departments. The fire supervision department has the right to read and write all data, the emergency management department has the right to prioritize reading early warning data, the operation and maintenance management department has the right to read sensor status data and modify calibration parameters, and the third-party audit department has the right to read data only for a specified period. Data access services matching the permissions are opened to the corresponding departments through a preset encrypted interface.

9. The intelligent fire early warning and emergency response system based on the Internet of Things according to claim 1, characterized in that, The collaborative tracing module displays fire monitoring data and triggers an early warning when the data exceeds a preset threshold, enabling multi-department collaborative response. Specifically, it acquires fire monitoring data through configured multi-department access permissions, categorizes and displays the data according to monitoring area and monitoring type, and compares the acquired fire monitoring data in real time with fire warning thresholds of 65°C, smoke concentration threshold of 0.15%, and CO concentration threshold of 35ppm. When any monitoring data exceeds the corresponding threshold, an early warning message is generated. The early warning information will be simultaneously pushed to fire supervision departments, emergency management departments, and operation and maintenance management departments; Initiate a multi-departmental collaborative response process, push location data of fire risk areas to fire supervision departments, personnel evacuation route planning data to emergency management departments, and equipment number and location information of faulty sensors to operation and maintenance management departments.

Images