AFIS intelligent fire-fighting monitoring system based on Internet of Things technology

Abstract

The invention discloses an AFIS intelligent fire-fighting monitoring system based on the Internet of Things technology, and relates to the technical field of fire-fighting safety, and the AFIS intelligent fire-fighting monitoring system comprises a front-end module, a central monitoring module, a data analysis module, an early warning module and a fault diagnosis module. The front-end module is used for monitoring fire-related environment data and fire-fighting equipment states through a plurality of sensor nodes; installing and deploying various types of sensor nodes in the key area; the collected original data is subjected to primary processing, including data cleaning, denoising, standardization and the like, so that the accuracy and reliability of the data are ensured; according to the invention, through integration of various sensor nodes, real-time monitoring of environment parameters of a key area and the state of fire-fighting equipment is realized, so that the fire prevention and response efficiency is obviously improved, the system can wirelessly transmit data by using the Internet of Things technology, the complexity of installation and maintenance is reduced, and the monitoring range is expanded.

Description

Technical Field

[0001] The present invention relates to the field of fire safety technology, and in particular to an AFIS intelligent fire monitoring system based on Internet of Things technology. Background Art

[0002] Although existing fire monitoring systems play an important role in fire prevention and monitoring, they still have some limitations. For example, some systems may rely on wired connections, which not only increases the complexity of installation and maintenance, but also may limit the expansion of monitoring range. In addition, traditional fire monitoring equipment may lack intelligence in data processing and analysis, resulting in insufficiently timely or accurate assessment of fire risks. In some cases, aging equipment or insufficient maintenance may lead to monitoring blind spots, increasing the risk of fire.

[0003] With the rapid development of IoT technology, wireless connection, remote monitoring and intelligent processing have become possible. However, when applying IoT technology to fire monitoring systems, there are challenges in the real-time, security and reliability of data. For example, wireless transmission may be interfered with, and data encryption and secure communication protocols need to be strengthened to protect privacy and prevent data tampering. In addition, the status monitoring and fault warning of fire equipment also require more sophisticated and intelligent algorithms to improve accuracy.

[0004] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0005] The purpose of the present invention is to solve the problems of insufficient real-time performance and accuracy in the existing fire monitoring system and the limitations of the application of Internet of Things technology, and to propose an AFIS intelligent fire monitoring system based on Internet of Things technology.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] An AFIS intelligent fire monitoring system based on Internet of Things technology, comprising:

[0008] A front-end module for monitoring fire-related environmental data and firefighting equipment status data through multiple sensor nodes;

[0009] The central monitoring module is used to receive data from different sensor nodes and send it to the data analysis module for analysis through the Internet of Things communication protocol;

[0010] Data analysis module, which is used to analyze the collected data in real time through algorithms to determine the fire risk and the status of fire fighting equipment;

[0011] The early warning module is used to issue a fire early warning based on the fire risk analysis in the data analysis module;

[0012] The fault diagnosis module is used to provide fault warning for abnormal fire-fighting equipment analyzed by the data analysis module.

[0013] Furthermore, the process of the front-end module monitoring fire-related environmental data and firefighting equipment status data through multiple sensor nodes is as follows:

[0014] Install smoke, temperature, flame, combustible gas and water flow sensors in key areas to monitor environmental parameters and firefighting equipment status in real time;

[0015] Sensor nodes detect smoke concentration, temperature changes, flames, gas leaks, water pressure and flow indicators;

[0016] Perform data cleaning, denoising and standardization to ensure data accuracy and reliability;

[0017] Compress and encode the processed data to adapt to wireless transmission and reduce data loss and errors;

[0018] According to monitoring requirements, set corresponding collection frequencies for different types of data;

[0019] Regularly self-check the sensor and communication status, and automatically perform maintenance or notify maintenance personnel when abnormalities occur.

[0020] Furthermore, the specific operation steps of compressing and encoding the processed data in the front-end module are as follows:

[0021] Apply compression algorithms to reduce data volume, and choose lossy or lossless compression according to needs;

[0022] Use Huffman coding, arithmetic coding or run-length coding techniques to reduce data redundancy;

[0023] Add header information, sequence number and checksum to form a data packet;

[0024] Use AES and other algorithms to encrypt data to ensure transmission security;

[0025] Send data via Wi-Fi, Zigbee, LoRa or NB-IoT technology;

[0026] Adjust the acquisition frequency and transmission rate according to bandwidth and energy consumption constraints;

[0027] Implement CRC or FEC mechanism to improve data transmission reliability;

[0028] Ensure data synchronization between the sensor and the receiver.

[0029] Furthermore, the specific operation steps of the front-end module to set corresponding collection frequencies for different types of data are as follows:

[0030] In the initial stage, environmental parameters and fire equipment status data are collected and stored, and historical data are used to analyze the characteristics and patterns under normal and abnormal conditions;

[0031] Extract key features from raw data;

[0032] Use machine learning algorithms to train models to identify normal and abnormal trends;

[0033] Apply trained models to monitor data in real time and predict short-term and long-term trends;

[0034] Dynamically adjust the data collection frequency based on the prediction results;

[0035] The collected new data is input into the model again for learning and adjustment to optimize the prediction accuracy and frequency adjustment strategy;

[0036] When the environment is stable, the acquisition frequency is reduced to reduce energy consumption and system load, and reasonable resource allocation is achieved. The intelligent algorithm is integrated with the early warning system. When an abnormality is detected, not only the acquisition frequency is increased, but also the early warning process is triggered;

[0037] A user interface is provided to display the current acquisition frequency and environmental status, allowing the operator to make manual adjustments as needed, and to regularly evaluate system performance, including the accuracy and response time of acquisition frequency adjustment, and to optimize based on feedback.

[0038] Furthermore, the specific operation steps of the central monitoring module sending the data to the data analysis module for analysis through the Internet of Things communication protocol are as follows:

[0039] Receive sensor node data via IoT communication protocol;

[0040] Assign a unique identifier to each sensor node and configure the communication protocol;

[0041] Synchronize the collected data in real time to ensure the timeliness of information;

[0042] Store encrypted data in a central database to keep historical records;

[0043] Forward stored data to the data analysis module for in-depth analysis;

[0044] Continuously monitor the status of sensors and communication equipment to ensure normal operation;

[0045] Set thresholds to detect data anomalies or equipment failures and record them;

[0046] When an anomaly is detected, relevant personnel are notified through preset channels;

[0047] Provide interfaces to remotely control sensor nodes or firefighting equipment;

[0048] Update the user interface in real time to display the latest monitoring data and system status;

[0049] Record all critical operations and system events for auditing and troubleshooting;

[0050] Regularly check system performance, perform maintenance and update software, and interact with data analysis modules to ensure data is timely used for risk assessment and condition monitoring.

[0051] Furthermore, the specific operation steps of the data analysis module to judge the fire risk and the status of the fire fighting equipment are as follows:

[0052] Receive encrypted data forwarded by the central monitoring module and decrypt it for analysis;

[0053] Integrate decrypted data with data sources to form a comprehensive monitoring view;

[0054] Clean the data, including removing noise and standardizing it, to ensure the accuracy of analysis;

[0055] Extract key features from the data for risk assessment;

[0056] Use statistical and machine learning algorithms to analyze data in real time to identify risk patterns and trends;

[0057] Assess the probability and urgency of fire occurrence based on the analysis results;

[0058] Analyze fire equipment data and monitor equipment operating status;

[0059] Identify data anomalies through thresholds and rules, indicating potential equipment failure or fire risks;

[0060] Generate decision support information and provide action recommendations to fire management personnel;

[0061] When high risk is detected, generate and send warning information to the warning module;

[0062] Conduct in-depth analysis of abnormal equipment data and diagnose the cause of the failure;

[0063] Generate analysis reports including risk assessment and equipment status;

[0064] Send analysis results and feedback back to the central monitoring module for system adjustment and optimization;

[0065] Continuously optimize machine learning models using new data to improve risk assessment accuracy;

[0066] Ensure that operators receive analysis results and warning information in real time through the user interface.

[0067] Furthermore, the data analysis module uses statistical and machine learning algorithms to analyze data in real time and identify risk patterns and trends. The specific operation steps are as follows:

[0068] Select the extracted features related to fire risk, including smoke density, temperature change rate and combustible gas concentration, construct derived features, and enhance the prediction ability of the model through mathematical transformation;

[0069] Select the corresponding algorithm based on data characteristics and business needs, use historical data to train the model, and optimize the model parameters through continuous iteration;

[0070] Apply stream processing technology to process real-time data;

[0071] Feed real-time data into the model to perform predictive analysis of fire risk, using machine learning models to identify patterns and trends in the data;

[0072] Based on the model output, the probability and risk level of fire occurrence are evaluated, the data change trend is analyzed, and the development direction of fire risk is predicted;

[0073] Set the risk assessment threshold. When the prediction result exceeds the threshold, identify it as an abnormal situation, convert the analysis result into an easy-to-understand format, and visualize it on the user interface;

[0074] Let the model continue to learn based on the latest data to adapt to environmental changes and improve prediction accuracy.

[0075] Furthermore, the specific operation steps of the early warning module for judging the need for fire early warning based on the fire risk analyzed in the data analysis module are as follows:

[0076] Receive the fire risk assessment results from the data analysis module, judge the fire risk level based on the risk assessment provided by the data analysis module, and determine whether an early warning needs to be issued;

[0077] Set thresholds for different risk levels. When the assessment results exceed the preset thresholds, the early warning program will be automatically initiated.

[0078] When a high risk is identified, generate warning information, including warning type, risk level, affected area and recommended response measures;

[0079] Send early warning information to relevant personnel or systems through different communication channels;

[0080] Automatically trigger emergency response measures in high-risk fire situations, including activating sprinkler systems and closing fire doors;

[0081] Real-time updates to the user interface ensure that operators view the latest warning information and system status, and record all warning events and corresponding response measures for future auditing and troubleshooting;

[0082] Establish a feedback mechanism to collect on-site feedback information after early warning to evaluate the accuracy and effectiveness of the early warning system. Based on the feedback information and actual fire conditions, continuously optimize the early warning parameters and thresholds to improve the intelligence level of the early warning system.

[0083] Furthermore, the specific operation steps of the fault diagnosis module for performing fault warning on the abnormal fire-fighting equipment analyzed by the data analysis module are as follows:

[0084] Receive fire equipment status data provided by the data analysis module;

[0085] Analyze data to identify deviations based on preset thresholds of normal operation;

[0086] Apply machine learning or deep learning techniques to classify abnormal data and identify failure modes;

[0087] Determine the exact location of the fault, analyze the cause of the fault by comprehensively analyzing historical data, usage and environmental factors;

[0088] Generate early warning information based on fault type and severity;

[0089] Through the central monitoring module, the warning information is sent to relevant personnel or systems;

[0090] Assess the risk of equipment failure when no failure mode is identified.

[0091] Furthermore, when the fault diagnosis module does not identify the fault mode, the process of evaluating the equipment failure risk is as follows:

[0092] Comprehensive analysis is performed by collecting risk parameters of fire-fighting equipment, including equipment time, maintenance times, operating hours, load changes and environmental factors. Load changes are obtained by collecting load changes of equipment in different time periods, and calculating the load through the variance calculation formula to obtain a negative rating. This negative rating is used as a standard to measure equipment load changes. The greater the negative rating, the greater the equipment load change.

[0093] Environmental factors collect humidity, oxygen concentration and corrosive gas concentration indicators around the equipment, and then calculate the difference with the preset standard humidity, standard oxygen concentration and standard corrosive gas concentration. If it does not exceed the standard, it is recorded as 0, and the humidity difference, oxygen difference and corrosive difference are obtained respectively. After normalization, they are multiplied by the preset weight coefficient and summed to obtain the environmental impact assessment value;

[0094] The equipment time, maintenance times, operating hours, negative evaluation values ​​and environmental impact assessment values ​​are converted into a unified dimension and range, that is, between 0 and 10, and calibrated as ss, cw, yt, fp and ph respectively, and then substituted into the following formula: ZPZ = [1.2 (ss * χ1 + cw * χ2) + yt * χ3 + fp * χ4] 0.94 *(1-ph -1 ) to obtain the comprehensive evaluation value ZPZ, where χ1, χ2, χ3, and χ4 are the preset weight coefficients of equipment time, maintenance times, operating time, and negative evaluation value respectively;

[0095] The obtained comprehensive evaluation value is compared with the preset comprehensive evaluation threshold. When the comprehensive evaluation value is greater than the comprehensive evaluation threshold, it is judged that the risk of failure of the fire-fighting equipment has reached the standard, and advance maintenance planning is carried out to avoid maintenance of the fire-fighting equipment when a failure occurs.

[0096] Compared with the prior art, the present invention has the following beneficial effects:

[0097] (1) The present invention realizes real-time monitoring of environmental parameters in key areas and the status of firefighting equipment by integrating multiple sensor nodes, thereby significantly improving the efficiency of fire prevention and response. By utilizing the Internet of Things technology, the system can transmit data wirelessly, reducing the complexity of installation and maintenance and expanding the monitoring range. The data preprocessing function of the front-end module, including cleaning, denoising and standardization, ensures the accuracy and reliability of the data and provides high-quality input for subsequent data analysis.

[0098] (2) In the present invention, the data analysis module uses advanced statistical and machine learning algorithms to perform real-time analysis on the collected data, effectively identifying fire risk patterns and trends. By dynamically adjusting the data collection frequency and implementing risk assessment, the system can timely predict and respond to potential abnormal situations. The early warning module further enhances the early warning capability of the system. When the fire risk assessment result exceeds the preset threshold, the early warning program can be automatically started, and the early warning information can be quickly transmitted through multiple communication channels to ensure that timely response measures are taken;

[0099] (3) In the present invention, the fault diagnosis module realizes the assessment of equipment failure risk by comprehensively analyzing the risk parameters of fire-fighting equipment, can identify the specific failure mode, and determine the exact location where the failure occurs, providing maintenance personnel with accurate fault diagnosis information. The system can also improve the accuracy of fault risk assessment by continuously learning and optimizing the analysis model when the failure mode is not identified. This intelligent fault diagnosis and maintenance planning mechanism helps to avoid fire-fighting equipment failures in emergency situations, thereby improving the reliability and safety of the entire fire monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0100] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0101] Figure 1 This is the overall system block diagram of the present invention. DETAILED DESCRIPTION

[0102] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0103] It should be understood that the terms "include" and "comprising" used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0104] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the disclosure. As used in this disclosure and claims, the singular forms of "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations.

[0105] like Figure 1 As shown, an AFIS intelligent fire monitoring system based on Internet of Things technology includes but is not limited to smoke sensors, temperature sensors, flame sensors, combustible gas sensors, and water flow sensors; each sensor node monitors the environmental parameters around it or the operating status of fire-fighting equipment, such as smoke concentration, temperature change, flame detection, specific gas leakage, and water pressure and flow of fire hydrants and sprinkler systems; the collected raw data is preliminarily processed, including data cleaning, denoising, and standardization, to ensure the accuracy and reliability of the data; the processed data is converted into a format suitable for wireless transmission, including data compression and encoding, to reduce data loss and errors during transmission. The specific process is as follows:

[0106] Use appropriate compression algorithms to reduce the size of the data. This can be lossy compression, discarding some unimportant information, or lossless compression, maintaining the integrity of the data while reducing the amount of data; Encode the compressed data and convert it into a format suitable for wireless transmission. This may include the use of specific coding techniques, such as Huffman coding, arithmetic coding, or run-length coding, to further reduce the redundancy of the data; Encapsulate the encoded data into a data packet suitable for wireless transmission, including adding necessary header information, sequence numbers, checksums, etc. to ensure the integrity and reliability of the data; To ensure the security of the data during transmission, encrypt the encapsulated data, usually using encryption algorithms such as AES; Send the data to the central monitoring module through wireless communication technologies (such as Wi-Fi, Zigbee, LoRa, NB-IoT, etc.);

[0107] Taking into account the bandwidth and energy limitations of wireless transmission, optimize the data transmission strategy, such as by adjusting the data acquisition frequency, adopting adaptive transmission rate and other methods; during the data transmission process, use error detection and correction mechanisms, such as cyclic redundancy check (CRC) or forward error correction (FEC) coding, to improve the reliability of data transmission; ensure data synchronization between sensor nodes and receivers to facilitate accurate data parsing and processing.

[0108] The environmental parameters and fire equipment status data are collected at different frequencies. The specific process is as follows:

[0109] In the initial stage, environmental parameters and fire equipment status data are collected and stored, and historical data is used to analyze the characteristics and patterns under normal and abnormal conditions; key features are extracted from the raw data, such as a sudden increase in temperature or an increase in smoke concentration; machine learning algorithms, such as time series analysis, hidden Markov models (HMMs) or recurrent neural networks (RNNs), are used to train models to identify normal and abnormal trends; the trained models are applied to monitor data in real time and predict short-term and long-term trends;

[0110] Dynamically adjust the data collection frequency based on the prediction results. For example, when the model predicts a potential abnormal trend, the collection frequency is automatically increased to monitor the situation more accurately; the new data collected is input into the model again for learning and adjustment to optimize the prediction accuracy and frequency adjustment strategy; when the environment is stable, the collection frequency is reduced to reduce energy consumption and system load, and achieve reasonable allocation of resources. The intelligent algorithm is integrated with the early warning system. When an abnormality is detected, not only the collection frequency is increased, but also the early warning process is triggered; a user interface is provided to display the current collection frequency and environmental status, allowing the operator to manually adjust it as needed, and the system performance is regularly evaluated, including the accuracy and response time of the collection frequency adjustment, and optimized based on feedback.

[0111] The front-end module performs regular self-checks to monitor the status of sensors and communication modules to ensure their normal operation. When an abnormality is detected, it automatically triggers the maintenance process or notifies maintenance personnel to conduct inspections and repairs.

[0112] The central monitoring module is used to receive data from different sensor nodes and send it to the data analysis module for analysis through the Internet of Things communication protocol;

[0113] Receive data from front-end sensor nodes through IoT communication protocols (such as MQTT, CoAP, Modbus, etc.), which may include information such as temperature, smoke concentration, and flame detection; configure unique identifiers for different sensor nodes and set corresponding IoT communication protocols (such as MQTT, CoAP, etc.) to receive data; synchronize the data collected by sensor nodes in real time to ensure the timeliness of the data;

[0114] Store encrypted data in a central database and retain data history for subsequent analysis and auditing; forward stored data to the data analysis module through internal communication protocols for in-depth analysis; continuously monitor the status of sensor nodes and communication devices to ensure they are working properly; set thresholds and rules to detect and record when sensor data indicates abnormal device status or failure; trigger an alarm mechanism when device failure or data anomaly is detected, and notify relevant personnel through preset communication channels (SMS, email, mobile application, etc.); provide an interface for the central monitoring module to remotely control sensor nodes or other firefighting equipment when necessary;

[0115] Real-time updates to the user interface ensure that operators can view the latest monitoring data and system status;

[0116] Record all key operations and system events for future auditing and troubleshooting; regularly check system performance, perform necessary maintenance tasks, and update system software as needed; interact with the data analysis module to ensure that the collected data can be used for fire risk assessment and fire equipment status monitoring in a timely and accurate manner.

[0117] The data analysis module is used to analyze the collected data in real time through algorithms to determine the fire risk and the status of fire fighting equipment;

[0118] Receive data forwarded from the central monitoring module, which has been encrypted and stored; decrypt the data stored in the database for analysis; integrate the decrypted data with other relevant data sources to obtain a comprehensive monitoring view; further clean and standardize the data to ensure the accuracy of the analysis; extract key features from the raw data, such as peak smoke concentration and abnormal temperature increase, which are crucial for fire risk assessment; use statistical analysis, machine learning and other algorithms to analyze the data in real time to identify fire risk patterns and trends. The specific steps are as follows:

[0119] Select extracted features related to fire risk, such as smoke density, temperature change rate, combustible gas concentration, etc., construct derived features, and enhance the model's prediction ability through mathematical transformation; select appropriate algorithms based on data characteristics and business needs, such as decision trees, random forests, support vector machines (SVMs), neural networks, etc., use historical data to train models, and optimize model parameters through continuous iteration; apply stream processing technologies, such as Apache Kafka or Apache Storm, to process real-time data;

[0120] Real-time data is input into the model to conduct predictive analysis of fire risks, and machine learning models are used to identify patterns and trends in the data, such as a continuous increase in smoke concentration or an abnormal peak in temperature. Based on the model output, the probability and risk level of fire are evaluated, the trend of data changes is analyzed, and the direction of fire risk development is predicted. A threshold for risk assessment is set, and when the prediction result exceeds the threshold, it is identified as an abnormal situation. The analysis results are converted into an easy-to-understand format and visualized on the user interface. The model is allowed to continuously learn based on the latest data to adapt to environmental changes and improve prediction accuracy.

[0121] Based on the analysis results, assess the possibility and urgency of fire;

[0122] Analyze fire equipment related data, such as water flow sensor readings, to monitor whether the fire protection system is in normal working condition; identify abnormal patterns in the data by setting thresholds and rules, which may indicate potential equipment failure or fire risk;

[0123] Generate decision support information to advise fire managers on whether action is needed;

[0124] When a high fire risk is detected, early warning information is generated and sent to the early warning module; abnormal fire equipment data is deeply analyzed to diagnose possible causes of failure; detailed analysis reports are generated, including fire risk assessment results and fire equipment status reports; analysis results and feedback are sent back to the central monitoring module for necessary adjustments and optimizations; machine learning algorithms are used to continuously optimize the analysis model based on new data to improve the accuracy of fire risk assessment; and the user interface is interacted with to ensure that operators can receive analysis results and early warning information in real time.

[0125] The early warning module is used to issue a fire early warning based on the fire risk analysis in the data analysis module;

[0126] Receive the fire risk assessment results and fire equipment status information from the data analysis module, judge the fire risk level based on the risk assessment provided by the data analysis module, and determine whether an early warning is needed; set thresholds for different risk levels, and automatically start the early warning program when the assessment results exceed the preset thresholds;

[0127] When a high risk is determined, early warning information is generated, including the type of warning, risk level, affected area and recommended response measures; early warning information is sent to relevant personnel or systems through multiple communication channels (such as SMS, email, mobile application push, automatic voice call, etc.); in the case of high fire risk, emergency response measures are automatically triggered, including starting the sprinkler system, closing the fire door, etc.;

[0128] Update the user interface in real time to ensure that operators can view the latest warning information and system status, and record all warning events and corresponding response measures for future audits and troubleshooting; establish a feedback mechanism to collect on-site feedback information after the warning to evaluate the accuracy and effectiveness of the warning system, and continuously optimize the warning parameters and thresholds based on the feedback information and actual fire situations to improve the intelligence level of the warning system.

[0129] The fault diagnosis module is used to provide fault warning for abnormal fire-fighting equipment analyzed by the data analysis module.

[0130] Receive data about the status of firefighting equipment from the data analysis module, which may include sensor readings, equipment performance parameters, etc.; by setting normal operating thresholds, the module analyzes the collected data to identify deviations from the normal state, thereby detecting potential abnormalities; using pattern recognition algorithms, such as machine learning or deep learning technology, classify abnormal data and identify specific failure modes; when a failure mode is identified, the module needs to determine the exact location where the failure occurred, such as a specific sensor or equipment component; analyze the cause of the failure, which may involve historical data comparison, equipment usage, environmental factors, etc.;

[0131] According to the fault type and severity, the corresponding warning information is generated and sent to relevant personnel or systems through the central monitoring module; when the fault mode is not identified, the risk of fire equipment failure is determined by comprehensive analysis of the data of the fire equipment, specifically by collecting the risk parameters of the fire equipment for comprehensive analysis, where the risk parameters of the fire equipment include:

[0132] Equipment time: the time the equipment is in use. Aging equipment may have a higher risk of failure. Maintenance times: the number of times the equipment is maintained or repaired. Frequent repairs may indicate potential problems. Running time: the continuous running time of the equipment. Long-term operation may cause component wear. Load change: the load change of the equipment in different time periods. The load is calculated through the variance calculation formula to obtain a negative rating, and this negative rating is used as a standard to measure the load change of the equipment. The larger the negative rating, the greater the load change of the equipment. Frequent or extreme load changes may affect the stability of the equipment. Environmental factors: by collecting the humidity, oxygen concentration and corrosive gas concentration indicators around the equipment, and then calculating the difference with the preset standard humidity, standard oxygen concentration and standard corrosive gas concentration, it is recorded as 0 when it is not exceeded, and the humidity difference, oxygen difference and corrosion difference are obtained respectively. After normalization, they are multiplied by the preset weight coefficients and summed to obtain the environmental impact assessment value.

[0133] The equipment time, maintenance times, operating hours, negative evaluation values ​​and environmental impact assessment values ​​are converted into a unified dimension and range, that is, between 0 and 10, and calibrated as ss, cw, yt, fp and ph respectively, and then substituted into the following formula: ZPZ = [1.2 (ss * χ1 + cw * χ2) + yt * χ3 + fp * χ4] 0.94 *(1-ph -1 ) to obtain the comprehensive evaluation value ZPZ, where χ1, χ2, χ3, and χ4 are the preset weight coefficients of equipment time, maintenance times, operating time, and negative evaluation value, and are set between 1.21-1.35, 0.94-0.98, 1.12-1.23, and 0.85-0.93, respectively; the obtained comprehensive evaluation value is used as a standard for measuring the risk of failure of fire-fighting equipment; the obtained comprehensive evaluation value is compared with the preset comprehensive evaluation threshold. When the comprehensive evaluation value is greater than the comprehensive evaluation threshold, it is judged that the risk of failure of the fire-fighting equipment meets the standard, and advance maintenance planning is carried out to avoid maintenance of the fire-fighting equipment when it fails.

[0134] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An AFIS intelligent fire monitoring system based on Internet of Things technology, characterized in that: include: A front-end module for monitoring fire-related environmental data and firefighting equipment status data through multiple sensor nodes; The central monitoring module is used to receive data from different sensor nodes and send it to the data analysis module for analysis through the Internet of Things communication protocol; Data analysis module, which is used to analyze the collected data in real time through algorithms to determine the fire risk and the status of fire fighting equipment; The early warning module is used to issue a fire early warning based on the fire risk analysis in the data analysis module; The fault diagnosis module is used to provide fault warning for abnormal fire-fighting equipment analyzed by the data analysis module.

2. According to claim 1, an AFIS intelligent fire monitoring system based on Internet of Things technology is characterized in that: The process of the front-end module monitoring fire-related environmental data and fire-fighting equipment status data through multiple sensor nodes is as follows: Install smoke, temperature, flame, combustible gas and water flow sensors in key areas to monitor environmental parameters and firefighting equipment status in real time; Sensor nodes detect smoke concentration, temperature changes, flames, gas leaks, water pressure and flow indicators; Perform data cleaning, denoising and standardization to ensure data accuracy and reliability; Compress and encode the processed data to adapt to wireless transmission and reduce data loss and errors; According to monitoring requirements, set corresponding collection frequencies for different types of data; Regularly self-check the sensor and communication status, and automatically perform maintenance or notify maintenance personnel when abnormalities occur.

3. The AFIS intelligent fire monitoring system based on Internet of Things technology according to claim 2 is characterized in that: The specific operation steps of compressing and encoding the processed data in the front-end module are as follows: Apply compression algorithms to reduce data volume, and choose lossy or lossless compression according to needs; Use Huffman coding, arithmetic coding or run-length coding techniques to reduce data redundancy; Add header information, sequence number and checksum to form a data packet; Use AES and other algorithms to encrypt data to ensure transmission security; Send data via Wi-Fi, Zigbee, LoRa or NB-IoT technology; Adjust the acquisition frequency and transmission rate according to bandwidth and energy consumption constraints; Implement CRC or FEC mechanism to improve data transmission reliability; Ensure data synchronization between the sensor and the receiver.

4. The AFIS intelligent fire monitoring system based on Internet of Things technology according to claim 2 is characterized in that: The specific operation steps of the front-end module to set the corresponding acquisition frequency for different types of data are as follows: In the initial stage, environmental parameters and fire equipment status data are collected and stored, and historical data are used to analyze the characteristics and patterns under normal and abnormal conditions; Extract key features from raw data; Use machine learning algorithms to train models to identify normal and abnormal trends; Apply trained models to monitor data in real time and predict short-term and long-term trends; Dynamically adjust the data collection frequency based on the prediction results; The collected new data is input into the model again for learning and adjustment to optimize the prediction accuracy and frequency adjustment strategy; When the environment is stable, the acquisition frequency is reduced to reduce energy consumption and system load, and reasonable resource allocation is achieved. The intelligent algorithm is integrated with the early warning system. When an abnormality is detected, not only the acquisition frequency is increased, but also the early warning process is triggered; A user interface is provided to display the current acquisition frequency and environmental status, allowing the operator to make manual adjustments as needed, and to regularly evaluate system performance, including the accuracy and response time of acquisition frequency adjustment, and to optimize based on feedback.

5. The AFIS intelligent fire monitoring system based on Internet of Things technology according to claim 1 is characterized in that: The specific operation steps of the central monitoring module sending the data to the data analysis module for analysis through the Internet of Things communication protocol are as follows: Receive sensor node data via IoT communication protocol; Assign a unique identifier to each sensor node and configure the communication protocol; Synchronize the collected data in real time to ensure the timeliness of information; Store encrypted data in a central database to keep historical records; Forward stored data to the data analysis module for in-depth analysis; Continuously monitor the status of sensors and communication equipment to ensure normal operation; Set thresholds to detect data anomalies or equipment failures and record them; When an anomaly is detected, relevant personnel are notified through preset channels; Provide interfaces to remotely control sensor nodes or firefighting equipment; Update the user interface in real time to display the latest monitoring data and system status; Record all critical operations and system events for auditing and troubleshooting; Regularly check system performance, perform maintenance and update software, and interact with data analysis modules to ensure data is timely used for risk assessment and condition monitoring.

6. The AFIS intelligent fire monitoring system based on Internet of Things technology according to claim 1 is characterized in that: The specific operation steps of the data analysis module to judge the fire risk and the status of the fire fighting equipment are as follows: Receive encrypted data forwarded by the central monitoring module and decrypt it for analysis; Integrate decrypted data with data sources to form a comprehensive monitoring view; Clean the data, including removing noise and standardizing it, to ensure the accuracy of analysis; Extract key features from the data for risk assessment; Use statistical and machine learning algorithms to analyze data in real time to identify risk patterns and trends; Assess the probability and urgency of fire occurrence based on the analysis results; Analyze fire equipment data and monitor equipment operating status; Identify data anomalies through thresholds and rules, indicating potential equipment failure or fire risks; Generate decision support information and provide action recommendations to fire management personnel; When high risk is detected, generate and send warning information to the warning module; Conduct in-depth analysis of abnormal equipment data and diagnose the cause of the failure; Generate analysis reports including risk assessment and equipment status; Send analysis results and feedback back to the central monitoring module for system adjustment and optimization; Continuously optimize machine learning models using new data to improve risk assessment accuracy; Ensure that operators receive analysis results and warning information in real time through the user interface.

7. The AFIS intelligent fire monitoring system based on Internet of Things technology according to claim 6 is characterized in that: The data analysis module uses statistical and machine learning algorithms to analyze data in real time and identify risk patterns and trends. The specific steps are as follows: Select the extracted features related to fire risk, including smoke density, temperature change rate and combustible gas concentration, construct derived features, and enhance the prediction ability of the model through mathematical transformation; Select the corresponding algorithm based on data characteristics and business needs, use historical data to train the model, and optimize the model parameters through continuous iteration; Apply stream processing technology to process real-time data; Feed real-time data into the model to perform predictive analysis of fire risk, using machine learning models to identify patterns and trends in the data; Based on the model output, the probability and risk level of fire occurrence are evaluated, the data change trend is analyzed, and the development direction of fire risk is predicted; Set the risk assessment threshold. When the prediction result exceeds the threshold, identify it as an abnormal situation, convert the analysis result into an easy-to-understand format, and visualize it on the user interface; Let the model continue to learn based on the latest data to adapt to environmental changes and improve prediction accuracy.

8. The AFIS intelligent fire monitoring system based on Internet of Things technology according to claim 1 is characterized in that: The specific operation steps of the early warning module for judging the fire risk analyzed in the data analysis module and requiring fire early warning are as follows: Receive the fire risk assessment results from the data analysis module, judge the fire risk level based on the risk assessment provided by the data analysis module, and determine whether an early warning needs to be issued; Set thresholds for different risk levels. When the assessment results exceed the preset thresholds, the early warning program will be automatically initiated. When a high risk is identified, generate warning information, including warning type, risk level, affected area and recommended response measures; Send early warning information to relevant personnel or systems through different communication channels; Automatically trigger emergency response measures in high-risk fire situations, including activating sprinkler systems and closing fire doors; Real-time updates to the user interface ensure that operators view the latest warning information and system status, and record all warning events and corresponding response measures for future auditing and troubleshooting; Establish a feedback mechanism to collect on-site feedback information after early warning to evaluate the accuracy and effectiveness of the early warning system. Based on the feedback information and actual fire conditions, continuously optimize the early warning parameters and thresholds to improve the intelligence level of the early warning system.

9. The AFIS intelligent fire monitoring system based on Internet of Things technology according to claim 1 is characterized in that: The specific operation steps of the fault diagnosis module for early warning of the abnormal fire-fighting equipment analyzed by the data analysis module are as follows: Receive fire equipment status data provided by the data analysis module; Analyze data to identify deviations based on preset thresholds of normal operation; Apply machine learning or deep learning techniques to classify abnormal data and identify failure modes; Determine the exact location of the fault, analyze the cause of the fault by comprehensively analyzing historical data, usage and environmental factors; Generate early warning information based on fault type and severity; Through the central monitoring module, the warning information is sent to relevant personnel or systems; Assess the risk of equipment failure when no failure mode is identified.

10. The AFIS intelligent fire monitoring system based on Internet of Things technology according to claim 9 is characterized in that: When the fault diagnosis module does not identify the fault mode, the process of evaluating the equipment failure risk is as follows: Comprehensive analysis is performed by collecting risk parameters of fire-fighting equipment, including equipment time, maintenance times, operating hours, load changes and environmental factors. Load changes are obtained by collecting load changes of equipment in different time periods, and calculating the load through the variance calculation formula to obtain a negative rating. This negative rating is used as a standard to measure equipment load changes. The greater the negative rating, the greater the equipment load change. Environmental factors collect humidity, oxygen concentration and corrosive gas concentration indicators around the equipment, and then calculate the difference with the preset standard humidity, standard oxygen concentration and standard corrosive gas concentration. If it does not exceed the standard, it is recorded as 0, and the humidity difference, oxygen difference and corrosive difference are obtained respectively. After normalization, they are multiplied by the preset weight coefficient and summed to obtain the environmental impact assessment value; The equipment time, maintenance times, operating hours, negative evaluation values ​​and environmental impact assessment values ​​are converted into a unified dimension and range, that is, between 0 and 10, and calibrated as ss, cw, yt, fp and ph respectively, and then substituted into the following formula: ZPZ = [1.2 (ss * χ1 + cw * χ2) + yt * χ3 + fp * χ4] 0.94 *(1-ph -1 ) to obtain the comprehensive evaluation value ZPZ, where χ1, χ2, χ3, and χ4 are the preset weight coefficients of equipment time, maintenance times, operating time, and negative evaluation value respectively; The obtained comprehensive evaluation value is compared with the preset comprehensive evaluation threshold. When the comprehensive evaluation value is greater than the comprehensive evaluation threshold, it is judged that the risk of failure of the fire-fighting equipment has reached the standard, and advance maintenance planning is carried out to avoid maintenance of the fire-fighting equipment when a failure occurs.

Images