Intelligent early warning system and method for fire-fighting fan

Abstract

The intelligent early warning system comprises an intelligent measurement and control terminal which is used for integrally regulating and controlling the operation condition of equipment; an Internet of Things module; the Internet of Things module comprises an equipment remote control module, a fire-fighting center linkage module and a fireproof valve execution machine; the data acquisition module is used for acquiring real-time data; the data acquisition module comprises a metering data acquisition module, a measurement data acquisition module and an equipment operation state acquisition module; the data processing calculation module is used for calculating the data acquired by the data acquisition module to judge true and false information of the multiple data; the data storage module is used for circularly storing the data calculated by the data processing calculation module; the post-processing module is used for post-processing the data output by the data storage module and feeding back the data to the intelligent measurement and control terminal; the post-processing module comprises an energy consumption analysis module and an alarm management module.

Description

Technical Field

[0001] This invention relates to the field of fire early warning and control system technology, and in particular to an intelligent early warning system and method for fire-fighting fans. Background Technology

[0002] With the rapid development of urban modernization, smart cities and smart fire protection have been elevated to the level of a strong nation, requiring the comprehensive construction of urban Internet of Things fire remote monitoring systems in my country to comprehensively improve the technological, information-based, and intelligent level of fire protection work, and to realize the transformation and upgrading of fire prevention and control work under information conditions, shifting from traditional fire protection to modern fire protection.

[0003] A typical intelligent smoke control system includes an intelligent smoke control controller, various controlled devices, and sensors. Sensors detect environmental parameters, while controlled devices implement fire prevention, smoke control, and smoke extraction measures automatically or manually to minimize fire damage and casualties during a fire. The intelligent smoke control controller receives fire alarm commands from the higher-level controller, sends commands to the lower-level controlled devices, and coordinates the operation of related equipment. It provides feedback on the device's operational status and physical location and can monitor various parameters of the controlled devices in real time to determine if they are operating normally. Traditional fire-fighting smoke exhaust fan control systems have a relatively low level of intelligence, cannot be remotely controlled, cannot achieve efficient and energy-saving operation, and have poor fire warning capabilities, making them prone to false alarms or missed alarms. Summary of the Invention

[0004] The purpose of this invention is to solve the problem of intelligent fire early warning for fire-fighting fans, and to provide an intelligent early warning system and method for fire-fighting fans.

[0005] Firstly, a smart early warning system for fire-fighting fans is provided, including: Intelligent monitoring and control terminal, used for overall control of equipment operation status; Internet of Things (IoT) module; used for remote control and linkage of devices; The data acquisition module is used to collect real-time data; The data processing and calculation module is used to calculate and determine the authenticity of multiple data sources based on the data collected by the data acquisition module. The data storage module is used to cyclically store the data processed by the data processing and calculation module. The post-processing module is used to post-process the data output from the data storage module and feed it back to the intelligent measurement and control terminal.

[0006] Furthermore, the data acquisition module includes a metering data acquisition module, a measurement data acquisition module, and an equipment operation status acquisition module; the metering data acquisition module is used to acquire real-time operational data; the measurement data acquisition module is used to acquire real-time measurement data; and the equipment operation status acquisition module is used to acquire the real-time operation status of the fan.

[0007] Furthermore, the metering data acquisition module includes a power metering device for real-time monitoring of the wind turbine's power output.

[0008] Furthermore, the IoT module includes a remote equipment control module, a fire control center linkage module, and a fire damper actuator; the remote equipment control module is used to remotely regulate the fan; the fire control center linkage module is used to link with the fire control center in real time; and the fire damper actuator is used to control and monitor the operating status of the fire damper.

[0009] Furthermore, the post-processing module includes an energy consumption analysis module and an alarm management module; the energy consumption analysis module is used to perform real-time analysis and control of the fan energy consumption; the alarm management module is used to provide real-time fire alarms.

[0010] Furthermore, the measurement data acquisition module includes a differential pressure transmitter, a noise sensor, a temperature transmitter, an atmospheric temperature transmitter, and a humidity transmitter.

[0011] Furthermore, the equipment operation status acquisition module includes a speed sensor and a signal feedback sensor for the fire damper actuator.

[0012] Secondly, a method for intelligent early warning of fire-fighting fans is provided, including the following steps: S1: Collect and judge the following data: noise A, dynamic pressure B, temperature C, total pressure D, humidity E, fan air volume I, electrical power J, and fire damper open / closed status K; Collect and correct the following data: fan efficiency H, power consumption U, and atmospheric temperature G; And set the corresponding initial thresholds for the judgment data and the error correction data respectively; S2: Establish a three-level decision-making model S21: Primary Verification Mechanism S211: Read key parameters: temperature C, humidity E, noise A, and power J; S212: Real-time monitoring of key parameters; triggering a secondary verification mechanism when any key parameter exceeds the threshold. S22: Secondary verification mechanism Read other key parameters from S212 for cross-validation; S23: Three-level verification mechanism S231: After the cross-validation of the parameters in S22 is passed, read the open / closed status K of the fire damper for further verification and judgment. S232: After the verification judgment in S231 is passed, read the fan air volume I, dynamic pressure B and total pressure D to perform multi-parameter coupling analysis and determine the fire characteristics; S3: Establish an error correction mechanism After the multi-parameter coupling analysis in S232 is passed, the error correction data in S1 is used to investigate false alarms and further determine the fire warning. S4: Final Decision Once the S2 Level 3 decision model is validated and the error correction mechanism fails to eliminate the anomaly, it is determined to be a fire warning. S5: Early Warning Output Based on the judgment result, different levels of alarms are output; S6: Dynamic threshold adjustment The data processing and calculation module learns from historical normal data and dynamically adjusts the threshold.

[0013] Furthermore, the cross-validation methods in S22 include: When any two of the following data points are simultaneously abnormal: temperature C rises briefly, noise A shows abnormal data, electrical power J increases abnormally without instruction, and humidity E drops rapidly for a short period of time, the verification passes and the three-level verification mechanism is triggered.

[0014] Furthermore, the verification and judgment of the fire damper's open / closed status K in S231 includes: When the fire damper is normally closed in state K, it is judged as a equipment malfunction, and the fire alarm is not triggered, but the equipment maintenance alarm is triggered. When the fire damper is in the open position K, it is determined that the review has passed and the fire warning is confirmed. When the fire damper K is abnormally closed under abnormal conditions, it is judged as a successful review and a fire warning is confirmed. Furthermore, the error correction mechanism in S3 includes: When the wind turbine efficiency H is lower than the preset threshold, an equipment fault alarm is triggered, and the warning output level is reduced. When the power consumption U does not fluctuate abnormally, but the power J increases abnormally, the equipment fault alarm is triggered, and the warning output level is reduced. When atmospheric temperature G and temperature C increase simultaneously, the warning output level is reduced, triggering an environmental factor alarm, which in turn reduces the warning output level.

[0015] Furthermore, the S6 warning output includes: When the primary verification mechanism is triggered, the alarm management module outputs a level one warning, records the log, and continuously monitors the system. When the secondary verification mechanism is triggered, the alarm management module outputs a secondary warning and issues a warning notification to relevant personnel. When the three-level verification mechanism is triggered, the alarm management module outputs a three-level warning, confirms the fire, links the fire protection system, and initiates the emergency procedure. When the error correction mechanism is triggered, the alarm management module lowers the warning output level and outputs equipment fault alarms or environmental factor alarms.

[0016] Furthermore, the multi-parameter coupling analysis in S232 includes: If the fan air volume I increases abnormally for a short period of time without instruction, and the fire damper K is closed, it is determined that the valve is faulty or that a fire caused the valve to open abnormally. The dynamic pressure B and total pressure D parameters are then read. If the dynamic pressure B and total pressure D fluctuate drastically and the temperature C is abnormal, then the fire characteristics are determined.

[0017] The beneficial effects of this invention are: By setting up a three-level decision model, cross-validation of equipment is achieved, improving the accuracy of fire early warning judgment. At the same time, through an error correction mechanism, fire data is checked using external data, further reducing the probability of false fire judgment. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the present invention; Figure 2 This is a schematic diagram of the module of the present invention. Detailed Implementation

[0019] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0020] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0021] Example 1 like Figures 1-2 As shown: A smart early warning system for fire-fighting fans, including Intelligent monitoring and control terminal, used for overall control of equipment operation status; Internet of Things (IoT) module; used for remote control and linkage of devices; The data acquisition module is used to collect real-time data; The data processing and calculation module is used to calculate and determine the authenticity of multiple data sources based on the data collected by the data acquisition module. The data storage module is used to cyclically store the data processed by the data processing and calculation module. In this solution, the data storage module upgrades the traditional fixed threshold to a probabilistic dynamic model. A Bayesian network is used to establish conditional probability relationships between parameters (e.g., the probability of a decrease in humidity due to an increase in temperature is 80%), and historical data is combined to calculate the outlier confidence level of each parameter in real time.

[0022] Workflow: Building network topology: Key parameters include: temperature (°C), humidity (°C), noise (A), and electrical power (J). Edge weights: Conditional probabilities trained based on 100,000 sets of historical data (e.g., P(humidity↓|temperature↑)=0.92). Real-time inference: When the temperature rises sharply, the system calculates the probability deviation of a decrease in the current humidity: If the actual humidity decrease is greater than the Bayesian predicted value + 3σ, then trigger secondary verification. Dynamic threshold adjustment: The base temperature threshold is automatically increased by 2℃ in summer (ambient temperature compensation). Nighttime noise threshold improved by 5dB (background noise compensation) When the oil pan catches fire, the humidity drop far exceeds the Bayesian prediction (actual drop of 17% vs. predicted drop of 9%), significantly improving the reliability of secondary verification and avoiding false triggering caused by environmental interference.

[0023] The post-processing module is used to post-process the data output from the data storage module and feed it back to the intelligent measurement and control terminal.

[0024] Furthermore, the data acquisition module includes a metering data acquisition module, a measurement data acquisition module, and an equipment operation status acquisition module; the metering data acquisition module is used to acquire real-time operational data; the measurement data acquisition module is used to acquire real-time measurement data; and the equipment operation status acquisition module is used to acquire the real-time operation status of the fan.

[0025] Furthermore, the metering data acquisition module includes a power metering device for real-time monitoring of the wind turbine's power output.

[0026] Furthermore, the IoT module includes a remote equipment control module, a fire control center linkage module, and a fire damper actuator; the remote equipment control module is used to remotely regulate the fan; the fire control center linkage module is used to link with the fire control center in real time; and the fire damper actuator is used to control and monitor the operating status of the fire damper.

[0027] Furthermore, the post-processing module includes an energy consumption analysis module and an alarm management module; the energy consumption analysis module is used to perform real-time analysis and control of the fan energy consumption; the alarm management module is used to provide real-time fire alarms.

[0028] Furthermore, the measurement data acquisition module includes a differential pressure transmitter, a noise sensor, a temperature transmitter, an atmospheric temperature transmitter, and a humidity transmitter.

[0029] Furthermore, the equipment operation status acquisition module includes a speed sensor and a signal feedback sensor for the fire damper actuator.

[0030] Example 2 A method for intelligent early warning of fire-fighting fans includes the following steps: S1: Collect and judge the following data: noise A, dynamic pressure B, temperature C, total pressure D, humidity E, fan air volume I, electrical power J, and fire damper open / closed status K; Collect and correct the following data: fan efficiency H, power consumption U, and atmospheric temperature G; And set the corresponding initial thresholds for the judgment data and the error correction data respectively; S2: Establish a three-level decision-making model S21: Primary Verification Mechanism S211: Read key parameters: temperature C, humidity E, noise A, and power J; S212: Real-time monitoring of key parameters; triggering a secondary verification mechanism when any key parameter exceeds the threshold. S22: Secondary verification mechanism Read other key parameters from S212 for cross-validation; S23: Three-level verification mechanism S231: After the cross-validation of the parameters in S22 is passed, read the open / closed status K of the fire damper for further verification and judgment. S232: After the verification judgment in S231 is passed, the fan air volume I, dynamic pressure B and total pressure D are read to perform multi-parameter coupling analysis and determine the fire characteristics; S3: Establish an error correction mechanism After the multi-parameter coupling analysis in S232 is passed, the error correction data in S1 is used to investigate false alarms and further determine the fire warning. S4: Final Decision Once the S2 Level 3 decision model is validated and the error correction mechanism fails to eliminate the anomaly, it is determined to be a fire warning. S5: Early Warning Output Based on the judgment result, different levels of alarms are output; S6: Dynamic threshold adjustment The data processing and calculation module learns from historical normal data and dynamically adjusts the threshold.

[0031] Furthermore, the cross-validation method in S22 includes the following: when any two of the following data are abnormal at the same time, the validation passes and the three-level validation mechanism is triggered: temperature C rises for a short time, noise A shows abnormal data, electrical power J increases abnormally without instructions, and humidity E drops rapidly for a short time.

[0032] Furthermore, the verification judgment of the fire damper opening and closing status K in S231 includes determining that when the fire damper opening and closing status K is normally closed, it is a faulty equipment and will not trigger a fire alarm, but will trigger an equipment maintenance alarm. When the fire damper is in the open position K, it is determined that the review has passed and the fire warning is confirmed. When the fire damper K is abnormally closed under abnormal conditions, it is judged as a successful review and a fire warning is confirmed. Furthermore, the error correction mechanism in S3 includes When the wind turbine efficiency H is lower than the preset threshold, an equipment fault alarm is triggered, and the warning output level is reduced. When the power consumption U does not fluctuate abnormally, but the power J increases abnormally, the equipment fault alarm is triggered, and the warning output level is reduced. When atmospheric temperature G and temperature C increase simultaneously, the warning output level is reduced, triggering an environmental factor alarm, which in turn reduces the warning output level.

[0033] Furthermore, the S6 warning output includes When the primary verification mechanism is triggered, the alarm management module outputs a level one warning, records the log, and continuously monitors the system. When the secondary verification mechanism is triggered, the alarm management module outputs a secondary warning and issues a warning notification to relevant personnel. When the three-level verification mechanism is triggered, the alarm management module outputs a three-level warning, confirms the fire, links the fire protection system, and initiates the emergency procedure. When the error correction mechanism is triggered, the alarm management module lowers the warning output level and outputs equipment fault alarms or environmental factor alarms.

[0034] Furthermore, the multi-parameter coupling analysis in S232 includes... If the fan air volume I increases abnormally for a short period of time without instruction, and the fire damper K is closed, it is determined that the valve is faulty or that a fire caused the valve to open abnormally. The dynamic pressure B and total pressure D parameters are then read. If the dynamic pressure B and total pressure D fluctuate drastically and the temperature C is abnormal, then the fire characteristics are determined.

[0035] Furthermore, in this solution, a confidence assessment model can be constructed by introducing DS evidence theory to address sensor conflict scenarios (such as abnormal fire damper signals but normal temperature) and quantify the credibility weight of each data source.

[0036] Workflow: Trustworthiness assignment (based on historical device failure rate): Initial confidence level of sensor type Fire damper status K 0.95 Temperature sensor C 0.90 Current harmonic detection* 0.85 (*New design) Conflict detection: When a fire damper reports "abnormal closure" but the temperature does not exceed the threshold, calculate the conflict factor: CONFLICT = 1 - [m1(K)⊕m2(C)] Decision restructuring: If CONFLICT > 0.7, initiate current harmonic analysis: Fire current: harmonic components are concentrated in 2-5kHz Motor fault current: harmonic components > 10kHz This solution enables the system to quickly pinpoint equipment malfunction (rather than fire) when abnormal electrical power is detected due to bearing aging and the high-order harmonics (12kHz) conflict with temperature data, reducing the false alarm rate by 83%. Furthermore, this solution can also employ a new abnormal propagation path tracking function, which uses timestamp alignment and spatial topology analysis to distinguish between fires and local equipment failures.

[0037] Hardware support: Deploy pressure wave sensors (sampling rate 1kHz) in the wind turbine duct network. Add ±10ms high-precision clock synchronization to each sensor Workflow: Establish a propagation model: Fire characteristics: Increased temperature → fluctuating wind pressure → increased noise (propagation path: A→B→C) Bearing failure: Increased noise → Current harmonics → Slight temperature rise (Path: C→B→A) Time series analysis: Extract the time difference Δt between the first and last nodes of the event chain. If Δt < 50ms and matches the fire path sequence, a Level 3 warning is triggered. Spatial positioning: The coordinates of the anomaly source were calculated using the time difference of arrival of the pressure wave (error < 0.5m). This solution can assume that the system detects a temperature rise (t=0ms) → wind pressure fluctuation (t=32ms) → increased noise (t=41ms), which conforms to the fire propagation sequence, and confirm that the fire source is located below the smoke hood in the catering area within 8 seconds.

[0038] Example 3 Scene: Oil pan catches fire in the dining area When the oil pan in the catering area caught fire, the system detected a sudden increase in temperature C from 25℃ to 58℃, a rapid drop in humidity E from 45% to 28%, an abnormal closure of the fire damper K due to high-temperature melting, and a sudden increase in fan airflow I from 3000m³ / h to 4200m³ / h. Within 2 seconds, the system triggered primary verification due to the sudden temperature increase, and within 5 seconds, completed secondary cross-verification through the combination of abnormal temperature and humidity. Subsequently, the abnormal closure of the fire damper triggered tertiary verification. Multi-parameter coupling analysis showed a sudden increase in airflow and dynamic pressure fluctuations exceeding 50%, confirming the fire characteristics in conjunction with the abnormal temperature. The error correction mechanism detected a fan efficiency of H=75% (normal) and ruled out false alarms. Within 8 seconds, a level 3 warning was issued, and the smoke extraction and sprinkler systems were activated for fire suppression.

[0039] Example 4 Scenario: Abnormal noise caused by aging fan bearings When the wind turbine bearings aged, noise level A increased from 85dB to 102dB (including high-frequency components), electrical power J increased from 15kW to 18kW without instruction, and wind turbine efficiency H plummeted from 68% to 43%. The primary verification triggered secondary verification due to noise exceeding the threshold; the combination of abnormal noise and power passed cross-verification. Before the tertiary verification, the error correction mechanism detected wind turbine efficiency H=43% (below the 50% threshold), determined it as an equipment failure, and dynamically downgraded to a secondary warning (equipment maintenance notification), guiding maintenance personnel to inspect the bearings and successfully preventing a false fire alarm.

[0040] The embodiments described above are merely illustrative of specific implementations of the present invention, and while the descriptions are detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention.

Claims

1. A fire-fighting fan intelligent early warning system, characterized in that, include: Intelligent monitoring and control terminal, used for overall control of equipment operation status; Internet of Things (IoT) module; Used for remote linkage and control of equipment; The data acquisition module is used to collect real-time data; The data processing and calculation module is used to calculate and determine the authenticity of multiple data sources based on the data collected by the data acquisition module. The data storage module is used to cyclically store the data processed by the data processing and calculation module. The post-processing module is used to post-process the data output from the data storage module and feed it back to the intelligent measurement and control terminal.

2. The intelligent early warning system for fire-fighting fans according to claim 1, characterized in that: The data acquisition module includes a metering data acquisition module, a measurement data acquisition module, and an equipment operation status acquisition module; the metering data acquisition module is used to acquire real-time operational data; the measurement data acquisition module is used to acquire real-time measurement data; and the equipment operation status acquisition module is used to acquire the real-time operation status of the fan.

3. The intelligent early warning system for fire-fighting fans according to claim 2, characterized in that: The metering data acquisition module includes a power metering device for real-time monitoring of the wind turbine's power output.

4. The intelligent early warning system for fire-fighting fans according to claim 1, characterized in that: The IoT module includes a remote equipment control module, a fire control center linkage module, and a fire damper actuator; the remote equipment control module is used to remotely regulate the fan; the fire control center linkage module is used to link with the fire control center in real time; and the fire damper actuator is used to control and monitor the operating status of the fire damper.

5. The intelligent early warning system for fire-fighting fans according to claim 1, characterized in that: The post-processing module includes an energy consumption analysis module and an alarm management module; the energy consumption analysis module is used to perform real-time analysis and control of the fan energy consumption; the alarm management module is used to provide real-time fire alarms.

6. The intelligent early warning system for fire-fighting fans according to claim 2, characterized in that: The measurement data acquisition module includes a differential pressure transmitter, a noise sensor, a temperature transmitter, an atmospheric temperature transmitter, and a humidity transmitter.

7. The intelligent early warning system for fire-fighting fans according to claim 2, characterized in that: The equipment operation status acquisition module includes a speed sensor and a signal feedback sensor for the fire damper actuator.

8. A method for intelligent early warning of fire-fighting fans, characterized in that, A fire-fighting fan intelligent early warning system according to any one of claims 1 to 7 includes the following steps: S1: Collect and judge the following data: noise A, dynamic pressure B, temperature C, total pressure D, humidity E, fan air volume I, electrical power J, and fire damper open / closed status K; Collect and correct the following data: fan efficiency H, power consumption U, and atmospheric temperature G; And set the corresponding initial thresholds for the judgment data and the error correction data respectively; S2: Establish a three-level decision-making model S21: Primary Verification Mechanism S211: Read key parameters: temperature C, humidity E, noise A, and power J; S212: Real-time monitoring of key parameters; triggering a secondary verification mechanism when any key parameter exceeds the threshold. S22: Secondary verification mechanism Read other key parameters from S212 for cross-validation; S23: Three-level verification mechanism S231: After the cross-validation of the parameters in S22 is passed, read the open / closed status K of the fire damper for further verification and judgment. S232: After the verification judgment in S231 is passed, read the fan air volume I, dynamic pressure B and total pressure D to perform multi-parameter coupling analysis and determine the fire characteristics; S3: Establish an error correction mechanism After the multi-parameter coupling analysis in S232 is passed, the error correction data in S1 is used to investigate false alarms and further determine the fire warning. S4: Final Decision Once the S2 Level 3 decision model is validated and the error correction mechanism fails to eliminate the anomaly, it is determined to be a fire warning. S5: Early Warning Output Based on the judgment result, different levels of alarms are output; S6: Dynamic threshold adjustment The data processing and calculation module learns from historical normal data and dynamically adjusts the threshold.

9. The intelligent early warning method for fire-fighting fans according to claim 8, characterized in that: The cross-validation methods in S22 include: When any two of the following data points are simultaneously abnormal: temperature C rises briefly, noise A shows abnormal data, electrical power J increases abnormally without instruction, and humidity E drops rapidly for a short period of time, the verification passes and the three-level verification mechanism is triggered.

10. The intelligent early warning method for fire-fighting fans according to claim 8, characterized in that: The verification and judgment of the open / closed status K of the fire damper in S231 includes: When the fire damper is normally closed in state K, it is judged as a equipment malfunction, and the fire alarm is not triggered, but the equipment maintenance alarm is triggered. When the fire damper is in the open position K, it is determined that the review has passed and the fire warning is confirmed. When the fire damper K is abnormally closed under abnormal conditions, it is judged as a successful review and a fire warning is confirmed.

11. The intelligent early warning method for fire-fighting fans according to claim 8, characterized in that: The error correction mechanism in S3 includes: When the wind turbine efficiency H is lower than the preset threshold, an equipment fault alarm is triggered, and the warning output level is reduced. When the power consumption U does not fluctuate abnormally, but the power J increases abnormally, the equipment fault alarm is triggered, and the warning output level is reduced. When atmospheric temperature G and temperature C increase simultaneously, the warning output level is reduced, triggering an environmental factor alarm, which in turn reduces the warning output level.

12. The intelligent early warning method for fire-fighting fans according to claim 8, characterized in that: S6 warning outputs include: When the primary verification mechanism is triggered, the alarm management module outputs a level one warning, records the log, and continuously monitors the system. When the secondary verification mechanism is triggered, the alarm management module outputs a secondary warning and issues a warning notification to relevant personnel. When the three-level verification mechanism is triggered, the alarm management module outputs a three-level warning, confirms the fire, links the fire protection system, and initiates the emergency procedure. When the error correction mechanism is triggered, the alarm management module lowers the warning output level and outputs equipment fault alarms or environmental factor alarms.

13. The intelligent early warning method for fire-fighting fans according to claim 8, characterized in that: The multi-parameter coupling analysis in S232 includes: If the fan air volume I increases abnormally for a short period of time without instruction, and the fire damper K is closed, it is determined that the valve is faulty or that a fire caused the valve to open abnormally. The dynamic pressure B and total pressure D parameters are then read. If the dynamic pressure B and total pressure D fluctuate drastically and the temperature C is abnormal, then the fire characteristics are determined.

Images