Hydropower station unit fire alarm auxiliary decision-making management system

Abstract

The invention discloses a hydropower station unit fire alarm auxiliary decision-making management system, which relates to the technical field of power equipment safety and comprises a fire data acquisition module, a fire data analysis module, a fire alarm module, a linkage control module and a system management module. And the fire data acquisition module is used for acquiring fire related parameter data in a hydropower station unit area in real time, wherein the fire related parameter data comprises smoke concentration, temperature change rate, flame characteristics and carbon monoxide concentration. By adopting multiple types of sensor units, a smoke sensor, a temperature sensor, a flame sensor, a carbon monoxide sensor and the like are covered for combined acquisition, compared with the condition that the types of sensors of an existing system are limited, multi-dimensional fire related data can be comprehensively and accurately acquired, deep analysis is performed on the acquired data by means of an intelligent algorithm, and the accuracy of the system is improved. The historical data and the real-time data are compared, the false alarm probability is reduced, and the alarm accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment safety, and in particular to a fire alarm auxiliary decision-making management system for hydropower station units. Background Art

[0002] As the core equipment for hydropower generation, hydropower station units undertake the critical task of converting water energy into electricity. They operate in a complex environment, housing a large number of electrical equipment, lubricating oil systems, and densely packed cabling. Long-term, high-load operation of electrical equipment can lead to fires due to insulation aging, short circuits, and other issues. Leaks in the lubricating oil system can also easily catch fire when exposed to high temperatures or open flames. Overloads and short circuits in cable lines are also significant fire hazards. A fire, if it occurs, would not only severely damage the hydropower station units themselves, leading to power outages, but could also trigger a chain reaction, endangering the safety of the entire hydropower station and causing significant economic losses and social impacts. While fire alarm systems for hydropower plant units are currently in use, they suffer from numerous shortcomings. Regarding fire data collection, existing systems utilize a limited range of sensors, often relying on only a few common sensors. These systems are unable to comprehensively and accurately capture multi-dimensional fire-related parameters such as smoke concentration, temperature change rate, flame characteristics, and carbon monoxide concentration. This results in insufficient detection of early signs of fire, which can easily lead to delayed alarms. Furthermore, existing fire alarm systems employ relatively simple alarm methods, typically relying solely on audible and visual alarms, making it difficult to ensure timely and effective notification of personnel in the noisy environment of a hydropower plant. Furthermore, the alarm levels are not sufficiently detailed, making it impossible to implement differentiated alarm strategies based on varying degrees of fire risk. Summary of the Invention

[0003] In order to solve the above technical problems, a hydropower station unit fire alarm auxiliary decision-making management system is provided. This technical solution solves the above problems.

[0004] In order to achieve the above objects, the technical solution adopted by the present invention is: A fire alarm auxiliary decision-making management system for hydropower station units, comprising: Fire data acquisition module, fire data analysis module, fire alarm module, linkage control module and system management module; The fire data acquisition module is used to collect fire-related parameter data in the hydropower station unit area in real time, including smoke concentration, temperature change rate, flame characteristics and carbon monoxide concentration; The fire data analysis module is electrically connected to the fire data acquisition module, and is used to perform preprocessing, feature extraction and data fusion on the collected fire data to generate an analysis data set that meets the fire alarm requirements; The fire alarm module is electrically connected to the fire data analysis module, and is used to output alarm information related to the current fire situation based on the analysis results, and adopt corresponding alarm methods according to different alarm levels; The linkage control module is electrically connected to the fire alarm module, and the linkage control module is used to trigger the corresponding fire fighting equipment linkage according to the alarm information; The system management module is used to configure, monitor, maintain and manage the entire fire alarm system.

[0005] Preferably, the fire data acquisition module includes: A multi-type sensor unit, which is used for different types of fire sensors, including smoke sensors, temperature sensors, flame sensors, and carbon monoxide sensors, for combined acquisition; A high-speed data transmission unit is used to quickly transmit the collected real-time fire data to the fire data analysis module.

[0006] Preferably, the fire data analysis module includes: A data screening unit, which is used to remove noise data and erroneous data and perform preliminary screening on the data; A feature extraction unit, configured to extract fire-related feature parameters from data collected by different sensors; The data fusion algorithm unit is used to fuse the data collected by different sensors and improve the accuracy of the data through the adaptive weighted fusion algorithm. Assume that the fluctuation coefficient of each sensor data is , calculated based on the standard deviation of the data over a period of time, and taking into account the importance coefficient of the sensor , then the fused data The formula is:

[0007] Where, represents the fused data, For the Data collected by sensors; A data standardization unit, configured to convert the processed data into a unified standard format; The intelligent analysis unit uses a self-learning algorithm to conduct in-depth analysis of fire data, compare historical data with real-time data, and calculate the false alarm risk value. The formula for the false alarm risk value is:

[0008] in, Indicates the false alarm risk value, the larger the value, the higher the possibility of false alarm; is the number of fire-related parameters; It is Fire parameter values ​​collected in real time; It is the first The mean of the parameters; It is the first The standard deviation of the parameters; It is The weight of a parameter reflects the importance of the parameter to the false alarm judgment, and .

[0009] Preferably, the fire alarm module includes: a fire risk assessment unit, which is used to perform risk assessment based on different fire-related parameters, including smoke concentration, temperature change rate, and preset fire thresholds, classify the risk levels corresponding to different fire conditions into different levels, and generate a fire risk level report; Among them, the changing rate of fire-related parameters is considered , and the degree of deviation of this parameter from the normal state , the fire risk assessment formula is:

[0010] Where, Indicates the comprehensive fire risk level, For the The risk level corresponding to each fire-related parameter, For the The weight of the parameters; An alarm signal generating unit, which is used to generate alarm signals of different levels according to the risk level. The alarm signals may include sound and light alarms, SMS notifications, and in-station broadcasts; The decision suggestion generation unit generates decision suggestions for responding to fires based on risk levels and on-site data.

[0011] Preferably, the fire risk assessment unit further comprises: a smoke assessment unit, the smoke assessment unit being used to assess the impact of changes in smoke concentration on fire risk and generate a smoke risk level; a temperature assessment unit, the temperature assessment unit being used to assess the impact of the temperature change rate on the fire risk and generate a temperature risk level; a flame assessment unit, the flame assessment unit being used to assess the impact of flame characteristics on fire risk and generate a flame risk level; a carbon monoxide assessment unit, the carbon monoxide assessment unit being used to assess the impact of carbon monoxide concentration on fire risk and generate a carbon monoxide risk level; The comprehensive risk determination unit is used to perform weighted synthesis on the risk levels generated by different assessment units to generate a final fire risk level.

[0012] Preferably, the linkage control module includes: A fire protection equipment linkage strategy unit, which formulates corresponding fire protection equipment linkage strategies based on different fire risk levels and the layout of hydropower station units, including activating different fire extinguishing devices in response to fires in different areas; The device control execution unit is used to send control instructions to corresponding fire-fighting equipment according to the linkage strategy to achieve linkage control of the equipment.

[0013] Preferably, the system management module includes: A system configuration unit, which is used to configure the parameters of the fire alarm system, including sensor sensitivity settings and alarm threshold adjustment; An operation monitoring unit, which is used to monitor the operation status of each module of the fire alarm system in real time, detect faults in a timely manner and issue an alarm; The maintenance management unit is used to perform daily maintenance and management of the system, including data backup and equipment maintenance reminders.

[0014] Preferably, the system is further optimized in real time through an intelligent self-learning algorithm to adapt to changes in different environments and fire conditions, specifically including: Automatically adjust fire thresholds based on historical fire data, real-time fire changes, and deep learning algorithms; Adaptively fuse the data collected by fire sensors and use a dynamic weighting algorithm to improve the reliability and accuracy of the data; A multi-level alarm mechanism based on hierarchical assessment uses fire risk assessment and data analysis to systematically determine the fire risk level, enabling accurate fire alarms. Automatically adjust linkage control strategies and alarm methods based on current fire conditions and historical data to improve fire response efficiency and reduce losses.

[0015] Preferably, the system further comprises: A big data storage and analysis platform, which is used to store large amounts of historical fire data and system operation data, and conduct in-depth data analysis to optimize fire risk assessment models and linkage control strategies; The user feedback and optimization module is used to collect feedback from hydropower station staff on fire alarm information and linkage control effects, and optimize and adjust the system based on the feedback information.

[0016] Preferably, the fire data analysis module is connected to an external fire monitoring system, obtains relevant data provided by the external fire monitoring through a secure data interface, and performs further analysis and processing.

[0017] Compared with existing technologies, the present invention offers the following advantages: by utilizing multiple sensor units, including smoke sensors, temperature sensors, flame sensors, and carbon monoxide sensors, the system can comprehensively and accurately acquire multi-dimensional fire-related data, while existing systems have limited sensor types. Furthermore, intelligent algorithms can be used to conduct in-depth analysis of the collected data, comparing historical data with real-time data. This reduces the probability of false alarms, improves alarm accuracy, and enhances the ability to detect early signs of fire. This effectively avoids alarm delays and buys valuable time for fire prevention and control.

[0018] In addition to traditional sound and light alarms, the alarm mechanism now includes text message notifications and in-station broadcasts. In the noisy environment of a hydropower station, these multiple alarm methods operate in parallel, ensuring that staff receive fire alarm information promptly and effectively. This improves the reliability and timeliness of alarm information transmission and ensures the efficient initiation of emergency response. Furthermore, through the fire risk assessment unit, a unique risk assessment formula is used to carefully classify fire risk levels, taking into account various fire-related parameters such as smoke concentration and temperature change rate, as well as preset fire thresholds. This allows for differentiated alarm strategies based on varying fire risk levels, enabling staff to quickly determine the severity of a fire and implement appropriate, precise response measures, thereby improving the pertinence and effectiveness of fire handling.

[0019] The linkage control module includes a fire protection equipment linkage strategy unit and an equipment control execution unit. This module can formulate targeted fire protection equipment linkage strategies based on different fire risk levels and the specific layout of the hydropower station units. It changes the existing system's mode of simply starting basic fire protection equipment. It can flexibly allocate fire protection resources according to actual conditions, give full play to the fire-fighting efficiency of fire protection equipment, minimize fire losses, and ensure the safe and stable operation of the hydropower station units and the entire hydropower station. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a system framework diagram of the present invention. DETAILED DESCRIPTION

[0021] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0022] Reference Figure 1 As shown, a fire alarm auxiliary decision-making management system for hydropower station units includes: Fire data acquisition module, fire data analysis module, fire alarm module, linkage control module and system management module; Fire data acquisition module: The fire data acquisition module is used to collect fire-related parameter data in the hydropower station unit area in real time, including smoke concentration, temperature change rate, flame characteristics and carbon monoxide concentration; Fire data analysis module: The fire data analysis module is electrically connected to the fire data acquisition module and is used to pre-process, extract features and fuse data on the collected fire data to generate an analysis data set that meets fire alarm requirements; Fire alarm module: The fire alarm module is electrically connected to the fire data analysis module. The fire alarm module is used to output alarm information related to the current fire situation based on the analysis results and take corresponding alarm methods according to different alarm levels; Linkage control module: The linkage control module is electrically connected to the fire alarm module and is used to trigger the linkage of corresponding fire-fighting equipment according to the alarm information; System management module: The system management module is used to configure, monitor and maintain the entire fire alarm system.

[0023] Specifically, the overall architecture of a fire alarm decision-making support management system for hydropower station units is defined. It consists of a fire data acquisition module, a fire data analysis module, a fire alarm module, a linkage control module, and a system management module. The fire data acquisition module is responsible for collecting key fire-related parameters within the hydropower station unit area in real time, such as smoke concentration, temperature change rate, flame characteristics, and carbon monoxide concentration. These parameters are important for determining the occurrence and development of a fire. The fire data analysis module is electrically connected to the acquisition module and preprocesses the collected data to remove impurities and outliers, extracting features closely related to the fire, and then integrating data from different sensors using data fusion technology to generate a high-quality analysis data set for the fire alarm module. Based on the results provided by the analysis module, the fire alarm module outputs alarm information that is tailored to the current fire situation and takes appropriate alarm actions based on different risk levels. Upon receiving the alarm information, the linkage control module rapidly triggers the linkage of relevant firefighting equipment, such as activating fire extinguishing devices and shutting down the ventilation system, to control the spread of the fire. The system management module is responsible for the configuration, operation monitoring, and maintenance of the entire system, ensuring stable and efficient operation. This modular system architecture design ensures clear division of labor and close coordination. Comprehensive data collection can promptly capture subtle changes in the early stages of a fire, giving fire prevention and control an advantage; the data analysis module improves data quality, laying the foundation for accurate alarms; diversified alarm methods ensure the effective transmission of alarm information; intelligent linkage control can quickly respond to and control fires, reducing losses; the system management module ensures the long-term stable operation of the system, and overall improves the reliability, accuracy and efficiency of the hydropower station unit fire alarm system.

[0024] The fire data acquisition module includes: A multi-type sensor unit, which is used for different types of fire sensors, including smoke sensors, temperature sensors, flame sensors, and carbon monoxide sensors, for combined acquisition; A high-speed data transmission unit is used to quickly transmit the collected real-time fire data to the fire data analysis module.

[0025] Specifically, the multi-type sensor unit combines smoke sensors, temperature sensors, flame sensors, and carbon monoxide sensors to collect fire-related data from multiple dimensions. Different types of sensors are sensitive to different fire characteristics. For example, smoke sensors detect changes in smoke concentration, temperature sensors monitor the rate of temperature change, flame sensors identify flame characteristics, and carbon monoxide sensors detect carbon monoxide concentration. They work together to comprehensively perceive signs of fire. The high-speed data transmission unit is responsible for quickly transmitting the collected real-time data to the fire data analysis module, ensuring the timeliness of the data and avoiding information lags caused by transmission delays. The combined collection of multiple types of sensors greatly improves the comprehensiveness and accuracy of fire data collection. Compared with a single or a few sensors, it can more accurately capture the complex early signs of a fire. High-speed data transmission ensures that data can be delivered to the analysis module in a timely manner, providing a guarantee for subsequent rapid analysis and alarm, reducing alarm delays caused by slow data transmission, and enhancing the system's timely response to fires.

[0026] The fire data analysis module includes: A data screening unit, which is used to remove noise data and erroneous data and perform preliminary screening on the data; A feature extraction unit, configured to extract fire-related feature parameters from data collected by different sensors; The data fusion algorithm unit is used to fuse the data collected by different sensors and improve the accuracy of the data through the adaptive weighted fusion algorithm. Assume that the fluctuation coefficient of each sensor data is , calculated based on the standard deviation of the data over a period of time, and taking into account the importance coefficient of the sensor , then the fused data The formula is:

[0027] Where, represents the fused data, For the Data collected by sensors; A data standardization unit is used to convert the processed data into a unified standard format.

[0028] Specifically, data screening and feature extraction improve data quality and fire signature recognition, providing strong support for accurate fire assessment. The adaptive weighted fusion algorithm fully accounts for data fluctuations and sensor importance, making the fused data more accurate and reliable. Compared to simpler data fusion methods, it can better reflect the true nature of fires. Data standardization facilitates data circulation and processing within the system, improving the efficiency and accuracy of the entire data analysis process, and providing a high-quality data foundation for subsequent fire risk assessment and alarming.

[0029] The intelligent analysis unit uses a self-learning algorithm to conduct in-depth analysis of fire data, compare historical data with real-time data, and calculate the false alarm risk value. The formula for the false alarm risk value is:

[0030] in, Indicates the false alarm risk value, the larger the value, the higher the possibility of false alarm; is the number of fire-related parameters; It is Fire parameter values ​​collected in real time; It is the first The mean of the parameters; It is the first The standard deviation of the parameters; It is The weight of a parameter reflects the importance of the parameter to the false alarm judgment, and .

[0031] Specifically, during operation, the system will continuously update the historical data sample library based on actual alarm conditions and feedback information, recalculate the mean, standard deviation and weight of the parameters, and achieve self-learning optimization, thereby continuously reducing the possibility of false alarms. For example, when the system collects real-time smoke concentration values ​​and temperature change rate values, the smoke concentration mean, standard deviation, and temperature change rate mean are obtained through historical data, and the smoke concentration weight and temperature change rate weight are determined, which can be substituted into the above formula to calculate the false alarm risk value.

[0032] The fire alarm module comprises: a fire risk assessment unit, which is used to perform risk assessment based on different fire-related parameters, including smoke concentration, temperature change rate, and preset fire thresholds, classify the risk levels corresponding to different fire conditions into different levels, and generate a fire risk level report; Among them, the changing rate of fire-related parameters is considered , and the degree of deviation of this parameter from the normal state , the fire risk assessment formula is:

[0033] Where, Indicates the comprehensive fire risk level, For the The risk level corresponding to each fire-related parameter, For the The weight of the parameters; An alarm signal generating unit, which is used to generate alarm signals of different levels according to the risk level. The alarm signals may include sound and light alarms, SMS notifications, and in-station broadcasts; The decision suggestion generation unit generates decision suggestions for responding to fires based on risk levels and on-site data.

[0034] Specifically, the risk assessment method that comprehensively considers multiple factors can more accurately reflect the true level of fire risk than judging based solely on fixed thresholds, providing a more reliable basis for subsequent alarms and responses. The diversified alarm signal generation method can ensure that staff receive alarm information in a timely manner in the noisy hydropower station environment. Multiple alarm forms are used in parallel, which improves the reliability and timeliness of alarm information transmission and enables staff to respond quickly.

[0035] The fire risk assessment unit further comprises: a smoke assessment unit, the smoke assessment unit being used to assess the impact of changes in smoke concentration on fire risk and generate a smoke risk level; a temperature assessment unit, the temperature assessment unit being used to assess the impact of the temperature change rate on the fire risk and generate a temperature risk level; a flame assessment unit, the flame assessment unit being used to assess the impact of flame characteristics on fire risk and generate a flame risk level; a carbon monoxide assessment unit, the carbon monoxide assessment unit being used to assess the impact of carbon monoxide concentration on fire risk and generate a carbon monoxide risk level; The comprehensive risk determination unit is used to perform weighted synthesis on the risk levels generated by different assessment units to generate a final fire risk level.

[0036] Specifically, the fire risk assessment unit is further refined into multiple subunits. The smoke assessment unit specifically assesses the impact of changes in smoke concentration on fire risk, determining the smoke risk level by analyzing factors such as the rate of smoke concentration increase and duration. The temperature assessment unit generates a temperature risk level based on the temperature change rate, taking into account the magnitude and speed of temperature increases or decreases. The flame assessment unit determines the flame risk level based on flame characteristics such as flame size, color, and flicker frequency. The carbon monoxide assessment unit generates a carbon monoxide risk level based on changes in carbon monoxide concentration and any excesses. The comprehensive risk assessment unit weights the risk levels generated by each subunit to determine the final fire risk level. This segmented assessment approach allows for a more precise assessment of risk from the perspective of different fire factors, avoiding misjudgments based on a single factor. By comprehensively considering risk levels from multiple dimensions, the final risk level derived through weighted synthesis more comprehensively and accurately reflects the actual fire risk level, providing a more precise basis for fire alarms and subsequent response measures, and facilitating the development of more effective fire prevention and control strategies.

[0037] The linkage control module includes: A fire protection equipment linkage strategy unit, which formulates corresponding fire protection equipment linkage strategies based on different fire risk levels and the layout of hydropower station units, including activating different fire extinguishing devices in response to fires in different areas; The device control execution unit is used to send control instructions to corresponding fire-fighting equipment according to the linkage strategy to achieve linkage control of the equipment.

[0038] Specifically, the fire-fighting equipment linkage strategy unit of the linkage control module formulates corresponding linkage strategies based on the fire risk level and the layout of the hydropower station units. For example, different fire-fighting devices are activated in different areas due to the different equipment types and importance. For example, carbon dioxide fire-fighting devices are used in areas where electrical equipment is concentrated, and foam fire-fighting devices are used in areas where oil equipment is concentrated. The equipment control execution unit sends control instructions to the corresponding fire-fighting equipment according to the linkage strategy to realize equipment linkage control and ensure that the fire-fighting equipment can play a role at the right time and place. Targeted linkage strategies can give full play to the effectiveness of fire-fighting equipment and avoid waste of resources and ineffective firefighting. Rationally allocate fire-fighting resources according to different areas and risk levels to improve fire-fighting efficiency, minimize fire losses, ensure the safety of hydropower station units and surrounding facilities, and reduce the impact of fires on power generation operations.

[0039] The system management module includes: A system configuration unit, which is used to configure the parameters of the fire alarm system, including sensor sensitivity settings and alarm threshold adjustment; An operation monitoring unit, which is used to monitor the operation status of each module of the fire alarm system in real time, detect faults in a timely manner and issue an alarm; The maintenance management unit is used to perform daily maintenance and management of the system, including data backup and equipment maintenance reminders.

[0040] Specifically, the system configuration unit of the system management module allows staff to configure fire alarm system parameters, such as adjusting sensor sensitivity to better adapt it to fire monitoring needs in different environments; setting alarm thresholds to optimize alarm trigger conditions based on actual conditions. The operation monitoring unit monitors the operating status of each system module in real time. By monitoring key performance indicators and analyzing data, it promptly detects module failures and issues alarms. The maintenance management unit is responsible for daily system maintenance, including regular data backup to prevent data loss, and prompting equipment maintenance based on equipment operating time and status to ensure long-term stable system operation. Flexible system configuration enables the system to adapt to the operating environments and management requirements of different hydropower station units, improving system applicability. Real-time operation monitoring promptly detects failures, reduces system downtime, and ensures the continuous availability of the fire alarm function. Comprehensive maintenance and management measures ensure system data security and equipment operation, extend system life, reduce maintenance costs, and overall improve system stability and reliability.

[0041] The system is further optimized in real time through intelligent self-learning algorithms to adapt to changes in different environments and fire conditions, including: Automatically adjust fire thresholds based on historical fire data, real-time fire changes, and deep learning algorithms; Adaptively fuse the data collected by fire sensors and use a dynamic weighting algorithm to improve the reliability and accuracy of the data; A multi-level alarm mechanism based on hierarchical assessment uses fire risk assessment and data analysis to systematically determine the fire risk level, enabling accurate fire alarms. Automatically adjust linkage control strategies and alarm methods based on current fire conditions and historical data to improve fire response efficiency and reduce losses.

[0042] Specifically, intelligent self-learning algorithms enable the system to continuously adapt to changing environments and fire conditions, improving system performance. Automatic adjustments to fire thresholds and data fusion algorithm weights enhance data quality and alarm accuracy. Precise multi-level alarms and intelligent linkage strategy adjustments improve fire response efficiency, minimize fire losses, and enhance the system's adaptability and response capabilities to complex and changing fire scenarios.

[0043] The system further comprises: A big data storage and analysis platform, which is used to store large amounts of historical fire data and system operation data, and conduct in-depth data analysis to optimize fire risk assessment models and linkage control strategies; The user feedback and optimization module is used to collect feedback from hydropower station staff on fire alarm information and linkage control effects, and optimize and adjust the system based on the feedback information.

[0044] Specifically, big data analysis provides data support for system optimization, making risk assessment models and linkage control strategies more scientific and reasonable. A user feedback mechanism ensures that the system can be improved based on actual usage, meeting the actual needs of staff, improving system usability and practicality, and promoting continuous optimization and upgrading of the system.

[0045] The fire data analysis module is connected to the external fire monitoring system, obtains relevant data provided by the external fire monitoring through a secure data interface, and performs further analysis and processing.

[0046] Specifically, the fire data analysis module connects to an external fire monitoring system through a secure data interface, acquiring relevant data from external fire monitoring systems, such as fire activity in the surrounding area and the distribution of firefighting resources. This data is further analyzed and processed, and integrated with internally collected and analyzed data to provide more comprehensive information for fire risk assessment and alarm generation. Connecting with external systems expands data sources and enriches information dimensions. By integrating external data, a more comprehensive understanding of the fire environment and potential risks can be achieved, improving the accuracy of fire risk assessments, providing a basis for developing more comprehensive fire prevention and control strategies, and enhancing the system's ability to respond to complex fire scenarios.

[0047] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. Various changes and improvements are possible without departing from the spirit and scope of the present invention, and such changes and improvements fall within the scope of the invention as claimed.

Claims

1. A fire alarm auxiliary decision-making management system for hydropower station units, characterized in that: include: Fire data acquisition module, fire data analysis module, fire alarm module, linkage control module and system management module; The fire data acquisition module is used to collect fire-related parameter data in the hydropower station unit area in real time, including smoke concentration, temperature change rate, flame characteristics and carbon monoxide concentration; The fire data analysis module is electrically connected to the fire data acquisition module, and is used to perform preprocessing, feature extraction and data fusion on the collected fire data to generate an analysis data set that meets the fire alarm requirements; The fire alarm module is electrically connected to the fire data analysis module, and is used to output alarm information related to the current fire situation based on the analysis results, and adopt corresponding alarm methods according to different alarm levels; The linkage control module is electrically connected to the fire alarm module, and the linkage control module is used to trigger the corresponding fire fighting equipment linkage according to the alarm information; The system management module is used to configure, monitor, maintain and manage the entire fire alarm system.

2. A hydropower station unit fire alarm auxiliary decision management system according to claim 1, characterized in that: The fire data acquisition module includes: A multi-type sensor unit, which is used for different types of fire sensors, including smoke sensors, temperature sensors, flame sensors, and carbon monoxide sensors, for combined acquisition; A high-speed data transmission unit is used to quickly transmit the collected real-time fire data to the fire data analysis module.

3. A hydropower station unit fire alarm auxiliary decision management system according to claim 1, characterized in that: The fire data analysis module includes: A data screening unit, which is used to remove noise data and erroneous data and perform preliminary screening on the data; A feature extraction unit, configured to extract fire-related feature parameters from data collected by different sensors; The data fusion algorithm unit is used to fuse the data collected by different sensors and improve the accuracy of the data through the adaptive weighted fusion algorithm. The fluctuation coefficient of each sensor data is set to , calculated based on the standard deviation of the data over a period of time, and taking into account the importance coefficient of the sensor , then the fused data The formula is: Where, represents the fused data, For the Data collected by sensors; A data standardization unit, configured to convert the processed data into a unified standard format; The intelligent analysis unit uses a self-learning algorithm to conduct in-depth analysis of fire data, compare historical data with real-time data, and calculate the false alarm risk value. The formula for the false alarm risk value is: in, Indicates the false alarm risk value, the larger the value, the higher the possibility of false alarm; is the number of fire-related parameters; It is Fire parameter values ​​collected in real time; It is the first The mean of the parameters; It is the first The standard deviation of the parameters; It is The weight of a parameter reflects the importance of the parameter to the false alarm judgment, and .

4. A hydropower station unit fire alarm auxiliary decision management system according to claim 1, characterized in that: The fire alarm module comprises: a fire risk assessment unit, which is used to perform risk assessment based on different fire-related parameters, including smoke concentration, temperature change rate, and preset fire thresholds, classify the risk levels corresponding to different fire conditions into different levels, and generate a fire risk level report; Among them, the changing rate of fire-related parameters is considered , and the degree of deviation of this parameter from the normal state , the fire risk assessment formula is: Where, Indicates the comprehensive fire risk level, For the The risk level corresponding to each fire-related parameter, For the The weight of the parameters; An alarm signal generating unit, which is used to generate alarm signals of different levels according to the risk level, and the alarm signals include sound and light alarms, SMS notifications, and station broadcasts; The decision suggestion generation unit generates decision suggestions for responding to fires based on risk levels and on-site data.

5. A hydropower station unit fire alarm auxiliary decision management system according to claim 1, characterized in that: The fire risk assessment unit further comprises: a smoke assessment unit, the smoke assessment unit being used to assess the impact of changes in smoke concentration on fire risk and generate a smoke risk level; a temperature assessment unit, the temperature assessment unit being used to assess the impact of the temperature change rate on the fire risk and generate a temperature risk level; a flame assessment unit, the flame assessment unit being used to assess the impact of flame characteristics on fire risk and generate a flame risk level; a carbon monoxide assessment unit, the carbon monoxide assessment unit being used to assess the impact of carbon monoxide concentration on fire risk and generate a carbon monoxide risk level; The comprehensive risk determination unit is used to perform weighted synthesis on the risk levels generated by different assessment units to generate a final fire risk level.

6. A hydropower station unit fire alarm auxiliary decision management system according to claim 1, characterized in that: The linkage control module includes: A fire protection equipment linkage strategy unit, which formulates corresponding fire protection equipment linkage strategies based on different fire risk levels and the layout of hydropower station units, including activating different fire extinguishing devices in response to fires in different areas; The device control execution unit is used to send control instructions to the corresponding fire-fighting equipment according to the linkage strategy to achieve linkage control of the equipment; The linkage effect evaluation unit conducts real-time evaluation of the linkage effect of fire-fighting equipment to provide a reference for subsequent decision-making.

7. A hydropower station unit fire alarm auxiliary decision-making management system according to claim 1, characterized in that: The system management module includes: A system configuration unit, which is used to configure the parameters of the fire alarm system, including sensor sensitivity settings and alarm threshold adjustment; An operation monitoring unit, which is used to monitor the operation status of each module of the fire alarm system in real time, detect faults in a timely manner and issue an alarm; The maintenance management unit is used to perform daily maintenance and management of the system, including data backup and equipment maintenance reminders.

8. The hydropower station unit fire alarm auxiliary decision-making management system according to claim 1, characterized in that: The system is further optimized in real time through intelligent self-learning algorithms to adapt to changes in different environments and fire conditions, including: Automatically adjust fire thresholds based on historical fire data, real-time fire changes, and deep learning algorithms; Adaptively fuse the data collected by fire sensors and use a dynamic weighting algorithm to improve the reliability and accuracy of the data; A multi-level alarm mechanism based on hierarchical assessment uses fire risk assessment and data analysis to systematically determine the fire risk level, enabling accurate fire alarms. Automatically adjust linkage control strategies and alarm methods based on current fire conditions and historical data to improve fire response efficiency and reduce losses.

9. The hydropower station unit fire alarm auxiliary decision-making management system according to claim 1, characterized in that: The system further comprises: A big data storage and analysis platform, which is used to store large amounts of historical fire data and system operation data, and conduct in-depth data analysis to optimize fire risk assessment models and linkage control strategies; The user feedback and optimization module is used to collect feedback from hydropower station staff on fire alarm information and linkage control effects, and optimize and adjust the system based on the feedback information.

10. The hydropower station unit fire alarm auxiliary decision management system according to claim 1, characterized in that: The fire data analysis module is connected to the external fire monitoring system, obtains relevant data provided by the external fire monitoring through a secure data interface, and performs further analysis and processing.

Images