Fire-fighting facility intelligent operation and maintenance online monitoring management method and system

Abstract

The application discloses a fire-fighting facility intelligent operation and maintenance online monitoring management method and system, relates to the technical field of fire-fighting equipment intelligent operation and maintenance, and is based on a pressure curve form obtained through pressure continuous monitoring, extracts four characteristic dimensions of pressure change amplitude, pressure drop speed, abnormal duration and recovery characteristics, establishes a data characteristic rule library, can quickly distinguish normal forest protection water use, illegal use, pipeline rupture, fire hydrant failure, fire-fighting water and other event types through rule comparison, for complex conditions with overlapping characteristics, adopts a water hammer wave speed method to calculate a leakage point distance based on a pressure signal time sequence difference of multiple intelligent fire hydrants in a pipe network, realizes rapid positioning, and performs weighted calculation based on the pressure change amplitude and the pressure drop speed, outputs a damage index, so as to judge the fault severity, facilitate maintenance response, and simultaneously monitor only fire hydrant pressure characteristics, so that the overall reconstruction and operation and maintenance cost is lower.

Description

Technical Field

[0001] This invention relates to the field of intelligent operation and maintenance technology for fire protection equipment, and in particular to a method and system for online monitoring and management of intelligent operation and maintenance of fire protection facilities. Background Technology

[0002] Forest fire hydrants, as core infrastructure for emergency forest fire fighting, are crucial equipment connecting forest fire water sources and ensuring water supply for firefighting operations. They are directly related to forest ecological security, the safety of forest rangers, and the safety of forest property. Given the complex terrain, dense vegetation, uneven water distribution, and vast and remote management areas of forest regions, the current management of forest fire hydrants still follows a traditional, extensive model. Daily operation and maintenance are mainly handled by forest farm protection teams and fire and rescue departments. Due to the inconvenient transportation, difficult inspections, and harsh environment in forest areas, there are widespread problems such as inadequate management, untimely operation and maintenance, and delayed hazard investigation. This seriously restricts the efficiency of emergency forest fire fighting and fails to fully realize the emergency support role of fire hydrants.

[0003] Currently, newly built fire hydrants typically have IoT capabilities, using built-in multi-sensor monitoring to detect faults and enabling remote unmanned management through valve control, video surveillance, and voice broadcasting, resulting in efficient operation and maintenance. However, for existing basic fire protection pipeline facilities, on the one hand, the transformation is difficult and costly, and on the other hand, the monitoring process involves many monitoring contents, leading to higher overall operation and maintenance costs and management difficulties. Furthermore, it is impossible to determine the type and location of faults in a timely manner. Therefore, this paper proposes an intelligent operation and maintenance online monitoring and management method and system for fire protection facilities. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent online monitoring and management method and system for the operation and maintenance of fire protection facilities, so as to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an intelligent operation and maintenance online monitoring and management method for fire protection facilities, comprising the following steps: S1. Establish an intelligent operation and maintenance management platform for fire hydrants; S2. Upgrade existing fire hydrants to be intelligent, and install solenoid valves with pressure sensors and embedded flow monitoring modules; S3. Intelligent pipeline monitoring based on smart fire hydrants: Through continuous pressure monitoring, the system determines the occurrence of events based on pressure changes and calls upon smart fire hydrants for verification. S4. Analyze and judge the fault based on monitoring results and historical big data; S5. Build a database to store monitoring and maintenance data; In step S4, the pressure change amplitude is obtained based on continuous pressure monitoring. Pressure reduction Abnormal time Recovery characteristics and valve outlet The data is used to establish a data feature rule base based on the stress characteristics of different types of events. The rule base uses a data fusion algorithm to make judgments after the monitoring data is fused. For typical data features, the event type is directly determined based on the threshold comparison results of typical features in the rule base. For atypical data characteristics, the weight of data fusion during the judgment of corresponding events is adjusted based on the dependence of different monitoring data in the judgment process of different types of events, thereby improving the accuracy of event type judgment.

[0006] Preferably, in step S3, a central monitoring module is built in the intelligent operation and maintenance management platform. By setting a sampling period, pressure data of the smart fire hydrant is continuously acquired. By designing a data reporting strategy, when the pressure value is within the normal range, data is uploaded periodically by setting a data reporting period; when the pressure change exceeds the threshold, data upload is triggered immediately. The central monitoring module uses an abnormal wake-up mechanism. When the pressure change curve triggers a preset rule, the central monitoring module actively calls the solenoid valve of the fire hydrant to obtain flow information and simultaneously determine the opening and closing status of the solenoid valve.

[0007] Preferably, the data feature rule base is based on data fusion analysis of monitoring data from the central monitoring module, wherein the pressure change amplitude... This reflects the current change in pipeline pressure, which in turn reflects the water volume; the rate of pressure drop. Indicates water output speed; abnormal time. It reflects the duration of the current event, used to determine whether it is a momentary or continuous event; recovery characteristics. It involves monitoring whether a regression occurs in the overall curve shape. =1 indicates that recovery is possible; =0 indicates no recovery, used to determine whether water flow has stopped, and is used to rule out pipe damage or fire hydrant malfunction. (Valve water flow...) It determines whether the water outlet is a fire hydrant by calling the solenoid valve flow detection module. This indicates that water is coming out of a fire hydrant; This indicates that the fire hydrant is not discharging water.

[0008] Preferably, the data feature rule base is established based on event type. By constructing an event judgment and prediction analysis model in the central monitoring module, the event type can be quickly judged by calling the data feature rule base. The judgment logic is as follows: This indicates that the water output was low, the water output speed was low, and the water output time was short throughout the entire water output process. Most importantly, the water output event had an ending behavior, and the water output location was at a fire hydrant. At this point, it can be directly judged as normal forest protection water use. All other cases are judged as abnormal water use. This indicates that the water volume is large, the water flow rate is fast, and the water flow time is long throughout the entire water outflow process. Furthermore, the water outlet is located at a fire hydrant, so it is directly judged as illegal theft. This indicates that the entire water outflow process lasts a long time and the water outflow event has no end. Most importantly, the water outflow location is not a fire hydrant. At this point, it is determined that the pipe has ruptured. This indicates that the entire water discharge process lasts a long time and the water discharge event has no ending behavior. Most importantly, the solenoid valve signal feedback of the fire hydrant cannot be obtained. At this time, it is determined that the leakage is caused by the failure of the solenoid valve of the fire hydrant. in Indicates the minimum allowable water output. Indicates the maximum allowable water output; Indicates the minimum permissible water flow rate. Indicates the maximum permissible water flow rate; Indicates the shortest allowed water discharge time. Indicates the maximum allowed water discharge time; This indicates the absence of a solenoid valve signal.

[0009] Preferably, in step S4, a comprehensive data analysis is performed based on historical analysis data stored in the database and subsequent maintenance and inspection verification information. Historical data is used to provide data support for the maintenance and updating of the event judgment and prediction analysis model. Furthermore, the weight of data fusion during the judgment of different types of events is adjusted based on the dependence of different monitoring data during the judgment process of different types of events. Thus, probability output is performed on data that may have overlapping event types during the analysis. The judgment logic is as follows: when , as well as When both exist, and At this point, make a judgment ,like If the value is 0, it indicates that water is being discharged from the valve and the discharge event has not terminated. In this case, the solenoid valve is invoked. If the solenoid valve responds, a weighted data fusion algorithm is used to calculate the value based on the pressure change amplitude. Pressure reduction and abnormal time The specific logic for using data fusion to determine whether water use is abnormal or normal for forest protection is as follows;

[0010] in ,and , respectively represent , as well as The weights; Initially

[0011] After adjusting the weights of both, cross-validation was performed. When identifying abnormal water usage, more attention is paid to the time of the abnormality, at which point the risk is increased. and reduce and ; When assessing normal forestry water usage, more attention is paid to the water output volume, at which point the volume is increased. At this time, it is appropriate to reduce and ; Finally, based on the calculation results of both, a threshold is designed. When the difference between the two calculation results is greater than If the event is larger, then the event is judged as the one with the larger Q value.

[0012] Preferably, in step S4, when accurately locating the pressure relief position, the pressure difference change signals of the nearest upper and lower fire hydrants Q2 and Q3 are obtained based on the position of the fire hydrant Q1 where the pressure difference signal first appears, along with the time of signal appearance. If the acquisition times of the pressure difference signals of the nearest fire hydrants Q2 and Q3 are similar, the solenoid valve signal of fire hydrant Q1 is acquired to determine whether water is flowing from fire hydrant Q1. If the acquisition times of the pressure difference signals of fire hydrants Q2 and Q3 differ significantly, it indicates that the pipeline leak point is between Q1 and the fire hydrant with the shorter acquisition time. Then, the time difference is calculated using the timestamp of the signal acquired by Q1 and the timestamp of the most recent pressure difference signal. The distance to the leak point is then calculated based on the water hammer wave velocity method, thereby achieving accurate location.

[0013] Preferably, after obtaining accurate positioning, the size of the damage is determined based on the pressure change amplitude; the rate of expansion of the damage location is judged based on the pressure drop rate; and the severity of the event is determined by weighted calculation based on the two, thereby providing corresponding early warning level signals and corresponding maintenance plans for different severity levels.

[0014] Preferably, in step S2, an alarm module is installed on the fire hydrant. The alarm module includes a horn and / or a buzzer and / or a warning light. In step S3, during long-term monitoring, all sensors except the pressure sensor are in a dormant state. After being woken up by the abnormal wake-up mechanism, the flow sensor continuously reads for 30 seconds to read the current opening degree of the solenoid valve and uploads the data. When theft is detected, the alarm module issues an on-site warning and sets a warning time threshold. If the pressure difference recovers within the threshold time, the theft stops, and the warning stops. Otherwise, the relevant theft information is sent to the nearest maintenance personnel through the intelligent operation and maintenance management platform.

[0015] Preferably, the central monitoring module is equipped with a self-testing module. By setting a self-testing cycle, the solenoid valve is automatically opened and closed and the pressure sensor is tested during the off-peak hours at night to ensure that the equipment is in normal working order. When a fire alarm is triggered within the area or a fire is identified based on a comparison with a data feature rule base, the solenoid valves of non-area fire hydrants are remotely shut off to ensure stable water supply and pressure within the fire area.

[0016] The intelligent operation and maintenance online monitoring and management system for fire protection facilities includes: The intelligent fire hydrant terminal is an existing fire hydrant equipped with a pressure sensor, a solenoid valve with an embedded flow monitoring module, a communication module, an alarm module, and a battery pack to provide a physical environment for data acquisition. The data acquisition and reporting module is used to collect data from fire hydrants according to a preset cycle and upload the data using the communication module. The central monitoring module is used to perform continuous monitoring operations; The fault analysis engine has a built-in data feature rule library, which is used to analyze and judge the fault type based on monitoring data and historical data. The machine learning enhancement module performs data analysis based on historical data to optimize and adjust the judgment threshold, thereby providing more reliable data support for the fault analysis engine. The database module is used to store historical monitoring data, maintenance and inspection results, and system encapsulation data; The maintenance work order and management module is used to assign maintenance orders based on fault analysis results.

[0017] The technical effects and advantages of this invention are as follows: 1. This intelligent online monitoring and management method for fire protection facilities extracts four feature dimensions—pressure change amplitude, pressure drop rate, abnormal duration, and recovery characteristics—based on the pressure curve shape obtained from continuous pressure monitoring. A data feature rule base is established, and through rule comparison, it can quickly distinguish event types such as normal forest protection water use, illegal theft, pipeline rupture, fire hydrant failure, and fire water use. For complex situations with overlapping features, and based on the time sequence difference of pressure signals from multiple smart fire hydrants in the pipeline network, the water hammer wave velocity method is used to calculate the distance to the leak point, achieving rapid location. Furthermore, a damage index is output based on a weighted calculation of pressure change amplitude and pressure drop rate, thereby judging the severity of the fault and facilitating maintenance response.

[0018] 2. The intelligent operation and maintenance online monitoring and management method for fire protection facilities adopts the following approach: under normal operating conditions, the intelligent fire hydrant only continuously monitors the water pressure, while components such as flow sensors, solenoid valves, and alarm modules are in a deep dormant state. When the pressure data triggers preset rule conditions, the central monitoring module actively calls the solenoid valve of the fire hydrant through an abnormal wake-up mechanism, wakes up the flow sensor for auxiliary verification, and uploads the obtained flow information and valve opening and closing status. On the one hand, this can effectively reduce energy consumption, extend the service life of the built-in battery, and eliminate the need for complex monitoring units, resulting in less monitoring content and lower equipment modification and operating costs.

[0019] 3. This intelligent online monitoring and management system for fire protection facilities enables equipment to perform self-checks during idle periods through a central monitoring module, ensuring that the equipment is in normal operating condition. This replaces manual inspections, reducing costs. At the same time, it ensures an effective supply of fire-fighting water during a fire. Furthermore, during a fire, it can delineate a target protection zone centered on the fire point and send remote water restriction commands to all fire hydrants in the outer area, ensuring stable water pressure in the target protection zone and effectively improving the effectiveness and timeliness of fire-fighting. Attached Figure Description

[0020] Figure 1 This is a flowchart of the intelligent operation and maintenance method of the present invention; Figure 2 This is a flowchart illustrating the logic for determining the type of time-related events in the intelligent operation and maintenance method of this invention. Figure 3 This is a schematic diagram of the functional architecture of the intelligent operation and maintenance system of the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Example 1: This embodiment of the invention provides the following... Figures 1-2 The online monitoring and management method for intelligent operation and maintenance of fire protection facilities, as shown, includes the following steps: S1. Build an intelligent operation and maintenance management platform for fire hydrants. The platform supports concurrent access and registration management of a large number of smart fire hydrant devices, is compatible with multiple communication protocols such as NB-IoT, 4G, and 5G, and has a built-in time-series database to store high-frequency monitoring data such as pressure and flow. It supports processing tens of thousands of data points per second and integrates full-process business modules such as equipment management, event analysis, work order flow, personnel scheduling, and report statistics. It also provides standardized interfaces to achieve data interoperability with existing smart cities, fire command centers, and emergency management systems.

[0023] S2. Based on the existing fire hydrants, carry out intelligent upgrades and renovations, add pressure sensors and solenoid valves with embedded flow monitoring modules, and also install communication modules, alarm modules and battery packs; at the same time, add alarm modules to the fire hydrants, including horns and / or buzzers and / or warning lights.

[0024] S3. Intelligent pipeline monitoring based on smart fire hydrants: Through continuous pressure monitoring, the system determines the occurrence of events based on pressure changes and calls upon smart fire hydrants for verification. In this step, a central monitoring module is built in the intelligent operation and maintenance management platform. By setting a sampling period, pressure data of the smart fire hydrant is continuously acquired. By designing a data reporting strategy, when the pressure value is within the normal range, data is uploaded periodically according to the set data reporting period; when the pressure change exceeds the threshold, data upload is triggered immediately. The central monitoring module uses an anomaly wake-up mechanism. When the pressure change curve triggers a preset rule, the central monitoring module actively calls the solenoid valve of the fire hydrant to obtain flow information and determine the opening and closing status of the solenoid valve. In practical applications, thresholds are set for three key characteristics: pressure change amplitude, pressure drop rate, and anomaly time. When the detected data exceeds any of these thresholds, an anomaly wake-up is initiated, and the data is verified through the solenoid valve, thereby effectively reducing daily monitoring costs.

[0025] During long-term monitoring, all sensors except the pressure sensor are in a dormant state. After being woken up by an abnormal wake-up mechanism, the flow sensor continuously reads for 30 seconds to read the current opening degree of the solenoid valve and uploads the data. When theft is detected, an on-site warning is issued through the alarm module, and a warning time threshold is set. If the differential pressure recovers within the threshold time, the theft will stop, and the warning will be stopped. Otherwise, the relevant theft information will be sent to the nearest maintenance personnel through the intelligent operation and maintenance management platform.

[0026] The central monitoring module is equipped with a self-test module. By setting the self-test cycle, it performs automatic opening and closing verification of solenoid valves and pressure sensor verification during off-peak hours at night to ensure normal equipment operation. The self-test process includes: L1, The central platform sends a "valve shut-off self-check" command to the fire hydrant; L2. Close the solenoid valve of the fire hydrant and maintain the closed state. Record the static pressure P1.

[0027] L3. Keep closed for 30 seconds and monitor whether the pressure drops. If there is no drop, the seal is good. If the pressure drops by more than 0.02 MPa, mark it as "internal leakage". L4. Send the "open valve self-test" command, open the valve briefly for 0.5 seconds and then close it, record the pressure shock response, and determine whether the solenoid valve operates smoothly. L5. Report the self-test results, including normal, solenoid valve stuck, internal leakage, and pressure sensor drift.

[0028] The entire self-inspection process is fully automated, and fire hydrants in the area are tested simultaneously. No on-site inspection by personnel is required, and all functional tests can be completed remotely.

[0029] S4. Analyze and judge the fault based on monitoring results and historical big data; In this step, the pressure change amplitude is obtained based on continuous pressure monitoring. Pressure reduction Abnormal time Recovery characteristics and valve outlet The data is used to establish a data feature rule base based on the stress characteristics of different types of events. The rule base uses a data fusion algorithm to make judgments after the monitoring data is fused. For typical data features, the event type is directly determined based on the threshold comparison results of typical features in the rule base. For atypical data characteristics, the weights of data fusion during event fusion are adjusted based on the dependence of different monitoring data on different event types, thereby improving the accuracy of event type identification. The data feature rule base is based on data fusion analysis of monitoring data from the central monitoring module, including pressure change amplitude. This reflects the current change in pipeline pressure, which in turn reflects the water volume; the rate of pressure drop. Indicates water output speed; abnormal time. It reflects the duration of the current event, used to determine whether it is a momentary or continuous event; recovery characteristics. It involves monitoring whether a regression occurs in the overall curve shape. =1 indicates that recovery is possible; =0 indicates no recovery, used to determine whether water flow has stopped, and is used to rule out pipe damage or fire hydrant malfunction. (Valve water flow...) It determines whether the water outlet is a fire hydrant by calling the solenoid valve flow detection module. This indicates that water is coming out of a fire hydrant; This indicates that the fire hydrant is not discharging water.

[0030] The data feature rule base is built based on event type. By constructing an event judgment and prediction analysis model in the central monitoring module, the event type can be quickly judged by calling the data feature rule base. The judgment logic is as follows: This indicates that the water output was low, the water output speed was low, and the water output time was short throughout the entire water output process. Most importantly, the water output event had an ending behavior, and the water output location was at a fire hydrant. At this point, it can be directly judged as normal forest protection water use. All other cases are judged as abnormal water use. This indicates that the water volume is large, the water flow rate is fast, and the water flow time is long throughout the entire water outflow process. Furthermore, the water outlet is located at a fire hydrant, so it is directly judged as illegal theft. This indicates that the entire water outflow process lasts a long time and the water outflow event has no end. Most importantly, the water outflow location is not a fire hydrant. At this point, it is determined that the pipe has ruptured. This indicates that the entire water discharge process lasts a long time and the water discharge event has no ending behavior. Most importantly, the solenoid valve signal feedback of the fire hydrant cannot be obtained. At this time, it is determined that the leakage is caused by the failure of the solenoid valve of the fire hydrant. in Indicates the minimum allowable water output. Indicates the maximum allowable water output; Indicates the minimum permissible water flow rate. Indicates the maximum permissible water flow rate; Indicates the shortest allowed water discharge time. Indicates the maximum allowed water discharge time; This indicates the absence of a solenoid valve signal.

[0031] The weight of data fusion during the judgment of different types of events is adjusted based on the dependence of different monitoring data in the judgment process of different types of events. In this way, the probability output is given for data that may have overlapping event types during the analysis. The judgment logic is as follows: when , as well as When both exist, and At this point, make a judgment ,like If the value is 0, it indicates that water is being discharged from the valve and the discharge event has not terminated. In this case, the solenoid valve is invoked. If the solenoid valve responds, a weighted data fusion algorithm is used to calculate the value based on the pressure change amplitude. Pressure reduction and abnormal time The specific logic for using data fusion to determine whether water use is abnormal or normal for forest protection is as follows;

[0032] in ,and , respectively represent , as well as The weights; Initially

[0033] After adjusting the weights of both, cross-validation was performed. When identifying abnormal water usage, more attention is paid to the time of the abnormality, at which point the risk is increased. and reduce and ; When assessing normal forestry water usage, more attention is paid to the water output volume, at which point the volume is increased. At this time, it is appropriate to reduce and ; Finally, based on the calculation results of both, a threshold is designed. When the difference between the two calculation results is greater than If the event is larger, then the event is judged as the one with the larger Q value.

[0034] Simultaneously, when accurately locating the pressure relief point, the system extrapolates upwards and downwards from the location of the fire hydrant Q1 where the differential pressure signal first appears, obtaining the differential pressure change signals of the nearest fire hydrants Q2 and Q3, as well as the time of their appearance. If the acquisition times of the differential pressure signals from the nearest two fire hydrants Q2 and Q3 are similar, the system acquires the solenoid valve signal from fire hydrant Q1 to determine if water is flowing from hydrant Q1. If the acquisition times of the differential pressure signals from fire hydrants Q2 and Q3 differ significantly, it indicates that the pipeline leak point is between Q1 and the fire hydrant with the shorter acquisition time. Then, the time difference is calculated using the timestamp of the signal acquired by Q1 and the timestamp of the most recent differential pressure signal. Finally, the distance to the leak point is calculated based on the water hammer wave velocity method, thereby achieving accurate location.

[0035] After obtaining precise location, the size of the damage is determined based on the amplitude of pressure change; the rate of expansion of the damage location is judged based on the rate of pressure reduction; and the severity of the event is determined by a weighted calculation based on the two factors, thereby providing corresponding early warning level signals and corresponding maintenance plans for different severity levels.

[0036] In practical applications, the event judgment and prediction analysis model outputs a damage index D(0-1), which is obtained by weighting the pressure change amplitude and pressure drop rate, and then mapping the result to the maintenance level. If D∈(0-0.2), it is marked as normal water pressure fluctuation and no maintenance is required; If D∈(0.21-0.4), it is marked as a level three minor leak. Possible faults include leakage due to aging of the sealing ring. At this time, the flow rate is <1L / min, the pressure fluctuation is small, and a single person needs to be arranged for repair within 7 days. If D∈(0.41-0.6), it is marked as a level 2 medium leakage. Possible faults include valve body cracks or loose connections. At this time, there is obvious water leakage and the pressure continues to drop >0.1MPa. Manual repair by multiple people is required within 48 hours. If D∈(0.61-0.8), it is marked as a first-level serious leak. At this time, the pipe may rupture, a large amount of water may leak, the pressure drop is >0.3MPa, and the surrounding water supply will be affected. Light equipment and personnel need to be arranged for repair within 12 hours. If D∈(0.81-1), this is marked as an emergency. At this time, there may be a burst pipe or complete damage to the fire hydrant, the pressure will drop to zero, water will gush from the ground, and immediate repairs are required. The corresponding area needs to be sealed off, and large equipment needs to be called in.

[0037] When a fire alarm is triggered within the designated area, or when a fire is identified based on a comparison with a data feature rule base, the solenoid valves of non-area fire hydrants are remotely shut off to ensure stable water supply and pressure within the fire area. In practical applications, the area is delineated through video monitoring, manual alarms, or a data feature rule base comparison structure. Fire hydrants within a 500-meter radius of the fire point are defined as the target protection zone, a buffer zone is defined as a radius of 500-1500 meters, and the rest is the outer perimeter zone. Depending on the specific area, fire hydrants in the outer perimeter zone are temporarily shut off.

[0038] S5. Build a database to store monitoring and maintenance data. During application, perform comprehensive data analysis based on historical analysis data stored in the database and subsequent maintenance verification information. Use historical data to provide data support for the maintenance and updating of the event judgment and prediction analysis model.

[0039] Working principle: Under normal operating conditions, the intelligent fire hydrant only continuously monitors water pressure, while components such as flow sensors, solenoid valves, and alarm modules are in deep dormancy. When the pressure data triggers preset rule conditions, the central monitoring module actively calls the solenoid valve of the fire hydrant through an abnormal wake-up mechanism, wakes up the flow sensor for auxiliary verification, and uploads the obtained flow information and valve opening / closing status. This effectively reduces energy consumption, extends the service life of the built-in battery, eliminates the need for complex monitoring units, reduces the amount of monitored data, and lowers equipment modification and operating costs.

[0040] Secondly, based on the pressure curve shape obtained from continuous pressure monitoring, four feature dimensions are extracted: pressure change amplitude (P), pressure drop rate (dP / dt), abnormal duration (T), and recovery characteristics. A data feature rule base is established, and by comparing the rules, event types such as normal forest protection water use, illegal theft, pipeline rupture, fire hydrant failure, and fire fighting water use can be quickly distinguished. For complex cases with overlapping features, an LSTM (Long Short-Term Memory) network is introduced for classification to improve the accuracy of subsequent analysis. Furthermore, based on the time sequence difference of pressure signals from multiple smart fire hydrants in the pipeline network, the fire hydrant with the first differential pressure signal and its timestamp are determined, and the signal time of neighboring fire hydrants is derived upstream and downstream. The distance to the leak point is calculated using the water hammer wave velocity method to achieve rapid location. Finally, a damage index is output based on a weighted calculation of pressure change amplitude and pressure drop rate to determine the severity of the fault and facilitate maintenance response.

[0041] Meanwhile, the method enables the equipment to perform self-checks during idle periods through a central monitoring module, ensuring that the equipment is in normal operating condition, replacing manual inspections to reduce costs, and ensuring an effective supply of fire-fighting water in the event of a fire. In addition, when a fire occurs, a target protection zone can be delineated with the fire point as the center, and remote water restriction commands can be sent to all fire hydrants in the outer area to ensure stable water pressure in the target protection zone, effectively improving the effectiveness and timeliness of fire-fighting.

[0042] Example 2, the present invention provides as follows Figure 3 The intelligent online monitoring and management system for fire protection facilities shown includes: The intelligent fire hydrant terminal adds a pressure sensor, a solenoid valve with an embedded flow monitoring module, a communication module, an alarm module, and a battery pack to the existing fire hydrant. The pressure sensor has a range of 0-1.6MPa, an accuracy of 0.25%FS, and IP68 protection. It continuously monitors the water pressure in the pipeline network and is the only long-term online monitoring item in the system. The flow monitoring module of the solenoid valve has a flow accuracy of >95%, can be activated on demand, and monitors instantaneous and cumulative flow. It supports remote valve opening / closing control. The communication module adopts a 5G wireless communication module. The alarm module adopts a combination of horn / buzzer / warning light. The battery pack uses lithium thionyl chloride with a capacity of ≥4AH and supports continuous pressure monitoring for ≥8 years.

[0043] The data acquisition and reporting module is used to collect data from fire hydrants according to a preset cycle and upload the data using the communication module. The central monitoring module is used to perform continuous monitoring operations; The fault analysis engine has a built-in data feature rule library, which is used to analyze and judge the fault type based on monitoring data and historical data. The machine learning enhancement module performs data analysis based on historical data to optimize and adjust the judgment threshold, thereby providing more reliable data support for the fault analysis engine. The database module is used to store historical monitoring data, maintenance results, and system encapsulation data; The maintenance work order and management module is used to assign maintenance orders based on fault analysis results.

[0044] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent operation and maintenance online monitoring and management of fire protection facilities, characterized in that, Includes the following steps: S1. Establish an intelligent operation and maintenance management platform for fire hydrants; S2. Upgrade existing fire hydrants to be intelligent, and install solenoid valves with pressure sensors and embedded flow monitoring modules; S3. Intelligent pipeline monitoring based on smart fire hydrants: Through continuous pressure monitoring, the system determines the occurrence of events based on pressure changes and calls upon smart fire hydrants for verification. S4. Analyze and judge the fault based on monitoring results and historical big data; S5. Build a database to store monitoring and maintenance data; In step S4, the pressure change amplitude is obtained based on continuous pressure monitoring. Pressure reduction Abnormal time Recovery characteristics and valve outlet The data is used to establish a data feature rule base based on the stress characteristics of different types of events. The rule base uses a data fusion algorithm to make judgments after the monitoring data is fused. For typical data features, the event type is directly determined based on the threshold comparison results of typical features in the rule base. For atypical data characteristics, the weights of data fusion during the judgment of different types of events are adjusted based on the dependence of different monitoring data in the judgment process of different types of events, thereby improving the accuracy of event type judgment. The judgment logic is as follows: In step S3, a central monitoring module is built in the intelligent operation and maintenance management platform. The data feature rule base performs data fusion analysis based on the monitoring data of the central monitoring module, including the pressure change amplitude. This reflects the current change in pipeline pressure, which in turn reflects the water volume; the rate of pressure drop. Indicates water output speed; abnormal time. It reflects the duration of the current event, used to determine whether it is a momentary or continuous event; Recovery characteristics It involves monitoring whether a regression occurs in the overall curve shape. =1 indicates that recovery is possible; =0 indicates no recovery, used to determine whether water flow has stopped, and is used to rule out pipe damage or fire hydrant malfunction. (Valve water flow...) It determines whether the water outlet is a fire hydrant by calling the solenoid valve flow detection module. This indicates that water is coming out of a fire hydrant; This indicates that the fire hydrant is not discharging water. when , as well as When both exist, and At this point, make a judgment ,like If the value is 0, it indicates that water is being discharged from the valve and the discharge event has not terminated. In this case, the solenoid valve is invoked. If the solenoid valve responds, a weighted data fusion algorithm is used to calculate the value based on the pressure change amplitude. Pressure reduction and abnormal time The data fusion method is used to determine whether water use is abnormal or normal for forest protection. The specific logic is as follows: in Indicates the probability of an event occurring. ,and , respectively represent , as well as The weights; Initially After weighting and adjusting for abnormal water use and normal forest protection water use respectively, the calculations were cross-validated. When identifying abnormal water usage, more attention is paid to the time of the abnormality, at which point the risk is increased. and reduce and ; When assessing normal forestry water usage, more attention is paid to the water output, at which point the flow rate is increased. At this time, it is appropriate to reduce and ; Finally, based on the calculation results of abnormal water use or normal forest protection water use, thresholds were designed. When the difference between the two calculation results is greater than If the probability of an event is greater than the probability of its occurrence (Q value), then the event is judged as the one with the higher probability of occurrence (Q value).

2. The intelligent operation and maintenance online monitoring and management method for fire protection facilities according to claim 1, characterized in that, The central monitoring module continuously acquires pressure data from the smart fire hydrant by setting a sampling period, and through a designed data reporting strategy, it periodically uploads data when the pressure value is within the normal range; when the pressure change exceeds the threshold, it immediately triggers data upload. The central monitoring module uses an abnormal wake-up mechanism. When the pressure change curve triggers a preset rule, the central monitoring module actively calls the solenoid valve of the fire hydrant to obtain flow information and simultaneously determine the opening and closing status of the solenoid valve.

3. The intelligent operation and maintenance online monitoring and management method for fire protection facilities according to claim 2, characterized in that, The data feature rule base is built based on event types. By constructing an event judgment and prediction analysis model in the central monitoring module, the event type is quickly determined by calling the data feature rule base. The judgment logic is as follows: This indicates that the water output was low, the water output speed was low, and the water output time was short throughout the entire water output process. Most importantly, the water output event had an ending behavior, and the water output location was at a fire hydrant. At this point, it can be directly judged as normal forest protection water use. All other cases are judged as abnormal water use. This indicates that the water volume is large, the water flow rate is fast, and the water flow time is long throughout the entire water outflow process. Furthermore, the water outlet is located at a fire hydrant, so it is directly judged as illegal theft. This indicates that the entire water outflow process lasts a long time and the water outflow event has no end. Most importantly, the water outflow location is not a fire hydrant. At this point, it is determined that the pipe has ruptured. This indicates that the entire water discharge process lasts a long time and the water discharge event has no ending behavior. Most importantly, the solenoid valve signal feedback of the fire hydrant cannot be obtained. At this time, it is determined that the leakage is caused by the failure of the solenoid valve of the fire hydrant. in Indicates the minimum allowable water output. Indicates the maximum allowable water output; Indicates the minimum permissible water flow rate. Indicates the maximum permissible water flow rate; Indicates the shortest allowed water discharge time. Indicates the maximum allowed water discharge time; This indicates the absence of a solenoid valve signal.

4. The intelligent operation and maintenance online monitoring and management method for fire protection facilities according to claim 3, characterized in that, In step S4, a comprehensive data analysis is performed based on historical analysis data stored in the database and subsequent maintenance and verification information. Historical data is used to provide data support for the maintenance and updating of the event judgment and prediction analysis model. Furthermore, the weight of data fusion during the judgment of different types of events is adjusted based on the dependence of different monitoring data during the judgment process of different types of events, so that data with overlapping event types can be output with probability during the analysis.

5. The intelligent operation and maintenance online monitoring and management method for fire protection facilities according to claim 4, characterized in that, In step S4, the pressure relief location is accurately located based on the pressure curve morphology of multiple smart fire hydrants. The pressure difference change signals of the nearest upper and lower fire hydrants Q2 and Q3 are obtained from the location of the fire hydrant Q1 where the pressure difference signal first appears, along with the time of signal appearance. If the acquisition times of the pressure difference signals of the nearest two fire hydrants Q2 and Q3 are similar, the solenoid valve signal of fire hydrant Q1 is acquired to determine if water is flowing from fire hydrant Q1. If the acquisition times of the pressure difference signals of fire hydrants Q2 and Q3 differ significantly, it indicates that the pipeline leak point is between fire hydrant Q1 and the fire hydrant with the shorter signal acquisition time. Then, the time difference is calculated using the timestamp of the signal acquisition by fire hydrant Q1 and the timestamp of the most recent pressure difference signal. Finally, the distance to the leak point is calculated based on the water hammer wave velocity method, thereby achieving accurate location.

6. The intelligent operation and maintenance online monitoring and management method for fire protection facilities according to claim 5, characterized in that, In step S4, the severity of a specific event is determined based on the shape of the pressure curve. After obtaining precise location, the size of the damage is determined based on the pressure change amplitude. The rate of expansion of the damage location is determined based on the pressure drop rate. Thus, the severity of the event is determined by weighted calculation based on the pressure change amplitude and the pressure drop rate. Corresponding warning level signals and corresponding maintenance plans are then given for different severity levels.

7. The intelligent operation and maintenance online monitoring and management method for fire protection facilities according to claim 2, characterized in that, In step S2, an alarm module is installed on the fire hydrant. The alarm module includes a horn and / or a buzzer and / or a warning light. In step S3, during long-term monitoring, all sensors except the pressure sensor are in a dormant state. After being awakened by the abnormal wake-up mechanism, the flow sensor continuously reads for 30 seconds to read the current opening degree of the solenoid valve and uploads the data. When theft is detected, the alarm module issues an on-site warning and sets a warning time threshold. If the pressure difference recovers within the threshold time, the theft stops, and the warning stops. Otherwise, the relevant theft information is sent to the nearest maintenance personnel through the intelligent operation and maintenance management platform.

8. The intelligent operation and maintenance online monitoring and management method for fire protection facilities according to claim 2, characterized in that, The central monitoring module is equipped with a self-testing module. By setting a self-testing cycle, it automatically verifies the opening and closing of the solenoid valve and the pressure sensor during off-peak hours at night to ensure that the equipment is in normal working order. When a fire alarm is triggered within the area or a fire is identified based on a comparison with a data feature rule base, the solenoid valves of fire hydrants in non-fire areas are remotely shut off to ensure stable water supply and pressure in the fire area.

9. A smart online monitoring and management system for fire protection facilities, used to execute the smart online monitoring and management method for fire protection facilities as described in any one of claims 1-8, characterized in that, include: The intelligent fire hydrant terminal is an existing fire hydrant equipped with a pressure sensor, a solenoid valve with an embedded flow monitoring module, a communication module, an alarm module, and a battery pack to provide a physical environment for data acquisition. The data acquisition and reporting module is used to collect data from fire hydrants according to a preset cycle and upload the data using the communication module. The central monitoring module is used to perform continuous monitoring operations; The fault analysis engine has a built-in data feature rule library, which is used to analyze and judge the fault type based on monitoring data and historical data. The machine learning enhancement module performs data analysis based on historical data to optimize and adjust the judgment threshold, thereby providing more reliable data support for the fault analysis engine. The database module is used to store historical monitoring data, maintenance results, and system encapsulation data; The maintenance work order and management module is used to assign maintenance orders based on fault analysis results.

Images