Device, control method and system for the dosing and automatic replenishment of fire extinguishing agents

Abstract

The application discloses a device, a control method and a system for quantitative spraying and automatic supply of fire extinguishing agents, aiming at solving the problem that the existing fire extinguishing system and method lack in precision and reaction speed and cannot meet the demand for efficient fire extinguishing. The control method comprises the following steps: S1, data acquisition; real-time data of a fire scene and the device are collected through a sensor unit; S2, data processing; a control unit processes the collected data to determine the current fire state and the use of the agents; S3, based on the processed data, the control unit automatically selects a suitable fire extinguishing mode and spraying amount, and adjusts the operation of a spraying unit and a supply unit; S4, the control unit continuously receives sensor feedback data, and adjusts the spraying and supply strategies in real time to ensure efficient use and continuous supply of the fire extinguishing agents. The application can realize accurate spraying and continuous supply of the fire extinguishing agents, improve the fire extinguishing efficiency, and reduce agent waste.

Description

Technical Field

[0001] This invention belongs to the field of fire protection technology, specifically relating to a device, control method, and system for the quantitative release and automatic replenishment of fire extinguishing agents. Background Technology

[0002] In the field of modern fire protection technology, fire extinguishing systems have been continuously evolving. Traditional fire extinguishing methods primarily rely on manually controlling the release of extinguishing agents. This method has significant drawbacks and is difficult to meet the needs of complex fire scenes. Manually controlling the release of extinguishing agents is often inaccurate, potentially leading to over- or under-release. In such cases, not only is the extinguishing agent wasted, but insufficient agents may also prevent effective fire suppression. Furthermore, during firefighting, agent replenishment often requires manual operation, increasing the complexity and time required for the operation. When the fire is intense, untimely replenishment may interrupt firefighting efforts, affecting the effectiveness of the extinguishing and even creating greater safety hazards.

[0003] Most existing fire extinguishing agent dispensing devices are single-function devices, lacking automation and intelligent control, and unable to be flexibly adjusted according to actual fire extinguishing needs. These single-function devices are inadequate in the face of complex and ever-changing fire environments. Although some automatic dispensing and replenishment technologies exist, most cannot achieve precise quantitative control, and the dispensing and replenishment processes are difficult to fully automate. Existing fire extinguishing systems often use simple level sensors or time controllers, methods that are lacking in accuracy and response speed, failing to meet the requirements for efficient fire extinguishing.

[0004] These problems and shortcomings of existing technologies often lead to difficulties in accurately controlling the release of extinguishing agents during actual firefighting operations, resulting in low firefighting efficiency; untimely replenishment of extinguishing agents may force the interruption of the firefighting process; and the lack of automated and intelligent control makes it impossible to flexibly adjust the release and replenishment strategies according to the fire situation. The existence of these problems and shortcomings makes it particularly important to develop a control method that can achieve quantitative release and automatic replenishment of extinguishing agents. This method can not only improve firefighting efficiency and effectiveness but also reduce agent waste, ensure a continuous supply of extinguishing agents, and effectively solve many problems in existing technologies. Summary of the Invention

[0005] To address the aforementioned technical shortcomings, the purpose of this invention is to provide a device, control method, and system for the quantitative release and automatic replenishment of fire extinguishing agents. This method enables precise release and continuous supply of fire extinguishing agents, improving fire extinguishing efficiency and reducing agent waste.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution:

[0007] The control method for quantitative release and automatic replenishment of fire extinguishing agents includes the following steps:

[0008] S1. Data Acquisition: Real-time data from the fire scene and inside the equipment is acquired through sensor units.

[0009] S2. Data Processing: The control unit processes the collected data to determine the current fire status and the status of agent usage.

[0010] S3. Based on the processed data, the control unit automatically selects the appropriate fire extinguishing mode and discharge volume, and adjusts the operation of the discharge unit and the supply unit.

[0011] S4. The control unit continuously receives sensor feedback data and adjusts the discharge and replenishment strategies in real time to ensure the efficient use and continuous supply of extinguishing agents.

[0012] Furthermore, the sensor unit in step S1 includes a flow sensor, a pressure sensor, a liquid level sensor, a temperature sensor, and a smoke sensor, which are distributed at various key nodes to collect real-time status data of the fire scene and the inside of the device.

[0013] The flow sensor is used to monitor the flow rate of the extinguishing agent; the pressure sensor is used to monitor the internal pressure of the device; the level sensor is used to monitor the remaining amount of extinguishing agent in the storage unit; the temperature sensor is used to monitor temperature changes at the fire scene; and the smoke sensor is used to monitor the smoke concentration at the fire scene.

[0014] Furthermore, the data processing in step S2 includes: data fusion, whereby the control unit receives and fuses data from various sensors to form a comprehensive judgment on the fire scene and system status; data fusion is achieved through a Kalman filtering algorithm, and the Kalman filtering steps include status prediction and updating;

[0015] The prediction steps involve the following formulas:

[0016] State prediction: (1)

[0017] in, For the first State prediction during the step; Let be the state transition matrix, describing the system from the previous time step. up to the current moment Changes in state; For the previous moment Estimated state at time; To control the input matrix, describe the input Impact on the state; For the current moment Control input;

[0018] Error covariance prediction: (2)

[0019] in, Predict the state error covariance matrix at the current moment and describe the distribution of the prediction error; This is the error variance matrix of the previous time step; This is the state transition matrix; This is the process noise covariance matrix, which describes the uncertainty or noise in the system process;

[0020] The update steps involve the following formulas:

[0021] Kalman gain calculation: (3)

[0022] in, Kalman gain describes how predicted values ​​are combined with measured values; The predicted value of the error covariance matrix; The measurement matrix describes how the state vector is mapped to the measurement space; To measure the noise covariance matrix, describe the uncertainty in the measurement;

[0023] Status Update: (4)

[0024] in, This is the updated state estimate; These are measured values; The measurement model predicts the value, representing the measured value calculated based on the predicted state.

[0025] Error covariance update: (5)

[0026] in, The updated error covariance matrix describes the error of the updated state estimate; It is the identity matrix;

[0027] The control unit uses a state transition matrix. Measurement matrix And based on sensor data Fire state estimation; process noise covariance matrix and measurement noise covariance matrix Used to correct prediction errors and ensure the accuracy of status judgment; through Kalman filtering, the control unit can adjust the judgment results in real time when receiving sensor data to adapt to changes in the fire scene and dynamically adjust the release and replenishment strategy of extinguishing agents.

[0028] Data filtering and correction: Data filtering uses moving average filtering or median filtering to smooth sensor data and eliminate random noise or isolated outliers; Data correction uses a Kalman filtering algorithm to dynamically correct sensor data, specifically including state prediction and update steps. The prediction step uses the state prediction formula and the error covariance prediction formula; the update step uses the Kalman gain formula and the state update formula; Outlier detection and removal removes abnormal sensor data that exceeds a reasonable range based on a set threshold, ensuring data accuracy.

[0029] Status assessment: Using fire models and chemical usage models, the current fire status and chemical consumption are assessed; Fire intensity assessment: Based on data from temperature and smoke sensors, the fire intensity is assessed using fire intensity formulas, and the rate of change of fire intensity is used to evaluate the intensity. Assess the fire's spread trend; assess chemical consumption: based on data from flow and level sensors, calculate the consumption rate and remaining quantity of chemicals using chemical consumption rate and remaining quantity formulas; determine the degree of fire control by combining fire intensity and chemical consumption data using fire status assessment formulas.

[0030] Formulas involved in fire intensity assessment:

[0031] Fire intensity formula: Let the fire intensity be... This is a comprehensive evaluation value based on temperature sensor data. and smoke concentration sensor data The formula for assessing fire intensity is:

[0032] (6)

[0033] in: and It is a weighting coefficient that reflects the different effects of temperature and smoke on fire intensity, and can be determined through experimental or empirical data.

[0034] Fire spread trend assessment: The fire spread trend can be assessed by the rate of change of fire intensity. If the fire intensity increases over time, it indicates a tendency for the fire to spread; the rate of change of fire intensity... Indicates the trend of fire spread:

[0035] (7)

[0036] like This indicates that the fire intensity is increasing and the possibility of it spreading is greater; conversely, if... If so, the fire may be weakening;

[0037] Formulas involved in drug consumption assessment:

[0038] Formula for drug consumption rate: Let the drug flow rate be... The unit is The rate of drug consumption Calculations can be made using flow sensor data:

[0039] (8)

[0040] Among them, traffic Measured in real time by a flow sensor;

[0041] Formula for remaining amount of medicine: Remaining amount of medicine Data from the liquid level sensor Calculate; assume the initial total amount of the reagent is... Then at a certain moment The remaining amount of the medicine at that time was:

[0042] (9)

[0043] This formula represents the integral of the total amount of medicine consumed from the initial time to the current time, based on the flow rate measured by the flow sensor. In time The points displayed will show the total consumption;

[0044] The formulas involved in the condition assessment are:

[0045] Fire status assessment formula: Taking into account both fire intensity and agent consumption rate, the fire status assessment formula is as follows:

[0046] (10)

[0047] in: It is a fire condition assessment value; yes An empirical coefficient is used to adjust the relative influence of fire intensity and agent consumption rate; if This indicates that the fire situation remains quite serious;

[0048] like This indicates that the fire may have been brought under control.

[0049] Furthermore, the fire extinguishing mode selection in step S3 specifically includes: the control unit automatically selecting a suitable fire extinguishing mode based on the fire status and on-site needs; a fire extinguishing mode library with multiple preset fire extinguishing modes, each corresponding to a different fire scenario; and mode matching, selecting the optimal fire extinguishing mode based on fire intensity, spread trend, and remaining agent quantity.

[0050] The calculation of the discharge volume in step S3 specifically includes: based on the fire intensity Fire extinguishing mode demand coefficient Calculate the required amount of extinguishing agent to be released. Its formula is:

[0051] (11)

[0052] in, As an adjustment constant, This refers to the remaining amount of medication.

[0053] The operation of adjusting the spraying unit and the refueling unit includes: optimizing the spraying volume, using optimization algorithms to adjust the spraying parameters to ensure maximum agent utilization;

[0054] The replenishment strategy is formulated based on the drug consumption rate and remaining quantity; replenishment trigger conditions are set to ensure the continuity of drug supply.

[0055] Furthermore, the real-time adjustment in S4 includes: a feedback mechanism, wherein the control unit continuously receives sensor feedback data and uses PID control formula 11 to adjust the spray and replenishment parameters in real time;

[0056] Closed-loop control continuously adjusts the discharge and replenishment parameters based on feedback data to ensure stable system operation; dynamic adjustment is made according to the rate of change of fire intensity. and drug consumption rate Formula 12 is used to dynamically adjust the discharge rate; Formula 13 is used to automatically adjust the discharge rate and extinguishing mode when the fire intensity changes; and Formula 13 is used to optimize agent consumption based on the current agent consumption rate. and forecasting needs Optimize the supply amount using Formula 14;

[0057] Intelligent prediction utilizes machine learning models to predict fire development and chemical demand, forecasting fire development based on Formula 15; chemical demand prediction, based on the current consumption rate and fire forecast, calculates chemical demand in advance using Formula 16 to optimize the replenishment plan;

[0058] Closed-loop control formula: A closed-loop control system can adjust the injection quantity and supply parameters through proportional-integral-derivative (PID) control; the PID control formula is as follows:

[0059] (12)

[0060] in, It is a control signal indicating the adjustment of the discharge or replenishment volume; This is the error value. It is a set value (target fire intensity or agent consumption rate). It is feedback data (actual fire intensity or chemical consumption rate). This is the proportionality coefficient. The integral coefficient is... These are the differential coefficients;

[0061] Dynamic adjustment formula: Dynamic release rate of extinguishing agent It can be based on the rate of change of fire intensity The drug consumption rate is adjusted as follows:

[0062] (13)

[0063] in, This is the adjusted spray volume; and It is an adjustment coefficient that controls the impact of changes in fire intensity and agent consumption on the discharge volume;

[0064] Fire status response formula: When the fire intensity changes significantly, the system automatically adjusts the extinguishing mode and discharge rate according to the new fire status.

[0065] (14)

[0066] in, For the new fire intensity, The newly selected fire suppression mode.

[0067] Supply optimization formula: Supply frequency and supply amount of medicine It can be determined by the current rate of drug consumption. and projected future demand The calculation shows that:

[0068] (15)

[0069] in, For adjustment coefficients, This is the future demand for chemicals predicted based on the current consumption rate and the fire's development.

[0070] Fire prediction model formula: Based on historical and real-time data, machine learning models predict future changes in fire intensity. This allows for advance adjustments to firefighting strategies. The prediction formula can be expressed as:

[0071] (16)

[0072] in, It is the basic prediction function of machine learning models (such as decision trees, support vector machines, etc.); These are the weights of each model; The input data includes historical fire data, real-time sensor data, etc.

[0073] Formula for predicting drug demand: Based on the current rate of drug consumption Fire development prediction The future demand for pharmaceuticals It can be calculated using the following formula:

[0074] (17)

[0075] Furthermore, it also includes safety and anomaly handling, specifically including: fault detection and handling, real-time monitoring of device status, and timely handling of anomalies; automatic diagnosis, the device has automatic diagnostic functions, can identify problems and issue alarms; emergency measures, in the event of a fault, the device automatically activates the emergency plan to ensure that the fire extinguishing process is not affected.

[0076] Furthermore, it also includes device self-learning and optimization, specifically including: data recording and analysis, where the device records all data during each fire extinguishing process to form a historical database; data analysis, where historical data is analyzed regularly to identify and improve deficiencies in the fire extinguishing strategy; self-learning algorithms, where self-learning algorithms are used to continuously optimize the fire extinguishing mode and discharge strategy to improve the device's intelligence level; and parameter adjustment, where control parameters are autonomously adjusted based on historical data and real-time feedback to improve fire extinguishing efficiency and reliability.

[0077] This invention also relates to a control system for the quantitative release and automatic replenishment of fire extinguishing agents, comprising:

[0078] The data acquisition module is used to collect real-time status data from the fire scene and the internal system.

[0079] The data processing module is used to process the data collected by the data acquisition module to determine the current fire status and the status of agent usage.

[0080] The decision-making module automatically selects the appropriate fire extinguishing mode and discharge volume based on the data processed by the data processing module, and adjusts the discharge and resupply operations.

[0081] The real-time adjustment module adjusts the spraying and replenishment strategies in real time based on data collected by the continuously received data acquisition module, ensuring the efficient use and continuous supply of extinguishing agents.

[0082] Furthermore, it also includes a security and anomaly handling module and a self-learning and optimization module;

[0083] The safety and anomaly handling module is used to monitor the device status in real time, handle anomalies promptly, automatically diagnose and identify problems, and issue alarms.

[0084] The self-learning and optimization module is used to periodically analyze data from historical firefighting processes, identify and improve deficiencies in firefighting strategies, continuously optimize firefighting modes and discharge strategies, and autonomously adjust control parameters based on historical data and real-time feedback.

[0085] The present invention also relates to a device for quantitative discharge and automatic replenishment of fire extinguishing agent, comprising: a fire extinguishing agent storage unit, a fire extinguishing agent discharge unit, a sensor unit, a control unit and a replenishment unit;

[0086] The fire extinguishing agent storage unit is in the form of an agent tank for storing fire extinguishing agents; the fire extinguishing agent dispensing unit dispenses the agent through nozzles, the opening and closing of which is controlled by a control unit; the sensor unit includes a level sensor, a flow sensor, a pressure sensor, a temperature sensor, and a smoke sensor for monitoring agent dosage, dispensing status, and fire conditions; the control unit has a built-in computer-readable storage medium for adjusting the dispensing volume and replenishment strategy in real time based on sensor data; the replenishment unit is used to automatically replenish the fire extinguishing agent to the storage unit and includes agent delivery pipelines and a pump.

[0087] The beneficial effects of this invention are as follows:

[0088] 1. Precise Quantitative Discharge: Existing technologies often rely on manual control in traditional fire extinguishing systems, making it difficult to achieve precise discharge of extinguishing agents. This can lead to over-discharge or under-discharge, affecting extinguishing efficiency and effectiveness. The advantage of this invention is that it uses flow and pressure sensors to monitor the agent discharge rate in real time, combined with a PID control algorithm, to achieve precise quantitative discharge of the extinguishing agent. The control unit dynamically adjusts the discharge rate based on real-time data, ensuring efficient use of the extinguishing agent and reducing waste.

[0089] 2. Automated and Intelligent Control: Existing technologies often rely on simple level sensors or time controllers in their fire suppression systems, lacking automated and intelligent control. This prevents flexible adjustments to discharge and replenishment strategies based on fire conditions. The advantages of this invention lie in its use of multiple sensors to monitor the fire scene and system status in real time, and its intelligent control algorithm to automatically select the fire suppression mode and discharge volume. The system possesses self-learning and optimization capabilities, continuously improving fire suppression efficiency and reliability, and enabling rapid response and effective fire suppression in complex fire environments.

[0090] 3. Continuous Agent Supply: Existing technologies often require manual replenishment of agents in traditional fire suppression systems, increasing the complexity and time required for firefighting. Delayed agent replenishment can lead to fire suppression interruptions, affecting the effectiveness of the extinguishing effort. The advantages of this invention are that a liquid level sensor monitors the remaining agent level in the storage unit in real time, and the control unit automatically starts and stops the replenishment unit based on the monitoring data, ensuring a continuous agent supply. During replenishment, the system monitors the replenishment status in real time, ensuring accuracy and timeliness, and avoiding fire suppression interruptions due to insufficient agent.

[0091] 4. Highly Effective Fire Extinguishing: Existing technologies suffer from a lack of coordination in the discharge and replenishment processes of existing fire extinguishing systems. The discharge and replenishment volumes are difficult to dynamically adjust according to fire development, resulting in poor fire extinguishing effectiveness. The advantages of this invention are that the control algorithm can adjust the discharge and replenishment strategies in real time based on fire development and agent consumption. Through multi-point monitoring and coordinated control, the system ensures uniform and effective coverage of the agent discharge, improving fire extinguishing efficiency and effectiveness, and making it suitable for various complex fire scenarios.

[0092] 5. Safety and Reliability: Existing technologies suffer from limited fault detection and handling capabilities in traditional fire suppression systems. System malfunctions can disrupt the fire suppression process, posing significant safety hazards. The advantages of this invention include a built-in fault detection and handling mechanism that enables real-time monitoring of the system status and timely handling of anomalies. The system possesses automatic diagnostic and emergency response functions, ensuring the continuity and safety of the fire suppression process and improving system reliability and safety. Attached Figure Description

[0093] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0094] Figure 1 The flowchart illustrates the control method for quantitative release and automatic replenishment of fire extinguishing agents provided in Embodiment 1 of the present invention. Detailed Implementation

[0095] 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.

[0096] Example 1

[0097] like Figure 1 As shown, the control method for quantitative release and automatic replenishment of fire extinguishing agents includes the following steps:

[0098] S1. Data Acquisition: Real-time data from the fire scene and inside the equipment is acquired through sensor units.

[0099] The sensor unit includes a flow sensor, a pressure sensor, a liquid level sensor, a temperature sensor, and a smoke sensor, which are distributed at various key nodes to collect real-time status data of the fire scene and the inside of the device.

[0100] The flow sensor is used to monitor the flow rate of the extinguishing agent; the pressure sensor is used to monitor the internal pressure of the device; the level sensor is used to monitor the remaining amount of extinguishing agent in the storage unit; the temperature sensor is used to monitor temperature changes at the fire scene; and the smoke sensor is used to monitor the smoke concentration at the fire scene.

[0101] This embodiment uses a flow sensor to monitor the flow rate of the sprayed agent in real time. Flow and pressure sensors also monitor the agent flow rate and system pressure in real time. Environmental sensors (such as temperature and smoke sensors) monitor changes at the fire scene in real time and transmit the data to the control unit. The pressure sensor monitors the pressure in the spray system to ensure stability during the spraying process. The environmental sensors, such as temperature and smoke sensors, monitor changes at the fire scene, providing data support for adjusting the spraying strategy.

[0102] S2. Data Processing: The control unit processes the collected data to determine the current fire status and the status of agent usage.

[0103] The data processing in step S2 includes: data fusion, where the control unit receives and fuses data from various sensors to form a comprehensive judgment of the fire scene and system status; data fusion is achieved through a Kalman filter algorithm, and the Kalman filter steps include state prediction and updating; the state prediction formula is... ,in This is the state transition matrix. The error covariance prediction is then... The control unit uses these formulas to predict the state of the fire scene, and after receiving sensor data, it uses the Kalman gain formula... The assessment is then revised to form a comprehensive judgment of the fire situation, and the firefighting strategy is dynamically adjusted accordingly.

[0104] The prediction steps involve the following formulas:

[0105] State prediction: (1)

[0106] in, For the first State prediction during the step; Let be the state transition matrix, describing the system from the previous time step. up to the current moment Changes in state; For the previous moment Estimated state at time; To control the input matrix, describe the input Impact on the state; For the current moment Control input;

[0107] Error covariance prediction: (2)

[0108] in, Predict the state error covariance matrix at the current moment and describe the distribution of the prediction error; This is the error variance matrix of the previous time step; This is the state transition matrix; This is the process noise covariance matrix, which describes the uncertainty or noise in the system process;

[0109] The update steps involve the following formulas:

[0110] Kalman gain calculation: (3)

[0111] in, Kalman gain describes how predicted values ​​are combined with measured values; The predicted value of the error covariance matrix; The measurement matrix describes how the state vector is mapped to the measurement space; To measure the noise covariance matrix, describe the uncertainty in the measurement;

[0112] Status Update: (4)

[0113] in, This is the updated state estimate; These are measured values; The measurement model predicts the value, representing the measured value calculated based on the predicted state.

[0114] Error covariance update: (5)

[0115] in, The updated error covariance matrix describes the error of the updated state estimate; It is the identity matrix;

[0116] The control unit uses a state transition matrix. Measurement matrix And based on sensor data Fire state estimation; process noise covariance matrix and measurement noise covariance matrix Used to correct prediction errors and ensure the accuracy of status judgment; through Kalman filtering, the control unit can adjust the judgment results in real time when receiving sensor data to adapt to changes in the fire scene and dynamically adjust the release and replenishment strategy of extinguishing agents.

[0117] Data filtering and correction: Data filtering uses moving average filtering or median filtering to smooth sensor data and eliminate random noise or isolated outliers; Data correction uses a Kalman filtering algorithm to dynamically correct sensor data, specifically including state prediction and update steps. The prediction step uses the state prediction formula and the error covariance prediction formula; the update step uses the Kalman gain formula and the state update formula; Outlier detection and removal removes abnormal sensor data that exceeds a reasonable range based on a set threshold, ensuring data accuracy.

[0118] Status assessment: Using fire models and chemical usage models, the current fire status and chemical consumption are assessed; Fire intensity assessment: Based on data from temperature and smoke sensors, the fire intensity is assessed using fire intensity formulas, and the rate of change of fire intensity is used to evaluate the intensity. Assess the fire's spread trend; assess chemical consumption: based on data from flow and level sensors, calculate the consumption rate and remaining quantity of chemicals using chemical consumption rate and remaining quantity formulas; determine the degree of fire control by combining fire intensity and chemical consumption data using fire status assessment formulas.

[0119] Formulas involved in fire intensity assessment:

[0120] Fire intensity formula: Let the fire intensity be... This is a comprehensive evaluation value based on temperature sensor data. and smoke concentration sensor data The formula for assessing fire intensity is:

[0121] (6)

[0122] in: and It is a weighting coefficient that reflects the different effects of temperature and smoke on fire intensity, and can be determined through experimental or empirical data.

[0123] Fire spread trend assessment: The fire spread trend can be assessed by the rate of change of fire intensity. If the fire intensity increases over time, it indicates a tendency for the fire to spread; the rate of change of fire intensity... Indicates the trend of fire spread:

[0124] (7)

[0125] like This indicates that the fire intensity is increasing and the possibility of it spreading is greater; conversely, if... If so, the fire may be weakening;

[0126] Formulas involved in drug consumption assessment:

[0127] Formula for drug consumption rate: Let the drug flow rate be... The unit is The rate of drug consumption Calculations can be made using flow sensor data:

[0128] (8)

[0129] Among them, traffic Measured in real time by a flow sensor;

[0130] Formula for remaining amount of medicine: Remaining amount of medicine Data from the liquid level sensor Calculate; assume the initial total amount of the reagent is... Then at a certain moment The remaining amount of the medicine at that time was:

[0131] (9)

[0132] This formula represents the integral of the total amount of medicine consumed from the initial time to the current time, based on the flow rate measured by the flow sensor. In time The points displayed will show the total consumption;

[0133] The formulas involved in the condition assessment are:

[0134] Fire status assessment formula: Taking into account both fire intensity and agent consumption rate, the fire status assessment formula is as follows:

[0135] (10)

[0136] in: It is a fire condition assessment value; yes An empirical coefficient is used to adjust the relative influence of fire intensity and agent consumption rate; if This indicates that the fire situation remains quite serious;

[0137] like This indicates that the fire may have been brought under control.

[0138] S3. Based on the processed data, the control unit automatically selects the appropriate fire extinguishing mode and discharge volume, and adjusts the operation of the discharge unit and the supply unit.

[0139] The fire extinguishing mode selection in step S3 specifically includes: the control unit automatically selecting the appropriate fire extinguishing mode according to the fire status and on-site needs; a fire extinguishing mode library with multiple preset fire extinguishing modes, each corresponding to different fire scenarios; and mode matching, selecting the optimal fire extinguishing mode based on fire intensity, spread trend, and remaining agent quantity.

[0140] The calculation of the discharge volume in step S3 specifically includes: based on the fire intensity Fire extinguishing mode demand coefficient Calculate the required amount of extinguishing agent to be released. Its formula is:

[0141] (11)

[0142] in, As an adjustment constant, This refers to the remaining amount of medication.

[0143] The operation of adjusting the spraying unit and the refueling unit includes: optimizing the spraying volume, using optimization algorithms to adjust the spraying parameters to ensure maximum agent utilization;

[0144] The replenishment strategy is formulated based on the drug consumption rate and remaining quantity; replenishment trigger conditions are set to ensure the continuity of drug supply.

[0145] The automatic replenishment control function of this invention includes a liquid level detection function, which uses a liquid level sensor to monitor the remaining amount of extinguishing agent in the storage unit in real time and transmit the data to the control unit; data processing, which allows the control unit to determine whether the current dosage is lower than a preset safe liquid level based on the data from the liquid level sensor; and multi-point monitoring, which uses multiple liquid level sensors distributed in different locations within a large storage unit to ensure the comprehensiveness and accuracy of agent monitoring.

[0146] The automatic replenishment control in the aforementioned automatic replenishment control includes: starting the replenishment unit, where the control unit issues a command to start the replenishment unit when the liquid level is lower than a preset value; a delivery pipeline and pump, the replenishment unit including the delivery pipeline and pump, responsible for delivering the extinguishing agent from the storage tank to the storage unit; the control unit applying a control algorithm to dynamically adjust the pump's working state and delivery speed based on data from the liquid level sensor to ensure the stability and efficiency of agent replenishment; replenishment quantity control by the control unit, where the control unit precisely controls the replenishment quantity based on real-time liquid level data to avoid over- or under-replenishment; and a flow sensor, installed on the replenishment pipeline to monitor the flow rate of the replenished agent in real time, ensuring the controllability of the replenishment process.

[0147] The feedback confirmation in the automatic quality replenishment control includes: continuous monitoring, where a level sensor continuously monitors the liquid level in the storage unit during replenishment; data feedback, where data from the level sensor is continuously fed back to the control unit, which calculates the replenishment progress in real time; automatic stop, where the control unit issues a command to immediately stop the replenishment unit when the liquid level reaches the preset level; valve control, where the control valve of the delivery pipeline is closed to ensure the safety and accuracy of the replenishment process; and pump shutdown, where the pump is stopped to avoid over-replenishment of the liquid.

[0148] S4. The control unit continuously receives sensor feedback data and adjusts the discharge and replenishment strategies in real time to ensure the efficient use and continuous supply of extinguishing agents.

[0149] The real-time adjustment in S4 includes: a feedback mechanism, in which the control unit continuously receives sensor feedback data and uses PID control formula 11 to adjust the spray and replenishment parameters in real time;

[0150] Closed-loop control continuously adjusts the discharge and replenishment parameters based on feedback data to ensure stable system operation; dynamic adjustment is made according to the rate of change of fire intensity. and drug consumption rate Formula 12 is used to dynamically adjust the discharge rate; Formula 13 is used to automatically adjust the discharge rate and extinguishing mode when the fire intensity changes; and Formula 13 is used to optimize agent consumption based on the current agent consumption rate. and forecasting needs Optimize the supply amount using Formula 14;

[0151] Intelligent prediction utilizes machine learning models to predict fire development and chemical demand, forecasting fire development based on Formula 15; chemical demand prediction, based on the current consumption rate and fire forecast, calculates chemical demand in advance using Formula 16 to optimize the replenishment plan;

[0152] Closed-loop control formula: A closed-loop control system can adjust the injection quantity and supply parameters through proportional-integral-derivative (PID) control; the PID control formula is as follows:

[0153] (12)

[0154] in, It is a control signal indicating the adjustment of the discharge or replenishment volume; This is the error value. It is a set value (target fire intensity or agent consumption rate). It is feedback data (actual fire intensity or chemical consumption rate). This is the proportionality coefficient. The integral coefficient is... These are the differential coefficients;

[0155] Dynamic adjustment formula: Dynamic release rate of extinguishing agent It can be based on the rate of change of fire intensity The drug consumption rate is adjusted as follows:

[0156] (13)

[0157] in, This is the adjusted spray volume; and It is an adjustment coefficient that controls the impact of changes in fire intensity and agent consumption on the discharge volume;

[0158] Fire status response formula: When the fire intensity changes significantly, the system automatically adjusts the extinguishing mode and discharge rate according to the new fire status.

[0159] (14)

[0160] in, For the new fire intensity, The newly selected fire suppression mode.

[0161] Supply optimization formula: Supply frequency and supply amount of medicine It can be determined by the current rate of drug consumption. and projected future demand The calculation shows that:

[0162] (15)

[0163] in, For adjustment coefficients, This is the future demand for chemicals predicted based on the current consumption rate and the fire's development.

[0164] Fire prediction model formula: Based on historical and real-time data, machine learning models predict future changes in fire intensity. This allows for advance adjustments to firefighting strategies. The prediction formula can be expressed as:

[0165] (16)

[0166] in, It is the basic prediction function of machine learning models (such as decision trees, support vector machines, etc.); These are the weights of each model; The input data includes historical fire data, real-time sensor data, etc.

[0167] Formula for predicting drug demand: Based on the current rate of drug consumption Fire development prediction The future demand for pharmaceuticals It can be calculated using the following formula:

[0168] (17)

[0169] The feedback control data acquisition for the quantitative discharge control includes: the control unit continuously receives data from flow and pressure sensors, and uses a built-in PID control algorithm to compare and analyze the preset discharge volume and real-time data to calculate the error. The opening of the control valve is adjusted according to the error to precisely control the discharge volume. Data processing includes the built-in algorithm of the control unit comparing and analyzing real-time data and the preset discharge volume. Error calculation includes calculating the error between the actual discharge volume and the preset discharge volume. The control algorithm in the feedback mechanism adopts a proportional-integral-derivative (PID) control algorithm, adjusting the opening of the control valve according to the error to achieve precise control of the discharge volume. Specifically, P (proportional) control: immediately adjusts the valve opening based on the current error. I (integral) control: accumulates past errors and adjusts the discharge strategy to eliminate long-term deviations. D (derivative) control: predicts the error change trend and adjusts in advance to reduce future deviations. Based on traditional PID control, an adaptive control algorithm is introduced to dynamically adjust control parameters based on historical data and real-time feedback, improving control accuracy.

[0170] Intelligent prediction uses machine learning algorithms to predict fire development and chemical consumption, allowing for advance adjustments; fire prediction models, based on historical and real-time data, predict fire development trends and adjust firefighting strategies in advance; chemical demand prediction calculates future chemical demand based on current consumption rates and fire development forecasts, optimizing replenishment plans.

[0171] The dynamic adjustment of the quantitative discharge control system includes fire scene data analysis: the control unit combines data from environmental sensors (such as fire intensity, temperature, smoke concentration, etc.) to dynamically analyze the fire development. Discharge strategy adjustments include: increasing the discharge volume (when the fire intensifies, the control unit increases the valve opening to increase the discharge volume and quickly control the fire); decreasing the discharge volume (when the fire weakens or the extinguishing effect is significant, the control unit reduces the valve opening to decrease the discharge volume and avoid agent waste); switching discharge modes (according to fire type and scene changes, the control unit can switch between different discharge modes (such as continuous discharge, intermittent discharge, etc.) to achieve the best extinguishing effect); multi-point monitoring and coordination (in large fire scenes, the system can work collaboratively through multiple discharge units and sensors to ensure uniform and effective coverage of agent discharge); area control (discharge strategies are set separately for different fire areas to precisely control the discharge volume in each area); and synchronous adjustment (data sharing and synchronous adjustment among multiple discharge units to ensure overall extinguishing efficiency).

[0172] It also includes safety and anomaly handling procedures, specifically: fault detection and handling, real-time monitoring of device status, and timely handling of anomalies; automatic diagnosis, the device has automatic diagnostic functions, can identify problems and issue alarms; emergency measures, in the event of a fault, the device automatically activates the emergency plan to ensure that the fire extinguishing process is not affected.

[0173] The safety and anomaly handling in the automatic quality replenishment control system includes: safety valves and pressure relief devices, which are installed in the replenishment system to prevent system failures or leaks caused by excessive pressure; fault detection and alarm, with a built-in fault detection mechanism in the control unit to monitor the operating status of the replenishment unit in real time; anomaly handling, where the control unit immediately issues an alarm and starts the backup replenishment system or takes other emergency measures when a fault or anomaly is detected in the replenishment unit; and a backup replenishment system, which is designed with backup replenishment pipelines and pumps to ensure timely switching in case of failure of the main replenishment system and to ensure uninterrupted supply of reagents.

[0174] The fault detection and alarm in the quantitative spray control includes: a built-in fault detection mechanism that promptly issues an alarm and performs self-repair or switches to a backup scheme when a sensor or control unit malfunctions; and emergency shutdown, in extreme cases (such as over-discharge of reagent, system failure, etc.), the control unit can immediately shut down the spray unit to ensure safety.

[0175] It also includes device self-learning and optimization steps, specifically including: data recording and analysis, where the device records all data during each fire extinguishing process to form a historical database; data analysis, where historical data is analyzed regularly to identify and improve deficiencies in the fire extinguishing strategy; self-learning algorithm, where the self-learning algorithm is used to continuously optimize the fire extinguishing mode and discharge strategy to improve the device's intelligence level; and parameter adjustment, where control parameters are autonomously adjusted based on historical data and real-time feedback to improve fire extinguishing efficiency and reliability.

[0176] The intelligent optimization and historical data analysis in the automatic quality replenishment control include: control optimization, where the control unit uses machine learning algorithms to optimize the replenishment strategy based on historical replenishment data and fire scene data, thereby improving replenishment efficiency and reliability; and historical data analysis, which stores data during the replenishment process, analyzes the replenishment situation periodically, identifies and resolves potential problems, and continuously improves system performance.

[0177] This embodiment also relates to a control system for the quantitative release and automatic replenishment of fire extinguishing agents, including:

[0178] The data acquisition module is used to collect real-time status data from the fire scene and the internal system.

[0179] The data processing module is used to process the data collected by the data acquisition module to determine the current fire status and the status of agent usage.

[0180] The decision-making module automatically selects the appropriate fire extinguishing mode and discharge volume based on the data processed by the data processing module, and adjusts the discharge and resupply operations.

[0181] The real-time adjustment module adjusts the spraying and replenishment strategies in real time based on data collected by the continuously received data acquisition module, ensuring the efficient use and continuous supply of extinguishing agents.

[0182] The safety and anomaly handling module is used to monitor the device status in real time, handle anomalies promptly, automatically diagnose and identify problems, and issue alarms.

[0183] The self-learning and optimization module is used to periodically analyze data from historical firefighting processes, identify and improve deficiencies in firefighting strategies, continuously optimize firefighting modes and discharge strategies, and autonomously adjust control parameters based on historical data and real-time feedback.

[0184] The quantitative discharge and automatic replenishment device for fire extinguishing agents in this embodiment includes a fire extinguishing agent storage unit, a fire extinguishing agent discharge unit, a sensor unit, a control unit, and a replenishment unit. The fire extinguishing agent storage unit stores the fire extinguishing agent and typically consists of multiple agent tanks, equipped with a level sensor to monitor the remaining agent quantity. The fire extinguishing agent discharge unit includes nozzles and control valves, and monitors the discharge status using flow and pressure sensors. The sensor unit, installed at key nodes, includes flow sensors, pressure sensors, level sensors, temperature sensors, and smoke sensors to collect real-time status data from the fire scene and within the system. The control unit is the core control system, with built-in control algorithms responsible for data processing and decision-making. The replenishment unit includes agent delivery pipelines and a pump for automatically replenishing the fire extinguishing agent.

[0185] In terms of quantitative discharge control, the device achieves this through the following steps: First, flow and pressure sensors are installed in the discharge unit to monitor the flow and pressure of the extinguishing agent in real time. Simultaneously, environmental sensors (such as temperature and smoke sensors) monitor changes at the fire scene. The control unit continuously receives sensor data and incorporates a PID control algorithm. Based on a comparison between the preset discharge rate and real-time data, it calculates the error and precisely controls the discharge rate by adjusting the opening of the control valve. The control unit dynamically adjusts the discharge strategy based on fire scene data. When the fire intensifies, the control unit increases the valve opening to increase the discharge rate; when the fire weakens, the control unit decreases the valve opening to reduce the discharge rate.

[0186] Regarding automatic quality replenishment control, the system achieves this through the following steps: First, a level sensor is installed in the storage unit to monitor the remaining amount of the reagent in real time. When the level falls below a preset value, the control unit issues a command to start the replenishment unit, which replenishes the reagent to the storage unit via a delivery pipeline and pump. During replenishment, a flow sensor monitors the flow rate of the replenished reagent to ensure the stability and efficiency of the replenishment process. Simultaneously, the level sensor continuously monitors the reagent level in the storage unit, and when the level reaches the preset value, the control unit issues a command to stop the replenishment unit's operation.

[0187] The control method for the quantitative discharge and automatic replenishment device of fire extinguishing agents mainly includes the following: First, real-time data from the fire scene and within the system is collected through sensor units. The control unit processes the collected data to determine the current fire status and agent usage. Based on the processed data, the control unit automatically selects the appropriate fire extinguishing mode and discharge rate, and adjusts the operation of the discharge and replenishment units. The control unit continuously receives sensor feedback data and adjusts the discharge and replenishment strategies in real time to ensure the efficient utilization and continuous supply of fire extinguishing agents.

[0188] Example 2

[0189] Taking a fire extinguishing system in an industrial plant as an example, the system is equipped with multiple agent storage tanks, each with a level sensor. Discharge units are installed in different areas of the plant, covering the entire area. The control unit receives sensor data and automatically adjusts the discharge rate in each area according to the fire situation. When the agent in a certain area is consumed too quickly, the system automatically activates the replenishment unit to replenish the agent.

[0190] Example 3

[0191] This home's smart fire suppression system includes a small agent storage tank with a level sensor monitoring the agent dosage in real time. Discharge units are installed in high-risk areas such as the kitchen and living room, using smart control valves to regulate the discharge rate. When a fire is detected, the control unit automatically adjusts the discharge rate based on the fire's intensity and simultaneously activates the resupply unit to ensure agent supply. The system can also integrate with smart home devices, such as smoke detectors and home monitoring systems, providing comprehensive safety protection.

[0192] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for controlling the quantitative release and automatic replenishment of fire extinguishing agents, characterized in that, Includes the following steps: S1. Data Acquisition: Real-time data from the fire scene and inside the equipment is acquired through sensor units. S2. Data Processing: The control unit processes the collected data to determine the current fire status and the status of agent usage. S3. Based on the processed data, the control unit automatically selects the appropriate fire extinguishing mode and discharge volume, and adjusts the operation of the discharge unit and the supply unit. S4. The control unit continuously receives sensor feedback data and adjusts the discharge and replenishment strategies in real time to ensure the efficient use and continuous supply of extinguishing agents. The real-time adjustment in S4 includes: a feedback mechanism, in which the control unit continuously receives sensor feedback data and uses PID control formula 11 to adjust the spray and replenishment parameters in real time; Closed-loop control continuously adjusts the discharge and replenishment parameters based on feedback data to ensure stable system operation; dynamic adjustment is made according to the rate of change of fire intensity. and drug consumption rate Formula 12 is used to dynamically adjust the discharge rate; Formula 13 is used to automatically adjust the discharge rate and extinguishing mode when the fire intensity changes; and Formula 13 is used to optimize agent consumption based on the current agent consumption rate. and forecasting needs Optimize the supply amount using Formula 14; Intelligent prediction utilizes machine learning models to predict fire development and chemical demand, forecasting fire development based on Formula 15; chemical demand prediction, based on the current consumption rate and fire forecast, calculates chemical demand in advance using Formula 16 to optimize the replenishment plan; Closed-loop control formula: The closed-loop control system uses PID control to adjust the injection quantity and replenishment parameters; the PID control formula is as follows: (11)； in, It is a control signal indicating the adjustment of the discharge or replenishment volume; This is the error value. It is a set value. It is feedback data; This is the proportionality coefficient. The integral coefficient is... These are the differential coefficients; Dynamic adjustment formula: Dynamic release rate of extinguishing agent It can be based on the rate of change of fire intensity The drug consumption rate is adjusted as follows: (12)； in, This is the adjusted spray volume; and It is an adjustment coefficient that controls the impact of changes in fire intensity and agent consumption on the discharge volume; Fire status response formula: When the fire intensity changes significantly, the system automatically adjusts the extinguishing mode and discharge rate according to the new fire status. (13)； in, For the new fire intensity, The newly selected fire suppression mode; Supply optimization formula: Supply frequency and supply amount of medicine It can be determined by the current rate of drug consumption. and projected future demand The calculation shows that: (14)； in, For adjustment coefficients, This is the future demand for chemicals predicted based on the current consumption rate and the fire's development. Fire prediction model formula: Based on historical and real-time data, machine learning models predict future changes in fire intensity. To adjust firefighting strategies in advance, the prediction formula can be expressed as: (15)； in, It is the basic prediction function of machine learning models; These are the weights of each model; It is the input data; Formula for predicting drug demand: Based on the current rate of drug consumption Fire development prediction The future demand for pharmaceuticals It can be calculated using the following formula: (16) 。 2. The control method for quantitative release and automatic replenishment of fire extinguishing agents according to claim 1, characterized in that, The sensor unit in step S1 includes a flow sensor, a pressure sensor, a liquid level sensor, a temperature sensor, and a smoke sensor, which are distributed at various key nodes to collect real-time status data of the fire scene and the inside of the device. The flow sensor is used to monitor the flow rate of the extinguishing agent; the pressure sensor is used to monitor the internal pressure of the device; the level sensor is used to monitor the remaining amount of extinguishing agent in the storage unit; the temperature sensor is used to monitor temperature changes at the fire scene; and the smoke sensor is used to monitor the smoke concentration at the fire scene.

3. The control method for quantitative release and automatic replenishment of fire extinguishing agents according to claim 1 or 2, characterized in that, The data processing in step S2 includes: data fusion, where the control unit receives and fuses data from various sensors to form a comprehensive judgment on the fire scene and system status; data fusion is achieved through the Kalman filtering algorithm, and the Kalman filtering steps include status prediction and updating; The prediction steps involve the following formulas: State prediction: (1); in, For the first State prediction during the step; Let be the state transition matrix, describing the system from the previous time step. up to the current moment Changes in state; For the previous moment Estimated state at time; To control the input matrix, describe the input Impact on the state; For the current moment Control input; Error covariance prediction: (2); in, Predict the state error covariance matrix at the current moment and describe the distribution of the prediction error; This is the error variance matrix of the previous time step; This is the state transition matrix; This is the process noise covariance matrix, which describes the uncertainty or noise in the system process; The update steps involve the following formulas: Kalman gain calculation: (3); in, Kalman gain describes how predicted values ​​are combined with measured values; The predicted value of the error covariance matrix; The measurement matrix describes how the state vector is mapped to the measurement space; To measure the noise covariance matrix, describe the uncertainty in the measurement; Status Update: (4); in, This is the updated state estimate; These are measured values; The measurement model predicts the value, representing the measured value calculated based on the predicted state. Error covariance update: (5); in, The updated error covariance matrix describes the error of the updated state estimate; It is the identity matrix; The control unit uses a state transition matrix. Measurement matrix And based on sensor data Fire state estimation; process noise covariance matrix and measurement noise covariance matrix Used to correct prediction errors and ensure the accuracy of status judgment; through Kalman filtering, the control unit can adjust the judgment results in real time when receiving sensor data to adapt to changes in the fire scene and dynamically adjust the release and replenishment strategy of extinguishing agents. Data filtering and correction: Data filtering uses moving average filtering or median filtering to smooth sensor data and eliminate random noise or isolated outliers; Data correction uses a Kalman filtering algorithm to dynamically correct sensor data, specifically including state prediction and update steps. The prediction step uses the state prediction formula and the error covariance prediction formula; the update step uses the Kalman gain formula and the state update formula; Outlier detection and removal removes abnormal sensor data that exceeds a reasonable range based on a set threshold, ensuring data accuracy. Status assessment: Using fire models and chemical usage models, the current fire status and chemical consumption are assessed; Fire intensity assessment: Based on data from temperature and smoke sensors, the fire intensity is assessed using fire intensity formulas, and the rate of change of fire intensity is used to evaluate the intensity. Assess the fire's spread trend; assess chemical consumption: based on data from flow and level sensors, calculate the consumption rate and remaining quantity of chemicals using chemical consumption rate and remaining quantity formulas; determine the degree of fire control by combining fire intensity and chemical consumption data using fire status assessment formulas. Formulas involved in fire intensity assessment: Fire intensity formula: Let the fire intensity be... This is a comprehensive evaluation value based on temperature sensor data. and smoke concentration sensor data The formula for assessing fire intensity is: (6)； in: and It is a weighting coefficient that reflects the different effects of temperature and smoke on fire intensity, and can be determined through experimental or empirical data. Fire spread trend assessment: The fire spread trend can be assessed by the rate of change of fire intensity. If the fire intensity increases over time, it indicates that the fire is spreading. (The rate of change of fire intensity is also relevant.) Indicates the trend of fire spread: (7)； like This indicates that the fire intensity is increasing and the possibility of it spreading is greater; conversely, if... If so, the fire may be weakening; Formulas involved in drug consumption assessment: Formula for drug consumption rate: Let the drug flow rate be... The unit is The rate of drug consumption Calculations can be made using flow sensor data: (8）； Among them, traffic Measured in real time by a flow sensor; Formula for remaining amount of medicine: Remaining amount of medicine Data from the liquid level sensor Calculate; assume the initial total amount of the reagent is... Then at a certain moment The remaining amount of the medicine at that time was: （9）； This formula represents the integral of the total amount of medicine consumed from the initial time to the current time, based on the flow rate measured by the flow sensor. In time The points displayed will show the total consumption; The formulas involved in the condition assessment are: Fire status assessment formula: Taking into account both fire intensity and agent consumption rate, the fire status assessment formula is as follows: （10）； in: It is a fire condition assessment value; yes An empirical coefficient is used to adjust the relative influence of fire intensity and agent consumption rate; if This indicates that the fire situation remains quite serious. like This indicates that the fire may have been brought under control.

4. The control method for quantitative discharge and automatic replenishment of fire extinguishing agents according to claim 3, characterized in that, The fire extinguishing mode selection in step S3 specifically includes: the control unit automatically selecting the appropriate fire extinguishing mode according to the fire status and on-site needs; a fire extinguishing mode library with multiple preset fire extinguishing modes, each corresponding to different fire scenarios; and mode matching, selecting the optimal fire extinguishing mode based on fire intensity, spread trend, and remaining agent quantity. The calculation of the discharge volume in step S3 specifically includes: based on the fire intensity Fire extinguishing mode demand coefficient Calculate the required amount of extinguishing agent to be released. Its formula is: （11）； in, As an adjustment constant, This refers to the remaining amount of medication. The operation of adjusting the spraying unit and the refueling unit includes: optimizing the spraying volume, using optimization algorithms to adjust the spraying parameters to ensure maximum agent utilization; The replenishment strategy is formulated based on the drug consumption rate and remaining quantity; replenishment trigger conditions are set to ensure the continuity of drug supply.

5. The control method for quantitative discharge and automatic replenishment of fire extinguishing agents according to claim 4, characterized in that, It also includes safety and anomaly handling, specifically: fault detection and handling, real-time monitoring of device status, and timely handling of anomalies; automatic diagnosis, the device has automatic diagnostic functions, can identify problems and issue alarms; emergency measures, in the event of a fault, the device automatically activates the emergency plan to ensure that the fire extinguishing process is not affected.

6. The control method for quantitative release and automatic replenishment of fire extinguishing agents according to claim 1, 4, or 5, characterized in that, It also includes device self-learning and optimization, specifically including: data recording and analysis, where the device records all data during each fire extinguishing process to form a historical database; data analysis, where historical data is analyzed regularly to identify and improve deficiencies in the fire extinguishing strategy; self-learning algorithms, where self-learning algorithms are used to continuously optimize the fire extinguishing mode and discharge strategy to improve the device's intelligence level; and parameter adjustment, where control parameters are autonomously adjusted based on historical data and real-time feedback to improve fire extinguishing efficiency and reliability.

7. A control system for the quantitative release and automatic replenishment of fire extinguishing agents, characterized in that, include: The data acquisition module is used to collect real-time status data from the fire scene and the internal system. The data processing module is used to process the data collected by the data acquisition module to determine the current fire status and the status of agent usage. The decision-making module automatically selects the appropriate fire extinguishing mode and discharge volume based on the data processed by the data processing module, and adjusts the discharge and resupply operations. The real-time adjustment module adjusts the spraying and replenishment strategies in real time based on data collected by the continuously received data acquisition module, ensuring the efficient use and continuous supply of extinguishing agents.

8. The control system for quantitative discharge and automatic replenishment of fire extinguishing agent according to claim 7, characterized in that, It also includes a security and exception handling module and a self-learning and optimization module; The safety and anomaly handling module is used to monitor the device status in real time, handle anomalies promptly, automatically diagnose and identify problems, and issue alarms. The self-learning and optimization module is used to periodically analyze data from historical firefighting processes, identify and improve deficiencies in firefighting strategies, continuously optimize firefighting modes and discharge strategies, and autonomously adjust control parameters based on historical data and real-time feedback.

9. A device for metered dispensing and automatic replenishment of fire extinguishing agent, comprising: The fire extinguishing agent storage unit, fire extinguishing agent dispensing unit, sensor unit, control unit, and supply unit are all included. The fire extinguishing agent storage unit is in the form of an agent tank for storing fire extinguishing agents; the fire extinguishing agent dispensing unit dispenses the agent through nozzles, the opening and closing of which is controlled by a control unit; the sensor unit includes a level sensor, a flow sensor, a pressure sensor, a temperature sensor, and a smoke sensor for monitoring agent dosage, dispensing status, and fire conditions; the control unit has a built-in computer-readable storage medium for adjusting the dispensing volume and replenishment strategy in real time based on sensor data; the replenishment unit is used to automatically replenish the fire extinguishing agent to the storage unit and includes agent delivery pipelines and a pump.

Images