Intelligent fire prevention and control system and method for energy storage power station

Abstract

The invention discloses an intelligent fire prevention and control system and method for an energy storage power station, belongs to the technical field of thermal runaway early warning, and can perform single battery level fire prevention and control based on a multi-source data fusion mode. Specifically, through cooperation of a battery management system, an energy management system and a power conversion system, residual electric quantity balance is carried out on abnormal single batteries, and meanwhile, a ventilation system is linked to inhibit combustible gas accumulation. In specific implementation, a thermal runaway prediction model needs to be constructed to calculate a source point where a fire may occur, on the basis, an independent composite detector is deployed in a battery module for any single battery, and the composite detector is used for collecting physical parameters of the single battery to form a basic data label; and specific numerical values are detected to form a basic data set. The basic data set is input into the thermal runaway prediction model for calculation, so that the risk that a fire may occur on the single battery level can be obtained, and decision judgment is made for the risk.

Description

Technical Field

[0001] The present invention relates to the technical field of early warning technology for thermal runaway of energy storage power stations, and in particular to an intelligent fire prevention and control system and method for energy storage power stations. Background Art

[0002] Although renewable energy (such as solar energy, wind energy, hydropower, biomass energy, etc.) has the advantages of being clean and sustainable, it also faces some technical, economic and environmental challenges, such as low energy density, relatively high intermittency and instability. In order to ensure the stable operation of the power grid, it is crucial to balance the supply and demand of electricity through energy storage power stations, improve the stability of the power grid, and promote the consumption of renewable energy.

[0003] However, current energy storage power stations are prone to fires in high-temperature, high-humidity environments due to factors such as unbalanced charge loads and battery aging. Existing firefighting systems mostly use overall flooding to extinguish fires, and are not sensitive enough to traditional smoke and temperature detection, making it difficult to identify early thermal runaway of battery cells. Therefore, it is difficult to accurately suppress individual batteries, which not only increases the risk of fire, but also leads to waste of fire extinguishing agents and the problem of fire re-ignition. Summary of the Invention

[0004] To this end, the present invention provides an intelligent fire prevention and control system for an energy storage power station to solve the problem in the prior art of fires caused by improper maintenance of energy storage power stations.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] According to the first aspect of the present invention;

[0007] Disclosed is an intelligent fire prevention and control method for an energy storage power station, comprising the following steps:

[0008] 1) Obtain the physical parameters of each single cell in the battery module to form basic data labels and BMS data labels, and at the same time detect specific values ​​to form basic data sets and BMS data sets;

[0009] 2) Train and build a thermal runaway prediction model;

[0010] 3) Input the basic data labels and basic data sets into the thermal runaway prediction model to make early warning evaluations. At the same time, input the BMS data labels and BMS data sets into the battery management system to ensure that the remaining power of each battery module remains consistent;

[0011] 4) Arranging the single cells in a matrix within the battery module and determining the position of each single cell in a coordinate format to generate positioning data;

[0012] 5) Input the early warning evaluation of the thermal runaway prediction model and the location data of the corresponding single battery into the risk management module, and execute the internal risk clearance procedure for the corresponding battery module through the risk management module according to the early warning evaluation level;

[0013] 6) Obtaining fire monitoring data of the battery module, forming an external data label and an external data set, and inputting them into the risk management module; when the value of the external data set exceeds a threshold, executing an external risk clearance procedure for the battery module through the risk management module.

[0014] Furthermore, in step 1), the BMS data tag includes the voltage, current, and state of charge information of the single battery, and the basic data tag includes the temperature, total smoke volume, combustible gas content, and pressure value of the single battery.

[0015] Furthermore, in step 2), the process of constructing the thermal runaway prediction model includes the following steps:

[0016] 21) Under experimental conditions, use sensors to detect the voltage, current, cell surface temperature, state of charge, and health status of the sample battery. At the same time, collect electrolyte gas precipitation ratio, battery surface expansion force, laboratory accelerated aging test and actual failure case data;

[0017] 22) Preprocess the data, normalize the data in units of heat, and calculate the relationship between the quantitative temperature change and heat generation and loss. The calculation formula is:

[0018]

[0019] Where ρ is the average density of the battery material, Cp is the specific heat capacity of the battery, is the rate of change of temperature with time, Q gen is the heat generation rate per unit volume, Q loss is the heat loss rate per unit volume;

[0020] 23) Real-time calculation based on formula When Q gen >>Q gen Q loss >>Q loss hour, Rising sharply until Determine the onset of thermal runaway.

[0021] Furthermore, Q is calculated based on the specific values ​​of BMS data tags and basic data tags. gen and Q loss The value of , where the calculation formula is:

[0022] Q gen=I 2 R int +∑A i e Ert *ΔH i ;

[0023] A i Pre-exponential factor, I 2 R int Ohmic heat, Ert is the activation energy, ΔH i is the reaction enthalpy change, Q gen is the heat generation rate per unit volume;

[0024] Q loss =Q conv +Q cond +Q rad ;

[0025] Q conv For convection cooling, Q cond For conduction cooling, Q rad is radiation heat dissipation, Q loss is the heat loss rate per unit volume.

[0026] Furthermore, the risk control module is an independent fire extinguishing unit configured in each battery module, and the independent fire extinguishing unit is suitable for spraying the fire extinguishing agent onto the corresponding battery module through the nozzle by controlling the mixing solenoid valve according to the positioning data set.

[0027] Furthermore, in step 5), the internal risk clearance procedure includes the following steps:

[0028] 51) When a level 3 risk warning is issued, the battery management system and the power conversion system work together to balance the charge of abnormal single cells to reduce resistance heat generation;

[0029] 52) When a secondary risk warning is issued, on the basis of reducing resistance heat, the independent fire extinguishing unit is activated and ventilation is carried out through the pipeline to reduce the flammable gas content in the battery module and abnormal single battery;

[0030] 53) When a level 1 risk warning is issued, fire extinguishing agent or water mist is sprayed in a targeted manner on the corresponding battery modules on the basis of reducing resistance heat and reducing the content of combustible gas.

[0031] Furthermore, in step 6), the external risk clearance procedure includes the following steps:

[0032] 61) Set warning values ​​according to the early stages of a fire. When the combustible gas content in the battery module and the maximum temperature in the cabin exceed the warning values, use an inert gas with a concentration greater than 35% to spray the location where the temperature is abnormally high;

[0033] 62) Risk values ​​are set according to the fire outbreak stage. When the temperature inside the energy storage station exceeds the risk value, the risk management module is activated to precisely spray fire extinguishing agents at the center of the fire. At the same time, the temperature control system is linked to adjust the air duct to achieve targeted cooling of the fire source area.

[0034] 63) Based on the reinforcement learning algorithm, the risk prevention and control weight parameters are updated at regular intervals, and the mixing ratio of water mist and dry powder in the fire extinguishing agent is dynamically adjusted according to the parameter changes.

[0035] According to the second aspect of the present invention;

[0036] Disclosed is a fire prevention and control system using the above-described intelligent fire prevention and control method for an energy storage power station. The energy storage power station is provided with a plurality of battery modules, each of which contains a plurality of single batteries. The fire prevention and control system includes:

[0037] A composite detector, each of the battery modules is provided with the composite detector;

[0038] A distributed optical fiber temperature sensor is provided on each of the battery modules;

[0039] A linked ventilation system is provided in the energy storage power station;

[0040] an infrared thermal imaging detection device, arranged in the energy storage power station;

[0041] A combustible gas detector is provided in the energy storage power station;

[0042] A fire extinguishing agent injection module extends into the energy storage power station and is used to inject fire extinguishing agent into each battery module to extinguish the fire;

[0043] The PLC controller is respectively connected to the composite detector, distributed optical fiber temperature sensor, linkage ventilation system, infrared thermal imaging detection device, combustible gas detector and fire extinguishing agent injection module by signal. The PLC controller is also respectively connected to the energy management system, power conversion system and battery management system.

[0044] Furthermore, the fire extinguishing agent injection module includes several fire extinguishing containers and corresponding nozzles arranged on one side of the battery module, each of the fire extinguishing containers is connected to one end of the fire extinguishing main pipe, and each of the nozzles is connected to the other end of the fire extinguishing main pipe. The output end of each fire extinguishing container is provided with a mixing solenoid valve, and the input end of each nozzle is provided with a cluster-level solenoid valve.

[0045] The present invention has the following advantages:

[0046] The intelligent fire prevention and control method for energy storage power stations disclosed in this invention is a battery protection safety system based on multi-source data fusion. Using composite sensors, it monitors thermal runaway data from energy storage unit cells (such as lithium-ion batteries and sodium-sulfur batteries) in real time. This significantly improves the problem of traditional smoke and temperature detectors being insufficiently sensitive and unable to identify early-stage thermal runaway (such as electrolyte leakage and gas evolution). Compared to existing technologies, this invention can achieve early warning of potential disasters in energy storage power stations. It can also accurately warn and suppress fire risks at the individual battery module level, thereby reducing the overall use of fire extinguishing agents and the risk of fire re-ignition. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a structural diagram of an intelligent fire prevention and control system for an energy storage power station according to the present invention;

[0048] Figure 2 Generate a flow chart for the internal risk elimination process of the present invention;

[0049] Figure 3 generating a flow chart for the external risk elimination procedure of the present invention;

[0050] As shown in the figure: 1 energy storage station; 2 linked ventilation system; 3 infrared thermal imaging detection device; 4 combustible gas detector; 5 energy management system; 6 power conversion system; 7 battery management system; 8 mixing solenoid valve; 9 fire extinguishing container; 10 cluster solenoid valve; 11 nozzle; 12 composite detector; 13 battery module; 14 distributed fiber optic temperature measurement system; 15 thermal runaway prediction model; 16 risk management module; 17 PLC controller. DETAILED DESCRIPTION

[0051] The following describes the implementation of the present invention using specific embodiments. Those skilled in the art will readily understand the other advantages and benefits of the present invention from the disclosure herein. Obviously, the embodiments described are only a portion of the present invention, not all of it. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are intended to fall within the scope of protection of the present invention.

[0052] Please refer to Figure 1-Figure 3 The present invention discloses an intelligent fire prevention and control method for energy storage power stations. This method primarily utilizes a battery management system 7, an energy management system 5, and a power conversion system 6 to coordinate and balance the remaining charge of abnormal cells, thereby reducing maintenance complexity. It also utilizes a ventilation system 2 to suppress the accumulation of combustible gases. The following describes the technical solutions disclosed in this invention using specific examples.

[0053] In a specific embodiment disclosed in the present invention, it is necessary to construct a thermal runaway prediction model 15 for calculating the possible ignition points of a fire and implementing corresponding disaster reduction and prevention measures. The disaster reduction and prevention measures are mainly implemented by installing a risk control module 16 in the battery module 13. On this basis, an independent composite detector 12 is deployed in any single cell in the battery module 13. The composite detector 12 is used to collect the physical parameters of a single cell to form a basic data label, and detect specific values ​​to form a basic data set. The basic data set is input into the thermal runaway prediction model 15 for calculation, and the risk of fire at the single cell level can be obtained, and a decision can be made on this.

[0054] In this embodiment, several single cells are arranged in a matrix within a single battery module 13. Therefore, the position of a single cell can be determined by coordinates, and then the multiple cells are sorted to form a positioning data set. Therefore, when applying the thermal runaway prediction model 15 to determine the battery status, different cells can be numbered.

[0055] In some embodiments, to maintain smooth communication between the composite detector 12, the thermal runaway prediction model 15, and the battery management system 7, all individual cells within the battery module 13 are connected to the battery management system 7 via a CAN bus. This allows the performance parameters of the individual cells within the battery module 13 to be acquired, thereby forming a BMS data tag and a BMS data set. Furthermore, a backup communication link is provided within the CAN bus so that if the CAN bus is physically disconnected, the backup communication link can be activated to avoid communication interruptions.

[0056] Furthermore, a combustible gas detector 4 and an infrared thermal imaging device 3 are installed within the battery module 13 to collect real-time information about the combustible gas content and maximum temperature within the battery module 13. A distributed fiber-optic temperature measurement system 14 is deployed within the energy storage station 1 to generate external data tags and datasets. This allows for monitoring changes in these tags and datasets, and for executing external risk mitigation procedures. In the event of a fire, the system can reduce the temperature or spray fire extinguishing agents to prevent the fire from spreading and further damage to the battery module 13.

[0057] The thermal runaway prediction model 15 can provide a warning assessment of the safety of individual batteries based on the input basic data set and the BMS data set. Then, based on the warning assessment level, the risk management module 16 uses the corresponding location data to execute an internal risk elimination procedure for the battery module 13, while simultaneously executing an external risk elimination procedure for the energy storage station 1 and the battery module 13.

[0058] In this embodiment, the BMS data tag includes the voltage, current, and state of charge information of the single battery, while the basic data tag includes the temperature, total smoke volume, combustible gas content, and pressure value of the single battery.

[0059] In some embodiments, the construction process of the thermal runaway prediction model 15 includes, first, using reinforcement learning to detect the voltage, current, cell surface temperature, state of charge, and health status of sample batteries through sensors during experimental testing. At the same time, the electrolyte gas precipitation ratio, battery surface expansion force, laboratory accelerated aging test data, and actual failure case data are collected. These are used as samples to learn the value function of the state or state-action pair, select the optimal action based on the value, and derive the basic model, thereby using a neural network to approximate the Q value and solve the high-dimensional state space problem. Then, based on this, the data is preprocessed, the obtained data is normalized in units of heat, and the relationship between the quantitative temperature change and heat generation and loss is calculated. The calculation formula is:

[0060]

[0061] It should be noted that in the formula, ρ is the average density of the battery material, C p is the specific heat capacity of the battery, is the rate of change of temperature with time, Q gen is the heat generation rate per unit volume, Q loss Heat loss rate per unit volume. It can be calculated in real time according to the formula When Q gen >>Q gen Q loss >>Q loss hour, Rising sharply until Determine the onset of thermal runaway.

[0062] In this embodiment, it is necessary to calculate Q based on the specific values ​​of the BMS data tag and the basic data tag. gen and Q loss The value of , where the calculation formula is:

[0063] Q gen =I 2 R int +∑A i e Ert *ΔH i ;

[0064] A i Pre-exponential factor, I 2 R int Ohmic heat, Ert is the activation energy, ΔH i is the reaction enthalpy change;

[0065] Q loss =Q conv +Q cond +Q rad ;

[0066] Q conv For convection cooling, Q cond For conduction cooling, Q rad To dissipate heat through radiation;

[0067] Q conv =hA(TT env );

[0068] j: convection coefficient, A: surface area, T env : ambient temperature;

[0069]

[0070] λ: thermal conductivity, temperature gradient;

[0071]

[0072] ∈: emissivity, σ: Stefan-Boltzmann constant.

[0073] Based on the above calculation formula, according to the combustible gas content and the rate of change of temperature over time in the basic data tag, a risk assessment level can be established for each single cell and a floating threshold can be generated. Specifically, when the combustible gas content and the rate of change of temperature over time are both below the threshold, it is normal. When the combustible gas content and the rate of change of temperature over time are both above the threshold, a level 1 risk warning is activated. When the combustible gas content is above the threshold and the rate of change of temperature over time is below the threshold, a level 2 risk warning is activated. When the combustible gas content is below the threshold and the rate of change of temperature over time is above the threshold, a level 3 risk warning is activated.

[0074] The intelligent fire prevention and control system for energy storage power plants will implement targeted suppression measures based on different risk warning levels. Specifically, the risk control module 16 is an independent fire extinguishing unit configured within each single cell. This independent fire extinguishing unit is adapted to control the mixing solenoid valve 8 based on the positioning data set, spraying the fire extinguishing agent through a pipeline onto the corresponding single cell. In this embodiment, each risk control module 16 is equipped with a backup pipeline. In the event of a pipeline blockage or disconnection, the backup pipeline can be promptly switched to reduce the risk of equipment failure in the event of a fire. Specifically, the risk control weight parameters can be updated at regular intervals based on a reinforcement learning algorithm. The risk control module 16 then uses a programmable logic controller (PLC) 17 as a lower-level controller, and the PLC 17 (programmable logic controller) drives the different mixing solenoid valves 8. By controlling the number of openings and closings of the mixing solenoid valves 8, the ratio of different fire extinguishing agents is achieved. The water mist and dry powder mixture ratio in the fire extinguishing agent is dynamically adjusted based on parameter changes.

[0075] Specifically, during the internal risk clearance process, if a Level 3 risk warning is issued, the battery management system 7 collaborates with the power conversion system 6 to balance the charge of the abnormal single cells to reduce resistive heat generation. If a Level 2 risk warning is issued, in addition to reducing resistive heat generation, the independent fire extinguishing unit is activated to ventilate the battery module 13 and the abnormal single cells through the ducts to reduce the flammable gas content. If a Level 1 risk warning is issued, in addition to reducing both resistive heat generation and flammable gas content, a fire extinguishing agent or fine water mist is sprayed in a targeted manner on the corresponding battery module 13.

[0076] In this embodiment, referring to Figure 1 The mixing solenoid valves 8 are connected to the fire extinguishing containers 9. Different fire extinguishing containers 9 contain different types of fire extinguishing agents, including solid, liquid, or gaseous fire extinguishing agents such as nitrogen, carbon dioxide, and water. The PLC controller 17 is used to open the different mixing solenoid valves 8 to mix the fire extinguishing agents. Furthermore, the cluster-level solenoid valves 10 are connected to the nozzles 11 to adjust the total amount of mixed fire extinguishing agent in the battery module 13. This effectively achieves the desired fire extinguishing effect in the battery module 13 and effectively reduces the amount of mixed fire extinguishing agent used.

[0077] In one embodiment disclosed herein, an external risk elimination program is included for routine equipment inspections to minimize the risk of fire. This program involves locally extinguishing a fire with an inert gas concentration greater than 35% in the early stages of the fire. During the initial outbreak of a fire, the risk management module 16 is activated to precisely spray fire extinguishing agents at the center of the fire, while the temperature control system is simultaneously activated to adjust the air ducts to achieve targeted cooling of the fire area.

[0078] Based on the same inventive concept, the present invention discloses an intelligent fire prevention and control system for energy storage power plants. The system comprises several energy storage stations 1, each equipped with several battery modules 13, each containing several single cells. Single cells are the smallest energy storage units in an energy storage plant. The system aims to achieve single-cell-level fire prevention and control by building a model algorithm and integrating multi-source data. The energy storage stations 1 are equipped with a coordinated ventilation system 2, an infrared thermal imaging detection device 3, and a combustible gas detector 4.

[0079] In some embodiments, the fire extinguishing agent injection module includes several fire extinguishing containers 9 and corresponding nozzles 11 arranged on one side of the battery module 13, each of the fire extinguishing containers 9 is connected to one end of the fire extinguishing main pipe, and each of the nozzles 11 is connected to the other end of the fire extinguishing main pipe. The output end of each fire extinguishing container 9 is provided with a mixing solenoid valve 8, and the input end of each of the nozzles 11 is provided with a cluster-level solenoid valve 10.

[0080] In this embodiment, the linked ventilation system 2, infrared thermal imaging detection device 3, and combustible gas detector 4 are all signal-connected to an editable logic controller 17, which is in turn connected to a plurality of mixing solenoid valves 8 and a plurality of cluster solenoid valves 10. The mixing solenoid valves 8 are mounted on the fire extinguishing container 9, while the cluster solenoid valves 10 are connected to the sprinkler heads 11, which are mounted on the battery module 13.

[0081] The above shows and describes the basic principles, main features, and advantages of the present invention. The various components mentioned in the present invention are conventional technologies in the prior art. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and improvements may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and improvements are intended to fall within the scope of the invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent fire prevention and control method for energy storage power station, characterized in that: The steps include: 1) obtaining the physical parameters of each single battery of the battery module (13) to form a basic data label and a BMS data label, and detecting specific values ​​to form a basic data set and a BMS data set; 2) Training and building a thermal runaway prediction model (15); 3) Inputting the basic data labels and basic data sets into the thermal runaway prediction model (15) to make an early warning evaluation; at the same time, inputting the BMS data labels and BMS data sets into the battery management system (7) to keep the remaining power of each battery module consistent; 4) Arranging the single cells in a matrix manner within the battery module (13), and determining the position of each single cell in a coordinate manner to form positioning data; 5) inputting the early warning evaluation of the thermal runaway prediction model (15) and the location data of the corresponding single battery into the risk control module (16), and executing the internal risk clearance procedure for the corresponding battery module (13) through the risk control module (16) according to the early warning evaluation level; 6) Obtaining fire monitoring data of the battery module (13), forming an external data tag and an external data set, and inputting them into the risk control module (16); when the value of the external data set exceeds a threshold, executing an external risk clearance procedure for the battery module (13) through the risk control module (16).

2. The intelligent fire prevention and control method for energy storage power station according to claim 1 is characterized in that: In step 1), the BMS data tag includes the voltage, current, and state of charge information of the single battery, and the basic data tag includes the temperature, total smoke volume, combustible gas content, and pressure value of the single battery.

3. The intelligent fire prevention and control method for energy storage power station according to claim 1 is characterized in that: In step 2), the construction process of the thermal runaway prediction model (15) includes the following steps: 21) Under experimental conditions, use sensors to detect the voltage, current, cell surface temperature, state of charge, and health status of the sample battery. At the same time, collect electrolyte gas precipitation ratio, battery surface expansion force, laboratory accelerated aging test and actual failure case data; 22) Preprocess the data, normalize the data in units of heat, and calculate the relationship between the quantitative temperature change and heat generation and loss. The calculation formula is: Where ρ is the average density of the battery material, Cp is the specific heat capacity of the battery, is the rate of change of temperature with time, Q gen is the heat generation rate per unit volume, Q loss is the heat loss rate per unit volume; 23) Real-time calculation based on formula When Q gen >>Q gen Q loss >>Q loss hour, Rising sharply until Determine the onset of thermal runaway.

4. The intelligent fire prevention and control method for energy storage power station according to claim 2 is characterized in that: Calculate Q based on the specific values ​​of BMS data tags and basic data tags gen and Q loss The value of , where the calculation formula is: Q gen =I 2 R int +ΣA i e Ert *ΔH i ; A i Pre-exponential factor, I 2 R int Ohmic heat, Ert is the activation energy, ΔH i is the reaction enthalpy change, Q gen is the heat generation rate per unit volume; Q loss =Q conv +Q cond +Q rad ; Q conv For convection cooling, Q cond For conduction cooling, Q rad is radiation heat dissipation, Q loss is the heat loss rate per unit volume.

5. The intelligent fire prevention and control method for energy storage power station according to claim 1 is characterized in that: The risk control module (16) is an independent fire extinguishing unit configured in each battery module (13), and the independent fire extinguishing unit is suitable for spraying the fire extinguishing agent onto the corresponding battery module (13) through a nozzle by controlling the mixing solenoid valve (8) according to the positioning data set.

6. The intelligent fire prevention and control method for energy storage power station according to claim 1 is characterized in that: In step 5), the internal risk clearance procedure includes the following steps: 51) When a third-level risk warning is issued, the battery management system (7) cooperates with the power conversion system (6) to balance the charge of abnormal single cells to reduce the generation of resistance heat; 52) When a second-level risk warning is issued, on the basis of reducing the resistance heat, the independent fire extinguishing unit is activated and ventilation is carried out through the pipeline to reduce the flammable gas content in the battery module (13) and the abnormal single battery; 53) When a first-level risk warning is issued, on the basis of reducing resistance heat and reducing the content of combustible gas, the corresponding battery module (13) is sprayed with a fire extinguishing agent or fine water mist in a directional manner.

7. The intelligent fire prevention and control method for energy storage power station according to claim 1 is characterized in that: In step 6), the external risk clearance procedure includes the following steps: 61) Setting a warning value according to the early stage of a fire, when the combustible gas content in the battery module (13) and the maximum temperature in the cabin exceed the warning value, an inert gas with a concentration greater than 35% is sprayed toward the position where the temperature is abnormally high; 62) A risk value is set according to the fire outbreak stage. When the temperature in the energy storage station (1) exceeds the risk value, the risk control module (16) is activated to precisely spray the fire extinguishing agent to the fire center, and at the same time, the temperature control system (2) is linked to adjust the air duct to achieve directional cooling of the fire source area. 63) Based on the reinforcement learning algorithm, the risk prevention and control weight parameters are updated at regular intervals, and the mixing ratio of water mist and dry powder in the fire extinguishing agent is dynamically adjusted according to the parameter changes.

8. A fire prevention and control system for an energy storage power station using the intelligent fire prevention and control method according to any one of claims 1 to 7, wherein a plurality of battery modules (13) are provided in the energy storage power station (1), and a plurality of single cells are provided in the battery modules (13), characterized in that: The prevention and control system includes: A composite detector (12), each of the battery modules (13) is provided with the composite detector (12); A distributed optical fiber temperature sensor (14), each of the battery modules (13) is provided with the distributed optical fiber temperature sensor (14); A linked ventilation system (2) is provided in the energy storage power station (1); An infrared thermal imaging detection device (3) is arranged in the energy storage power station (1); A combustible gas detector (4) is arranged in the energy storage power station (1); A fire extinguishing agent injection module extends into the energy storage power station (1) and is used to inject fire extinguishing agent into each battery module (13) to extinguish a fire; The PLC controller (17) is respectively connected to the composite detector (12), the distributed optical fiber temperature sensor (14), the linkage ventilation system (2), the infrared thermal imaging detection device (3), the combustible gas detector (4) and the fire extinguishing agent injection module via signals. The PLC controller (17) is also respectively connected to the energy management system (5), the power conversion system (6) and the battery management system.

9. The prevention and control system according to claim 8, characterized in that: The fire extinguishing agent injection module includes a plurality of fire extinguishing containers (9) and corresponding nozzles (11) arranged on one side of the battery module (13), each of the fire extinguishing containers (9) is connected to one end of the fire extinguishing main pipe, each of the nozzles (11) is connected to the other end of the fire extinguishing main pipe, the output end of each fire extinguishing container (9) is provided with a mixing solenoid valve (8), and the input end of each nozzle (11) is provided with a cluster-level solenoid valve (10).

Images