Novel liquid nitrogen fire extinguishing and cooling method and system suitable for energy storage power station

Abstract

The invention provides a novel liquid nitrogen fire extinguishing and cooling method and system suitable for an energy storage power station, and relates to the technical field of energy storage power stations. Comprising the steps of setting a composite detector network, collecting environment data in real time and positioning; constructing a thermal runaway early warning model based on a deep neural network, inputting environmental data, and outputting a thermal runaway risk level of each detection point; a fire alarm control system is constructed, and graded response is realized; fire extinguishing process data are recorded, and remote monitoring is achieved; normal operation of the system is recovered. Through efficient monitoring, intelligent evaluation, automatic response, an elastic fire extinguishing mode, digital management and an efficient post-disaster recovery mechanism, the safety and reliability of the energy storage power station are comprehensively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage power stations, and particularly to a novel liquid nitrogen fire extinguishing and temperature reduction method and system applicable to energy storage power stations. Background Art

[0002] Container energy storage systems mostly use lithium batteries as energy storage media. Lithium batteries have the risk that overheating may cause thermal runaway. Once thermal runaway occurs, it may trigger a fire or even an explosion. Batteries are densely arranged inside the container. Once a fire is triggered by a fault in a certain battery, the fire may quickly spread throughout the container. The overheat reaction of the battery will release a large amount of gas, which is extremely likely to cause a combustion explosion accident at high temperatures and is also the main reason for battery explosions. Containers are usually installed in open areas or on rooftops, which makes it difficult for fire rescue to access and increases the difficulty of extinguishing fires. The chemical properties of high-energy-density lithium-ion batteries are very active. Once a lithium battery releases the energy it stores, it is very easy to have an out-of-control chain reaction, thus triggering a combustion explosion.

[0003] Traditional fire extinguishing generally uses gas fire extinguishing agents, water-based fire extinguishing agents and dry powder fire extinguishing agents, which have problems such as low fire extinguishing efficiency, easy reignition after fire extinguishing, inability to suppress explosions, and secondary pollution after fire extinguishing. Gas fire extinguishing agents have a poor cooling effect on batteries, and the battery temperature will rise again, resulting in secondary reignition. The fire extinguishing effect is poor and reignition is likely to occur. A large amount of toxic gases such as hydrogen fluoride are generated in the initial stage of combustion. Although the fire extinguishing technology has a good fire extinguishing effect, it has a poor cooling effect on batteries, and the battery temperature will rise again, resulting in secondary reignition. Water-based fire extinguishing agents consume a large amount of water, have a long fire extinguishing time, are prone to reignition, and in the case of energy storage power stations with very high output voltages, they will cause system short circuits and induce secondary fires, resulting in the overall scrapping of the batteries. Dry powder fire extinguishing agents have a poor fire extinguishing effect and produce a large amount of residues; they have almost no effect on lithium battery fires. At the same time, early warning of the thermal runaway of lithium-ion batteries is an urgent problem to be solved at present. Summary of the Invention

[0004] The present invention provides a novel liquid nitrogen fire extinguishing and temperature reduction method and system applicable to energy storage power stations to solve the defects existing in the prior art.

[0005] On the one hand, the present invention provides a novel liquid nitrogen fire extinguishing and temperature reduction method and system applicable to energy storage power stations, including:

[0006] S1. Set up a composite detector network to collect the environmental data of each detection point in the energy storage cabin in real time. The environmental data includes hydrogen concentration data, carbon monoxide concentration data and temperature data, and locate the battery module corresponding to each detection point.

[0007] S2. Build a thermal runaway warning model based on a deep neural network, optimize the hyperparameters of the thermal runaway warning model using the particle swarm optimization algorithm, input environmental data, and output the thermal runaway risk levels of each detection point.

[0008] S3. Build a fire alarm control system, set different levels of warning methods according to the thermal runaway risk levels, and link the battery management system and the fire extinguishing system to achieve hierarchical response.

[0009] S4. Record the fire extinguishing process data in real time and upload it to the cloud platform to achieve remote monitoring and data analysis.

[0010] S5. After confirming that the fire has been completely controlled, perform exhaust, inspection, replacement, and reset operations to restore the normal operation of the system.

[0011] According to a novel liquid nitrogen fire extinguishing and temperature reduction method and system for energy storage power stations provided by the present invention, in step S1, the process of setting up the composite detector network includes:

[0012] Select micro-detectors that meet the preset requirements.

[0013] Set one micro-detector on each battery module, evenly arrange a preset number of micro-detectors in the energy storage cabin, and increase the density of micro-detectors in the battery pack dense area and the ventilation dead corner area.

[0014] Equip each micro-detector with a data acquisition unit, and the data acquisition unit is used to convert the sensor signals collected by the micro-detector into digital signals and perform preprocessing to obtain preprocessed data.

[0015] According to a novel liquid nitrogen fire extinguishing and temperature reduction method and system for energy storage power stations provided by the present invention, in step S2, the process of building a thermal runaway warning model based on a deep neural network includes:

[0016] Collect the historical operation data of the energy storage power station, and the historical operation data includes normal operating condition data, fault condition data, and thermal runaway event data.

[0017] Annotate the historical operation data, and mark the thermal runaway risk level corresponding to each data point.

[0018] Extract environmental features from the historical operation data, and the environmental features include hydrogen concentration features, carbon monoxide concentration features, and temperature features. Combine the environmental features of the historical operation data and the thermal runaway risk levels annotated by the environmental features to divide the training set, validation set, and test set.

[0019] Design a deep neural network model structure, including an input layer, hidden layers, and an output layer. The input layer is used to receive environmental features. The hidden layers are used to learn the non-linear relationships between environmental features and extract high-level features. The output layer is used to output the thermal runaway risk level corresponding to each environmental feature, obtaining a basic model.

[0020] Use the training set to train the basic model, retain the model parameters that meet the test accuracy, and obtain a thermal runaway warning model.

[0021] According to a novel liquid nitrogen fire extinguishing and cooling method and system applicable to energy storage power stations provided by the present invention, in step S2, the process of optimizing the hyperparameters of the thermal runaway warning model using the particle swarm optimization algorithm includes:

[0022] Set the hyperparameters to be optimized, where the hyperparameters include the number of hidden layers, the number of neurons in each layer, the learning rate, and the regularization coefficient.

[0023] Define the value range for each hyperparameter.

[0024] Initialize the particle swarm, including setting the number of particles, where each particle represents a candidate solution for a combination of hyperparameters. Initialize the particle positions and velocities. Randomly initialize the position of each particle within the value range of the hyperparameters, where the position of each particle represents a set of values of the hyperparameters. Randomly initialize the velocity of each particle, and the velocity represents the direction and step size of the particle moving in the search space.

[0025] Fitness evaluation: For each particle, use its corresponding combination of hyperparameters to construct and train a thermal runaway warning model on the training set, and use the validation set to evaluate the performance of the thermal runaway warning model as the fitness value.

[0026] Update the individual optimal position: For each particle, compare the fitness value of its current position with the fitness value of its individual optimal position. If the fitness value of the current position is better than the fitness value of the individual optimal position, update the current position to the individual optimal position of the particle.

[0027] Update the global optimal position: Compare the fitness values of the individual optimal positions of all particles, find the individual optimal position with the best fitness value, and update the position of this individual optimal position to the global optimal position.

[0028] Limit the particle velocity to prevent the particle velocity from being too large, causing the particle to fly out of the search space, and at the same time ensure that the particle position is within the value range of the hyperparameters.

[0029] Repeat the fitness evaluation - update the global optimal solution until the preset number of iterations is met.

[0030] When the iteration terminates, output the hyperparameter combination corresponding to the global optimal position as the hyperparameter combination of the thermal runaway warning model.

[0031] According to a novel liquid nitrogen fire extinguishing and cooling method and system for energy storage power stations provided by the present invention, in step S3, the process of achieving hierarchical response includes:

[0032] S31. Record data for battery modules with a low thermal runaway risk level, strengthen monitoring, and notify the management personnel.

[0033] S32. Take safety measures for battery modules with a medium thermal runaway risk level. The safety measures include reducing the charge and discharge power and stopping operation.

[0034] S33. Use a liquid nitrogen fire extinguishing system to spray liquid nitrogen for cooling battery modules with a high thermal runaway risk level.

[0035] S34. Adopt a cyclic point spraying strategy to continuously reduce the oxygen concentration and inhibit the reignition of battery modules that have experienced thermal runaway.

[0036] According to a novel liquid nitrogen fire extinguishing and cooling method and system for energy storage power stations provided by the present invention, in step S33, the process of spraying liquid nitrogen for cooling battery modules with a high thermal runaway risk level includes:

[0037] Locate the position information of the battery module according to the thermal runaway risk level output by the thermal runaway warning model, and adjust the direction of the liquid nitrogen nozzle according to the position information.

[0038] Spray liquid nitrogen onto the battery module with a high thermal runaway risk level, and control the spraying amount and spraying time to avoid battery damage caused by excessive cooling.

[0039] The liquid nitrogen quickly vaporizes, absorbs heat, and reduces the temperature of the battery module.

[0040] According to a novel liquid nitrogen fire extinguishing and cooling method and system for energy storage power stations provided by the present invention, in step S34, the cyclic point spraying strategy includes:

[0041] Continuously monitor the temperature change of the battery module that has experienced thermal runaway, and transmit the monitoring data to the fire alarm control system in real time.

[0042] The fire alarm control system analyzes the monitoring data to judge whether there is a risk of reignition.

[0043] If the monitoring data rises again, the liquid nitrogen fire extinguishing system conducts a second spraying.

[0044] According to a novel liquid nitrogen fire extinguishing and temperature reduction method and system for an energy storage power station provided by the present invention, in step S4, the fire alarm control system records the thermal runaway early warning time, thermal runaway risk level, liquid nitrogen injection volume, and battery module temperature change data, and uploads the recorded data to the Internet of Things monitoring cloud platform. Through the Internet of Things monitoring cloud platform, the operation status and safety risks of the energy storage power station are comprehensively monitored.

[0045] According to a novel liquid nitrogen fire extinguishing and temperature reduction method and system for an energy storage power station provided by the present invention, in step S5, the process of restoring the normal operation of the system includes: after confirming that the fire has been completely controlled, starting the exhaust ventilation system of the energy storage cabin, comprehensively inspecting the battery modules and the liquid nitrogen fire extinguishing system of the energy storage power station, replacing the battery modules that have experienced thermal runaway, comprehensively testing the replaced battery modules to ensure that their performance meets the requirements, resetting the fire alarm control system and the liquid nitrogen fire extinguishing system, restoring the normal operation state of the system, and re-entering the monitoring mode.

[0046] On the other hand, the present invention also provides a novel liquid nitrogen fire extinguishing and temperature reduction system for an energy storage power station, including:

[0047] A composite detection module, which is used to collect the hydrogen concentration, carbon monoxide concentration, and temperature data of each detection point in the energy storage cabin in real time through a composite detector network, and locate the battery module corresponding to each detection point.

[0048] A thermal runaway risk assessment module, which is used to construct a thermal runaway early warning model based on a deep neural network, optimize the hyperparameters of the thermal runaway early warning model using a particle swarm algorithm, input environmental data, and output the thermal runaway risk level of each detection point.

[0049] An alarm control and hierarchical response module, which is used to construct a fire alarm control system, set different levels of early warning methods according to the thermal runaway risk level, and link the battery management system and the fire extinguishing system to achieve hierarchical response.

[0050] A cloud platform remote monitoring module, which is used to record the fire extinguishing process data in real time and upload it to the cloud platform to achieve remote monitoring and data analysis.

[0051] A system reset module, which is used to perform exhaust, inspection, replacement, and reset operations to restore the normal operation of the system.

[0052] A novel liquid nitrogen fire extinguishing and temperature reduction method, system, device and storage medium applicable to energy storage power stations provided by the present invention can collect environmental data such as hydrogen, carbon monoxide and temperature in the energy storage cabin in real time by setting up a composite detector network. It can accurately locate the battery module corresponding to each detection point and realize the early identification of potential hazards. Different from traditional fire detection methods, this system has the ability of active monitoring, can quickly detect problems in the initial stage of thermal runaway, and greatly reduces the losses caused by fires. The thermal runaway early warning model constructed based on a deep neural network optimizes hyperparameters through a particle swarm algorithm, ensuring the efficient and accurate output of the thermal runaway risk level. This intelligent evaluation system can quantitatively analyze potential risks according to real-time environmental data, providing a scientific basis for subsequent alarm and control. The setting of a hierarchical response mechanism enables the system to take corresponding measures according to different risk levels, thereby optimizing the allocation of resources and improving the fire extinguishing efficiency. The construction of a fire alarm control system enables the entire fire extinguishing process to achieve an automated linkage response. When the risk level reaches the set threshold, the system can automatically start the linked battery management system, adjust the battery charge and discharge state, and prevent the battery from further heating up. At the same time, the fire extinguishing system can also respond quickly, first spraying liquid nitrogen to effectively reduce the heat and prevent the spread of the fire. Such a linkage control not only speeds up the fire extinguishing response time but also significantly reduces the delays and error risks caused by human operations. The characteristics of liquid nitrogen spraying make the fire extinguishing method more flexible. While cooling down, liquid nitrogen will not cause secondary damage to the battery and also avoids the possible electrical short circuits and equipment damage caused by traditional water flooding fire extinguishing. Therefore, this method can effectively protect the integrity of the energy storage system while suppressing thermal runaway, achieving the dual goals of fire extinguishing and protection. The real-time recording and uploading of data to the cloud platform form a complete monitoring and management system. The remote monitoring achieved through the cloud platform not only facilitates the staff to keep track of the operation status of the energy storage power station at any time but also provides a basis for future data analysis and optimization. By using big data analysis, potential risks of the energy storage power station can be explored, the operation efficiency of the entire system can be improved, and even data basis can be provided for subsequent improvement and upgrade. After the fire is controlled, the system can quickly confirm the fire situation and perform operations such as exhaust, equipment inspection, fault replacement and system reset to ensure a thorough safety assessment of the environment. This efficient post-disaster recovery mechanism avoids economic losses caused by system shutdown and ensures that the energy storage power station can resume normal operation in a short time. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0054] Figure 1 It is a schematic flow chart of a new type of liquid nitrogen fire extinguishing and temperature reduction method applicable to an energy storage power station provided by an embodiment of the present invention;

[0055] Figure 2 It is an experimental system diagram provided by an embodiment of the present invention;

[0056] Figure 3 It is a diagram of the experimental battery arrangement provided by an embodiment of the present invention;

[0057] Figure 4 It is a comparative diagram of dry powder fire extinguishing experiments provided by an embodiment of the present invention;

[0058] Figure 5 It is a comparative diagram of water-based fire extinguishing experiments provided by an embodiment of the present invention;

[0059] Figure 6 It is a comparative diagram of heptafluoropropane fire extinguishing experiments provided by an embodiment of the present invention;

[0060] Figure 7 It is a comparative diagram of perfluoromethyl hexanone fire extinguishing experiments provided by an embodiment of the present invention;

[0061] Figure 8 It is a comparative diagram of liquid nitrogen explosion suppression and fire extinguishing experiments provided by an embodiment of the present invention;

[0062] Figure 9 It is a schematic structural diagram of a new type of liquid nitrogen fire extinguishing and temperature reduction system applicable to an energy storage power station provided by an embodiment of the present invention. Specific embodiments

[0063] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without making creative efforts shall fall within the protection scope of the present invention.

[0064] The following combines Figures 1-9 Describe a new type of liquid nitrogen fire extinguishing and temperature reduction method and system applicable to an energy storage power station of the present invention.

[0065] Figure 1 It is a schematic flow chart of a new type of liquid nitrogen fire extinguishing and temperature reduction method applicable to an energy storage power station provided by an embodiment of the present invention.

[0066] Such as Figure 1As shown, a new type of liquid nitrogen fire extinguishing and temperature reduction method and system applicable to an energy storage power station provided by an embodiment of the present invention, the execution subject can be a new type of liquid nitrogen fire extinguishing and temperature reduction method and system applicable to an energy storage power station, including:

[0067] S1. Set up a composite detector network to collect environmental data of each detection point in the energy storage cabin in real time. The environmental data includes hydrogen concentration data, carbon monoxide concentration data, and temperature data, and locate the battery module corresponding to each detection point.

[0068] The process of setting up the composite detector network includes:

[0069] Select miniature detectors with high sensitivity, high precision, and fast response speed for hydrogen, carbon monoxide, and temperature.

[0070] Set one miniature detector on each battery module, evenly arrange a preset number of miniature detectors in the energy storage cabin, and increase the density of miniature detectors in the battery pack dense area and the ventilation dead corner area.

[0071] Equip each miniature detector with a data acquisition unit. The data acquisition unit is used to convert the sensor signals collected by the miniature detector into digital signals and perform preprocessing to obtain preprocessed data.

[0072] S2. Build a thermal runaway warning model based on a deep neural network, optimize the hyperparameters of the thermal runaway warning model using the particle swarm algorithm, input the environmental data, and output the thermal runaway risk level of each detection point.

[0073] The process of building a thermal runaway warning model based on a deep neural network includes:

[0074] Collect historical operation data of the energy storage power station. The historical operation data includes normal condition data, fault condition data, and thermal runaway event data.

[0075] Annotate the historical operation data and mark the thermal runaway risk level corresponding to each data point.

[0076] Extract environmental features from the historical operation data. The environmental features include hydrogen concentration features, carbon monoxide concentration features, and temperature features, and combine the environmental features of the historical operation data and the thermal runaway risk levels annotated by the environmental features to divide the training set, validation set, and test set.

[0077] Design the structure of the deep neural network model, including an input layer, a hidden layer, and an output layer. The input layer is used to receive environmental features. The hidden layer is used to learn the non-linear relationship between environmental features and extract high-level features. The output layer is used to output the thermal runaway risk level corresponding to each environmental feature to obtain a basic model.

[0078] Train the basic model using the training set, retain the model parameters that meet the test accuracy, and obtain the thermal runaway warning model.

[0079] The process of optimizing the hyperparameters of the thermal runaway warning model using the particle swarm optimization algorithm includes:

[0080] Set the hyperparameters to be optimized, including the number of hidden layers, the number of neurons in each layer, the learning rate, and the regularization coefficient.

[0081] Define the value range for each hyperparameter.

[0082] Initialize the particle swarm, including setting the number of particles. Each particle represents a candidate solution for a combination of hyperparameters. Initialize the particle positions and velocities. Randomly initialize the position of each particle within the value range of the hyperparameters. The position of each particle represents a set of values of the hyperparameters. Randomly initialize the velocity of each particle. The velocity represents the direction and step size of the particle moving in the search space.

[0083] Fitness evaluation: For each particle, use its corresponding combination of hyperparameters to construct and train the thermal runaway warning model on the training set, and use the validation set to evaluate the performance of the thermal runaway warning model as the fitness value.

[0084] Update the individual optimal position: For each particle, compare the fitness value of its current position with the fitness value of its individual optimal position. If the fitness value of the current position is better than the fitness value of the individual optimal position, update the current position to the individual optimal position of the particle.

[0085] Update the global optimal position: Compare the fitness values of the individual optimal positions of all particles, find the individual optimal position with the best fitness value, and update the position of this individual optimal position to the global optimal position.

[0086] Limit the particle velocity to prevent the particle velocity from being too large, causing the particle to fly out of the search space, and at the same time ensure that the particle position is within the value range of the hyperparameters.

[0087] Repeat the fitness evaluation - update the global optimal solution until the preset number of iterations is met.

[0088] When the iteration terminates, output the combination of hyperparameters corresponding to the global optimal position as the combination of hyperparameters of the thermal runaway warning model.

[0089] S3. Build a fire alarm control system, set different levels of warning methods according to the thermal runaway risk level, and link the battery management system and the fire extinguishing system to achieve hierarchical response.

[0090] The process of achieving hierarchical response includes:

[0091] S31. Record data for battery modules with a low thermal runaway risk level, strengthen monitoring, and notify the management personnel.

[0092] S32. Take safety measures for battery modules with a medium thermal runaway risk level. The safety measures include reducing the charge and discharge power and stopping operation.

[0093] S33. Use a liquid nitrogen fire extinguishing system to spray liquid nitrogen for cooling battery modules with a high thermal runaway risk level. The process includes:

[0094] Locate the position information of the battery module according to the thermal runaway risk level output by the thermal runaway warning model, and adjust the direction of the liquid nitrogen nozzle according to the position information.

[0095] Spray liquid nitrogen onto the battery module with a high thermal runaway risk level, and control the spraying amount and spraying time to avoid battery damage caused by excessive cooling.

[0096] The liquid nitrogen quickly vaporizes, absorbs heat, and reduces the temperature of the battery module.

[0097] S34. Adopt a cyclic spot spraying strategy to continuously reduce the oxygen concentration and inhibit the reignition of the battery module that has experienced thermal runaway.

[0098] The cyclic spot spraying strategy includes:

[0099] Continuously monitor the temperature change of the battery module that has experienced thermal runaway, and transmit the monitoring data to the fire alarm control system in real time.

[0100] The fire alarm control system analyzes the monitoring data to judge whether there is a risk of reignition.

[0101] If the monitoring data rises again, the liquid nitrogen fire extinguishing system conducts a second spraying.

[0102] S4. Record the data of the fire extinguishing process in real time and upload it to the cloud platform to achieve remote monitoring and data analysis.

[0103] The fire alarm control system records the thermal runaway warning time, thermal runaway risk level, liquid nitrogen spraying amount, and the data of the temperature change of the battery module, and uploads the recorded data to the Internet of Things monitoring cloud platform. Through the Internet of Things monitoring cloud platform, comprehensively monitor the operation status and safety risks of the energy storage power station.

[0104] S5. After confirming that the fire has been completely controlled, perform exhaust, inspection, replacement, and reset operations to restore the normal operation of the system.

[0105] The process of restoring the system to normal operation includes: after confirming that the fire has been completely controlled, start the exhaust ventilation system of the energy storage cabin, conduct a comprehensive inspection of the battery modules and liquid nitrogen fire extinguishing system of the energy storage power station, replace the battery modules that have experienced thermal runaway, conduct a comprehensive test on the replaced battery modules to ensure that their performance meets the requirements, reset the fire alarm control system and the liquid nitrogen fire extinguishing system, restore the system to its normal operating state, and re-enter the monitoring mode.

[0106] Figure 2 It is the experimental system diagram provided by the embodiment of the present invention.

[0107] Figure 3 It is the experimental battery arrangement diagram provided by the embodiment of the present invention.

[0108] Figure 4 It is the dry powder fire extinguishing experimental comparison diagram provided by the embodiment of the present invention.

[0109] Figure 5 It is the water-based fire extinguishing experimental comparison diagram provided by the embodiment of the present invention.

[0110] Figure 6 It is the heptafluoropropane fire extinguishing experimental comparison diagram provided by the embodiment of the present invention.

[0111] Figure 7 It is the perfluoromethylcyclohexanone fire extinguishing experimental comparison diagram provided by the embodiment of the present invention.

[0112] Figure 8 It is the liquid nitrogen explosion suppression and fire extinguishing experimental comparison diagram provided by the embodiment of the present invention.

[0113] As Figures 2-8 shown, when using dry powder to extinguish the explosion-proof fire of thermally runaway lithium-ion batteries, monomer A reignites immediately after the dry powder fire extinguishing agent is sprayed out. Monomer B is affected by the flame of monomer A and the heat transferred from the high-temperature battery body, and finally enters the stage of rapid thermal runaway. During the spraying process of the fire extinguishing agent, the dry powder fire extinguishing agent entering the experimental box from the spraying port fails to take effect immediately, and the surface temperature of the monomer is still rising. It rises to the maximum value of 232 °C about 5 s after spraying, and then the surface temperature of the monomer begins to decrease. After stopping the spraying of the dry powder fire extinguishing agent, the surface temperature of the battery immediately rises again. The peak surface temperatures of monomers A and B are 418 °C and 426 °C respectively. It can be seen from the experiment that dry powder fire extinguishing has little effect on lithium battery fires.

[0114] When using water-based to prevent explosion and extinguish fire for thermally runaway lithium-ion batteries, most of the water sprayed on the surface of lithium iron phosphate batteries is lost, reducing the cooling effect of water on high-temperature lithium batteries and resulting in insufficient heat absorption during the vaporization process after spraying. Therefore, monomer A reignited after stopping water spraying. Monomer B's safety valve released pressure under the heating of monomer A and had an initial explosion with an open flame. The open flame lasted for a short time and went out after 18 s. After stopping the water column spraying, the surface temperature of the battery immediately rose. The peak surface temperatures of monomers A and B were 347 °C and 209 °C respectively. It can be seen from the experiment that water-based fire extinguishing has a large water consumption, a long fire extinguishing time, and is prone to reignition. In the case of a very high output voltage such as an energy storage power station, it will cause a system short circuit and induce a secondary fire, resulting in the overall scrapping of the battery.

[0115] When using heptafluoropropane to prevent explosion and extinguish fire for thermally runaway lithium-ion batteries, a very small amount of combustible gas was generated from the pressure relief valve of monomer A 182 s after the end of heptafluoropropane fire extinguishing agent spraying, and there was no reignition. Monomer B had a slight deformation and expansion under the influence of the heat conducted by the high-temperature cell body of monomer A. After stopping the heptafluoropropane fire extinguishing agent spraying, the peak surface temperatures of monomers A and B were 195 °C and 90 °C respectively. It can be seen from the experiment that hydrogen fluoride is generated during the heptafluoropropane fire extinguishing process, which pollutes the atmosphere at the same time.

[0116] When using perfluoromethylcyclohexanone to prevent explosion and extinguish fire for thermally runaway lithium-ion batteries, gas was generated from monomer A 161 s after the end of perfluoromethylcyclohexanone fire extinguishing agent spraying. The amount of gas was small and gradually stopped generating gas. Due to the easy vaporization characteristic of perfluoromethylcyclohexanone, a large amount of heat was absorbed during the vaporization process, effectively blocking the heat transfer between the lithium battery packs. Therefore, only monomer B had a deformation and expansion. After stopping the perfluoromethylcyclohexanone fire extinguishing agent spraying, the peak surface temperatures of monomers A and B were 240 °C and 123 °C respectively. Hydrogen fluoride is generated during the process of using perfluoromethylcyclohexanone for fire extinguishing, which pollutes the atmosphere at the same time.

[0117] When using liquid nitrogen explosion suppression and fire extinguishing to prevent explosion and extinguish fire for thermally runaway lithium-ion batteries, with the continuous injection of liquid nitrogen, liquid nitrogen absorbed a large amount of heat and continuously vaporized to form a low-oxygen atmosphere, destroying the relevant reaction chain, slowing down the heat transfer between the batteries, and enabling subsequent reactions to be inhibited in a timely manner. Therefore, no gas was generated from monomer A after the end of liquid nitrogen spraying, and monomer B did not experience thermal runaway. After stopping the liquid nitrogen spraying, the surface temperature of the lithium iron phosphate battery gradually rose. Finally, the surface temperatures of monomers A and B rose to 141 °C and 61 °C respectively. Compared with other fire extinguishing agents, the upward trend of the battery surface temperature after the action of liquid nitrogen is significantly reduced. It can be seen from the experiment that using liquid nitrogen explosion suppression and fire extinguishing has prominent advantages such as cooling, explosion suppression, inerting, and total liquid nitrogen flooding.

[0118] In summary, this embodiment provides a novel liquid nitrogen fire extinguishing and temperature reduction method applicable to energy storage power stations. By setting up a composite detector network, the system can collect environmental data such as hydrogen, carbon monoxide, and temperature in the energy storage cabin in real time. It can accurately locate the battery modules corresponding to each detection point and achieve early identification of potential hazards. Different from traditional fire detection methods, this system has the ability of active monitoring, can quickly detect problems in the initial stage of thermal runaway, and greatly reduces the losses caused by fires. The thermal runaway early warning model constructed based on a deep neural network optimizes the hyperparameters through the particle swarm algorithm, ensuring the efficient and accurate output of the thermal runaway risk level. This intelligent evaluation system can quantitatively analyze potential risks based on real-time environmental data, providing a scientific basis for subsequent alarms and controls. The setting of the hierarchical response mechanism enables the system to take corresponding measures according to different risk levels, thereby optimizing the allocation of resources and improving the fire extinguishing efficiency. The construction of the fire alarm control system enables the entire fire extinguishing process to achieve an automated linkage response. When the risk level reaches the set threshold, the system can automatically start the linked battery management system, adjust the battery charge and discharge state, and prevent the battery from further heating up. At the same time, the fire extinguishing system can also respond quickly, first spraying liquid nitrogen to effectively reduce the heat and prevent the spread of the fire. Such a linkage control not only speeds up the fire extinguishing response time but also significantly reduces the risks of delays and errors caused by human operations. The characteristics of liquid nitrogen spraying make the fire extinguishing method more flexible. While cooling down, liquid nitrogen will not cause secondary damage to the battery and also avoids the electrical short circuits and equipment damage that may occur in traditional water flooding fire extinguishing. Therefore, this method can effectively protect the integrity of the energy storage system while suppressing thermal runaway, achieving the dual goals of fire extinguishing and protection. The real-time recording and uploading of data to the cloud platform form a complete monitoring and management system. The remote monitoring achieved through the cloud platform not only facilitates the staff to keep track of the operation status of the energy storage power station at any time but also provides a basis for future data analysis and optimization. By using big data analysis, potential risks of the energy storage power station can be explored, the operation efficiency of the entire system can be improved, and even data basis can be provided for subsequent improvements and upgrades. After the fire is controlled, the system can quickly confirm the fire situation and perform operations such as exhaust, equipment inspection, fault replacement, and system reset to ensure a thorough safety assessment of the environment. This efficient post-disaster recovery mechanism avoids economic losses caused by system shutdowns and ensures that the energy storage power station can resume normal operation in a short time.

[0119] Based on the same general inventive concept, the present invention also protects a novel liquid nitrogen fire extinguishing and temperature reduction system applicable to energy storage power stations. The novel liquid nitrogen fire extinguishing and temperature reduction system provided by the present invention will be described below. The novel liquid nitrogen fire extinguishing and temperature reduction system applicable to energy storage power stations described below can be mutually referred to and corresponding to the novel liquid nitrogen fire extinguishing and temperature reduction method applicable to energy storage power stations described above.

[0120] Figure 9 It is a schematic structural diagram of a new type of liquid nitrogen fire extinguishing and temperature reduction system applicable to an energy storage power station provided by an embodiment of the present invention.

[0121] As Figure 9 shown, the new type of liquid nitrogen fire extinguishing and temperature reduction system applicable to an energy storage power station provided by an embodiment of the present invention includes:

[0122] A composite detection module, which is used to collect the hydrogen concentration, carbon monoxide concentration and temperature data of each detection point in the energy storage bin in real time through a composite detector network, and locate the battery module corresponding to each detection point.

[0123] A thermal runaway risk assessment module, which is used to construct a thermal runaway early warning model based on a deep neural network, optimize the hyperparameters of the thermal runaway early warning model by using a particle swarm algorithm, input environmental data, and output the thermal runaway risk level of each detection point.

[0124] An alarm control and hierarchical response module, which is used to construct a fire alarm control system, set different levels of early warning methods according to the thermal runaway risk level, and link with the battery management system and the fire extinguishing system to achieve hierarchical response.

[0125] A cloud platform remote monitoring module, which is used to record the fire extinguishing process data in real time and upload it to the cloud platform to achieve remote monitoring and data analysis.

[0126] A system reset module, which is used to perform exhaust, inspection, replacement and reset operations to restore the normal operation of the system.

[0127] The device embodiments described above are only illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0128] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solutions, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0129] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A new liquid nitrogen fire extinguishing and cooling method and system suitable for energy storage power stations, characterized in that: include: S1. Set up a composite detector network to collect environmental data of each detection point in the energy storage cabin in real time, the environmental data including hydrogen concentration data, carbon monoxide concentration data and temperature data, and locate the battery module corresponding to each detection point; S2. Construct a thermal runaway warning model based on a deep neural network, and use a particle swarm algorithm to optimize the hyperparameters of the thermal runaway warning model, input the environmental data, and output the thermal runaway risk level of each detection point; S3. Build a fire alarm control system, set different levels of warning methods according to the thermal runaway risk level, and link the battery management system and the fire extinguishing system to achieve a graded response; S4, real-time record of fire extinguishing process data, and upload to the cloud platform to achieve remote monitoring and data analysis; S5. After confirming that the fire is completely under control, vent, inspect, replace and reset the system to restore normal operation.

2. A new liquid nitrogen fire extinguishing and cooling method and system suitable for energy storage power stations according to claim 1, characterized in that: In step S1, the process of setting up the composite detector network includes: Select a microdetector that meets the preset requirements; A micro detector is installed on each battery module, a preset number of micro detectors are evenly arranged in the energy storage compartment, and the density of micro detectors is increased in areas with dense battery packs and ventilation dead corners; Each micro-detector is equipped with a data acquisition unit, which is used to convert the sensor signal collected by the micro-detector into a digital signal and perform preprocessing to obtain preprocessed data.

3. A new liquid nitrogen fire extinguishing and cooling method and system suitable for energy storage power stations according to claim 1, characterized in that: In step S2, the process of constructing a thermal runaway warning model based on a deep neural network includes: Collecting historical operation data of the energy storage power station, the historical operation data including normal operating condition data, fault operating condition data and thermal runaway event data; Annotating the historical operating data and marking the thermal runaway risk level corresponding to each data point; Extracting environmental features from the historical operation data, the environmental features including hydrogen concentration features, carbon monoxide concentration features, and temperature features, and combining the environmental features of the historical operation data and the thermal runaway risk levels marked by the environmental features to divide the data into a training set, a validation set, and a test set; Design a deep neural network model structure, including an input layer, a hidden layer and an output layer; the input layer is used to receive the environmental features; the hidden layer is used to learn the nonlinear relationship between the environmental features and extract high-level features; the output layer is used to output the thermal runaway risk level corresponding to each environmental feature to obtain a basic model; The basic model is trained using the training set, and model parameters that meet the test accuracy are retained to obtain a thermal runaway warning model.

4. A new liquid nitrogen fire extinguishing and cooling method and system suitable for energy storage power stations according to claim 1, characterized in that: In step S2, the process of optimizing the hyperparameters of the thermal runaway warning model using a particle swarm algorithm includes: Setting hyperparameters to be optimized, including the number of hidden layers, the number of neurons in each layer, the learning rate, and the regularization coefficient; Define the value range for each hyperparameter; Initialize the particle swarm, including setting the number of particles, each particle represents a candidate solution for a hyperparameter combination; initialize the particle position and velocity, randomly initialize the position of each particle within the range of hyperparameter values, and the position of each particle represents a set of hyperparameter values; randomly initialize the velocity of each particle, and the velocity represents the direction and step size of the particle's movement in the search space; Fitness evaluation: For each particle, the corresponding hyperparameter combination is used on the training set to construct and train the thermal runaway warning model, and the performance of the thermal runaway warning model is evaluated using the validation set as the fitness value; Update individual optimal position: For each particle, compare the fitness value of its current position with the fitness value of its individual optimal position. If the fitness value of the current position is better than the fitness value of the individual optimal position, update the current position to the individual optimal position of the particle. Update the global optimal position: compare the fitness values ​​of the individual optimal positions of all particles, find the individual optimal position with the best fitness value, and update the position of the individual optimal position to the global optimal position; Limit the particle speed to prevent the particle speed from being too high, causing the particle to fly out of the search space, while ensuring that the particle position is within the value range of the hyperparameter; Repeat the fitness evaluation-update the global optimal solution until the preset number of iterations is met; When the iteration is terminated, the hyperparameter combination corresponding to the global optimal position is output as the hyperparameter combination of the thermal runaway warning model.

5. A new liquid nitrogen fire extinguishing and cooling method and system suitable for energy storage power stations according to claim 1, characterized in that: In step S3, the process of implementing the hierarchical response includes: S31. Record data for battery modules with a low thermal runaway risk level, strengthen monitoring and notify management personnel; S32. Take safety measures for the battery module with a medium thermal runaway risk level, wherein the safety measures include reducing the charge and discharge power and stopping operation; S33. Use a liquid nitrogen fire extinguishing system to spray liquid nitrogen to cool down battery modules with a high risk level of thermal runaway; S34. Use a cyclic point-spraying strategy to continuously reduce oxygen concentration and suppress the re-ignition of battery modules that have already experienced thermal runaway.

6. A new liquid nitrogen fire extinguishing and cooling method and system suitable for energy storage power stations according to claim 5, characterized in that: In step S33, the process of cooling the battery module with a high thermal runaway risk level by spraying liquid nitrogen includes: Locating the battery module position information according to the thermal runaway risk level output by the thermal runaway warning model, and adjusting the direction of the liquid nitrogen nozzle according to the position information; Spray liquid nitrogen onto battery modules with a high risk of thermal runaway, and control the spray volume and spray time to avoid battery damage caused by excessive cooling; Liquid nitrogen vaporizes quickly, absorbing heat and lowering the temperature of the battery modules.

7. A new liquid nitrogen fire extinguishing and cooling method and system suitable for energy storage power stations according to claim 5, characterized in that: In step S34, the cyclic point spraying strategy includes: Continuously monitor the temperature changes of the battery modules that have thermal runaway, and transmit the monitoring data to the fire alarm control system in real time; The fire alarm control system determines whether there is a risk of re-ignition by analyzing the monitoring data; If the monitoring data increases again, the liquid nitrogen fire extinguishing system will spray a second time.

8. A new liquid nitrogen fire extinguishing and cooling method and system suitable for energy storage power stations according to claim 1, characterized in that: In step S4, the fire alarm control system records the thermal runaway warning time, thermal runaway risk level, liquid nitrogen injection volume and battery module temperature change data, and uploads the recorded data to the IoT monitoring cloud platform. Through the IoT monitoring cloud platform, the operating status and safety risks of the energy storage power station are comprehensively monitored.

9. A new liquid nitrogen fire extinguishing and cooling method and system suitable for energy storage power stations according to claim 1, characterized in that: In step S5, the process of restoring the normal operation of the system includes: after confirming that the fire is completely under control, starting the exhaust ventilation system of the energy storage cabin, conducting a comprehensive inspection of the battery modules and liquid nitrogen fire extinguishing system of the energy storage power station, replacing the battery modules that have thermal runaway, and conducting a comprehensive test on the replaced battery modules to ensure that the performance meets the requirements, resetting the fire alarm control system and the liquid nitrogen fire extinguishing system, restoring the normal operation of the system, and re-entering the monitoring mode.

10. A new liquid nitrogen fire extinguishing and cooling system applicable to an energy storage power station, using a new liquid nitrogen fire extinguishing and cooling method applicable to an energy storage power station as claimed in any one of claims 1 to 9, characterized in that: The novel liquid nitrogen fire extinguishing and cooling system applicable to the energy storage power station comprises: The composite detection module is used to collect the hydrogen concentration, carbon monoxide concentration and temperature data of each detection point in the energy storage bin in real time through the composite detector network, and locate the battery module corresponding to each detection point; The thermal runaway risk assessment module is used to build a thermal runaway warning model based on a deep neural network, and use a particle swarm algorithm to optimize the hyperparameters of the thermal runaway warning model. It inputs environmental data and outputs the thermal runaway risk level of each detection point. The alarm control and hierarchical response module is used to build a fire alarm control system, set different levels of early warning methods according to the risk level of thermal runaway, and link the battery management system and fire extinguishing system to achieve hierarchical response; The cloud platform remote monitoring module is used to record the fire extinguishing process data in real time and upload it to the cloud platform to achieve remote monitoring and data analysis; The system reset module is used to perform exhaust, inspection, replacement and reset operations to restore the normal operation of the system.

Images