Fire control system for container type lithium iron phosphate battery energy storage system

Abstract

The invention provides a fire control system for a container type lithium iron phosphate battery energy storage system, and belongs to the technical field of safety of electrochemical energy storage systems. The system comprises a data acquisition module which comprises a distributed sensor group and is used for acquiring environment and battery state data; the data analysis and decision module is used for predicting the thermal runaway risk of the battery through a preset risk prediction model according to the collected data, and is also used for dynamically adjusting the trigger threshold value of each alarm level according to the collected data, and determining the alarm level in combination with the predicted thermal runaway risk of the battery; the execution control module is used for executing a corresponding preset fire extinguishing strategy according to the determined alarm level; and the reburning monitoring module is used for generating a secondary fire extinguishing instruction according to the real-time data acquired by the data acquisition module after executing the fire extinguishing strategy. According to the invention, through multi-dimensional data fusion and a dynamic threshold adjustment mechanism, the accuracy and response timeliness of lithium battery thermal runaway early warning are significantly improved.

Description

Technical Field

[0001] The present invention relates to the field of electrochemical energy storage system safety technology, and in particular to a fire control system for a containerized lithium iron phosphate battery energy storage system. Background Art

[0002] With the large-scale application of renewable energy and the rapid growth in grid-side energy storage demand, containerized lithium iron phosphate battery energy storage systems have become a mainstream technology solution in the power energy storage field due to their high energy density, long cycle life, and modular deployment advantages. However, battery systems are prone to thermal runaway chain reactions under abnormal operating conditions such as overcharging, over-discharging, mechanical abuse, or thermal diffusion, leading to safety accidents such as the release of flammable gases, fires, and even explosions. Especially in closed container environments, the localized high temperatures and gas accumulation caused by thermal runaway can accelerate the spread of fire. Traditional firefighting methods cannot achieve accurate early warning and rapid response, seriously threatening the safe operation of energy storage facilities and the stability of the power grid.

[0003] Current firefighting technologies for lithium battery energy storage systems mostly rely on threshold alarm mechanisms based on a single physical quantity and lack the ability to integrate and analyze multi-dimensional data, resulting in high false alarm and missed alarm rates. Furthermore, existing systems typically employ fixed alarm thresholds, failing to dynamically adjust response strategies based on battery aging and changes in ambient temperature and humidity, making them difficult to adapt to complex operating conditions. Firefighting execution often utilizes a "full-cabin spraying" mode, without designing hierarchical control strategies for the thermal runaway stage and spatial distribution. This can easily lead to waste of extinguishing agents or insufficient suppression effects. Crucially, most solutions fail to consider post-extinguishing re-ignition risk monitoring, resulting in delayed secondary fire handling and further exacerbating safety hazards. These issues have become technical bottlenecks restricting the safety and reliability of containerized energy storage systems. Summary of the Invention

[0004] The present invention provides a fire control system for a container-type lithium iron phosphate battery energy storage system, which is used to solve the problems of high false alarm rate and delayed fire extinguishing response in the prior art.

[0005] In order to achieve the above-mentioned objectives, an embodiment of the present invention provides, on the one hand, a fire control system for a containerized lithium iron phosphate battery energy storage system, the fire control system comprising: a data acquisition module, including a distributed sensor group, for collecting environmental and battery status data; a data analysis and decision module, for predicting the risk of battery thermal runaway based on the collected data through a preset risk prediction model, and for dynamically adjusting the trigger thresholds of each alarm level based on the collected data, and determining the alarm level in combination with the predicted battery thermal runaway risk; an execution control module, for executing a corresponding preset fire extinguishing strategy based on the determined alarm level; and a re-ignition monitoring module, for generating a secondary fire extinguishing instruction based on the real-time data collected by the data acquisition module after executing the fire extinguishing strategy, so as to control the execution control module to perform secondary fire extinguishing.

[0006] Optionally, the risk prediction model is constructed based on a long short-term memory network, and the battery thermal runaway risk is predicted based on the collected data through a preset risk prediction model, including: preprocessing the collected data; extracting features related to the battery thermal runaway risk based on the preprocessed data; using principal component analysis to reduce the dimensionality of the extracted features; and calculating based on the reduced dimensionality data through the risk prediction model to obtain the risk probability of battery thermal runaway.

[0007] Optionally, the trigger thresholds of each alarm level are dynamically adjusted based on the collected data, including: converting the battery life data, charge and discharge times data, and ambient temperature data into corresponding fuzzy quantities through a fuzzy logic algorithm; performing inference operations on the converted fuzzy quantities using preset fuzzy rules to obtain a fuzzy quantity of an adjustment coefficient; converting the obtained fuzzy quantity of the adjustment coefficient into a precise value through a defuzzification algorithm, and adjusting the trigger thresholds of each alarm level according to the converted precise value.

[0008] Optionally, the alarm level is determined in combination with the predicted battery thermal runaway risk, including: if the battery thermal runaway risk probability is in a first preset interval and the collected data exceeds the trigger threshold of at least one first-level alarm, it is determined as a first-level alarm; if the battery thermal runaway risk probability is in a second preset interval and the collected data meets the trigger threshold of at least one second-level alarm, it is determined as a second-level alarm; if the battery thermal runaway risk probability is in a third preset interval and the collected data meets the trigger threshold of at least one third-level alarm, it is determined as a third-level alarm.

[0009] Optionally, the execution control module is configured as follows: when it is determined to be a level one alarm, the fan is started, and the sound and light alarm is controlled to send out a level one alarm signal; when it is determined to be a level two alarm, the partition isolation valve corresponding to the thermal runaway battery compartment is switched to manual mode, and the spraying of the fire extinguishing agent is delayed, and the sound and light alarm is controlled to send out a level two alarm signal; when it is determined to be a level three alarm, the partition isolation valve corresponding to the thermal runaway battery compartment is opened, the fine water mist system is started, and the spraying of the fire extinguishing agent is delayed, and the sound and light alarm is controlled to send out a level three alarm signal.

[0010] Optionally, the re-ignition monitoring module is configured to: analyze the temperature and gas concentration data collected in real time by the data acquisition module within a preset time after the execution of the fire extinguishing strategy; when abnormal temperature rise or sudden change in gas concentration occurs, generate a secondary fire extinguishing instruction, and control the execution control module to execute the fire extinguishing strategy corresponding to the first-level alarm.

[0011] Optionally, the data analysis and decision module is further configured to dynamically adjust the alarm level according to the data collected in real time by the data collection module when executing the fire extinguishing strategy.

[0012] On the other hand, a fire control method is also provided, which is applied to the above-mentioned fire control system. The fire control method includes: obtaining environmental and battery status data and performing preprocessing; predicting the battery thermal runaway risk based on the preprocessed data through a preset risk prediction model; determining the alarm level based on the predicted battery thermal runaway risk and the trigger threshold of each alarm level; and executing the corresponding preset fire extinguishing strategy based on the determined alarm level.

[0013] Optionally, before determining the alarm level based on the predicted battery thermal runaway risk and the trigger thresholds of each alarm level, the fire control method further includes: adjusting the trigger threshold based on the collected data using a fuzzy logic algorithm and preset fuzzy rules.

[0014] Optionally, after executing the corresponding preset fire extinguishing strategy according to the determined alarm level, the fire control method also includes: generating a secondary fire extinguishing instruction within a preset time based on the real-time acquired environment and battery status data; and controlling the execution control module to execute the fire extinguishing strategy corresponding to the first-level alarm according to the secondary fire extinguishing instruction.

[0015] The present invention provides a fire control system for a containerized lithium iron phosphate battery energy storage system. The present invention adopts a long-short-term memory network and a fuzzy logic algorithm to collaboratively analyze battery aging, environmental variables and real-time status data to achieve accurate prediction of risk probability; combined with a graded fire extinguishing strategy and intelligent re-ignition monitoring technology, it can not only delay the spread of fire through local ventilation in the early stage of thermal runaway, but also accurately locate the faulty cabin and trigger directional fire extinguishing in an emergency, effectively avoiding the waste of resources caused by spraying the entire cabin; at the same time, through structured data integration and multi-level communication protocol adaptation, a closed-loop control system from risk perception, intelligent decision-making to fire extinguishing execution is constructed, which shortens the fire extinguishing response time while reducing the false alarm rate, and realizes the monitoring of secondary fire conditions, providing a fire protection solution for the containerized energy storage system that is both efficient, economical and safe. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the present invention or the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. In the drawings: Figure 1 This is a structural diagram of a fire control system provided by an embodiment of the present invention; Figure 2 is a risk prediction flow chart provided by an embodiment of the present invention; Figure 3 is an alarm level determination table provided by an embodiment of the present invention; Figure 4 This is a detailed flow chart of a fire control system provided by an embodiment of the present invention; Figure 5 This is a flow chart of the operation of a fire control system provided by an embodiment of the present invention; Figure 6 This is another operation flow chart of a fire control system provided by an embodiment of the present invention; Figure 7 This is a flow chart of a fire control method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following describes the specific implementation of the embodiment of the present invention in detail with reference to the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the embodiment of the present invention and is not used to limit the embodiment of the present invention.

[0018] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. In the embodiments of this application, certain software, components, models, and other existing solutions in the industry may be mentioned. These should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use such solutions.

[0019] Against the backdrop of today's energy structure transformation, containerized lithium iron phosphate battery energy storage systems have been widely used in the power energy storage field due to their advantages such as high energy density, long cycle life, and good safety. Against the backdrop of today's energy structure transformation, containerized lithium iron phosphate battery energy storage systems have been widely used in the power energy storage field due to their advantages such as high energy density, long cycle life, and good safety. Therefore, the development of a more accurate and responsive fire control system is particularly important.

[0020] To address this issue, the present invention provides a fire control system for containerized lithium iron phosphate battery energy storage systems. This system comprehensively collects environmental and battery status data, accurately predicts thermal runaway risks, intelligently adjusts alarm thresholds, accurately determines alarm levels and implements targeted firefighting strategies, and effectively monitors re-ignition. This significantly improves the accuracy of fire warnings, the efficiency of firefighting, and the timeliness of re-ignition response, comprehensively ensuring the safety of containerized lithium iron phosphate battery energy storage systems and significantly reducing fire risks and losses.

[0021] The following combination Figure 1-Figure 7 The present invention will be described in detail.

[0022] Example 1: like Figure 1 As shown, an embodiment of the present invention provides a fire control system for a containerized lithium iron phosphate battery energy storage system, the fire control system comprising: a data acquisition module, including a distributed sensor group, for collecting environmental and battery status data; a data analysis and decision module, for predicting the risk of battery thermal runaway based on the collected data through a preset risk prediction model, and for dynamically adjusting the trigger threshold of each alarm level based on the collected data, and determining the alarm level in combination with the predicted battery thermal runaway risk; an execution control module, for executing a corresponding preset fire extinguishing strategy based on the determined alarm level; and a re-ignition monitoring module, for generating a secondary fire extinguishing instruction based on the real-time data collected by the data acquisition module after executing the fire extinguishing strategy, so as to control the execution control module to perform secondary fire extinguishing.

[0023] The core of the fire control system provided by the present invention is composed of four major modules: data acquisition, data analysis and decision-making, execution control, and re-ignition monitoring. The data acquisition module uses a distributed sensor group to collect environmental and battery status data in all directions to provide data for subsequent precise analysis. The data analysis and decision-making module is extremely critical. It can not only predict the risk of battery thermal runaway with the help of a preset risk prediction model, but also dynamically adjust the alarm threshold through a fuzzy logic algorithm, and determine the alarm level in combination with the risk prediction results and the collected data. The execution control module executes the corresponding preset fire extinguishing strategy in an orderly manner according to the determined alarm level. After the fire extinguishing action is completed, the re-ignition monitoring module uses the data collected in real time by the data acquisition module to keenly capture anomalies, generate secondary fire extinguishing instructions, and eliminate the hidden dangers of re-ignition. The system has outstanding advantages. Through the close and intelligent collaboration of each module, a comprehensive closed-loop protection system covering fire prevention, precise monitoring, efficient firefighting and re-ignition prevention is constructed, which greatly improves the ability of the container-type lithium iron phosphate battery energy storage system to cope with fire risks, effectively ensures the safe and stable operation of the system, and reduces the probability of fire accidents and the degree of loss.

[0024] like Figure 2 As shown, preferably, the risk prediction model is constructed based on a long short-term memory network, and the battery thermal runaway risk is predicted based on the collected data through a preset risk prediction model, including: preprocessing the collected data; extracting features related to the battery thermal runaway risk based on the preprocessed data; using the principal component analysis method to reduce the dimension of the extracted features; and calculating the risk probability of the battery thermal runaway based on the reduced dimension data through the risk prediction model.

[0025] In a preferred embodiment of the present invention, a risk prediction model constructed based on a long-short-term memory network can effectively capture the complex patterns of battery status changes over time. When predicting the risk of battery thermal runaway, the collected data is first preprocessed to remove noise and fill missing values, making the data cleaner and more accurate, laying a good foundation for subsequent analysis. Based on the preprocessed data, features closely related to the risk of battery thermal runaway are then extracted, such as the temperature change rate and the gas concentration growth trend. These features can effectively reflect the potential thermal runaway risk of the battery. The extracted features are then subjected to dimensionality reduction using principal component analysis, which reduces the number of features while retaining the key information, reduces the model complexity, and improves computational efficiency. Finally, based on the reduced dimensionality data, the risk prediction model is used to calculate and output the risk probability of battery thermal runaway. This series of steps makes risk prediction more scientific and accurate, providing a strong basis for subsequent alarm level determination and fire extinguishing strategy execution, greatly improving the fire control system's ability to warn of battery thermal runaway risks and helping to take measures to prevent fire accidents in advance.

[0026] Preferably, the method of dynamically adjusting the trigger threshold of each alarm level based on the collected data includes: converting the battery life data, charge and discharge times data and ambient temperature data into corresponding fuzzy quantities through a fuzzy logic algorithm; performing inference operations on the converted fuzzy quantities using preset fuzzy rules to obtain an adjustment coefficient fuzzy quantity; converting the obtained adjustment coefficient fuzzy quantity into an exact value through a defuzzification algorithm, and adjusting the trigger threshold of each alarm level according to the converted exact value.

[0027] In a preferred embodiment of the present invention, a process for dynamically adjusting alarm thresholds using a fuzzy logic algorithm is described. First, the algorithm categorizes battery life into fuzzy variables such as "short," "medium," and "long" based on age. It also categorizes charge and discharge cycles into fuzzy variables such as "low," "medium," and "high" based on their range. Ambient temperature is also categorized into fuzzy variables such as "low," "normal," and "high" based on their temperature range. For example, a battery life of less than two years is classified as "short," charge and discharge cycles between 500 and 1000 are classified as "medium," and an ambient temperature exceeding 35°C is classified as "high." These converted fuzzy variables are then inferred using pre-set fuzzy rules. For example, if the battery life is "long," the charge and discharge cycles are "high," and the ambient temperature is "high," the fuzzy rules might set the corresponding adjustment coefficient fuzzy variable to "significant increase," indicating a significant increase in the alarm threshold. In this case, the risk of thermal runaway is higher, making early warning more important. Finally, a defuzzification algorithm is used to convert the fuzzy adjustment coefficient into a precise value. Common defuzzification methods, such as the center of gravity method, calculate specific values based on the distribution of fuzzy quantities in the domain, and then precisely adjust the trigger thresholds for each alarm level based on this precise value. Compared to traditional fixed threshold settings, this method of adjusting alarm thresholds based on fuzzy logic algorithms can fully account for the complex and variable factors in battery energy storage system operation, making the alarm thresholds more closely aligned with actual operating conditions. This significantly improves the accuracy and flexibility of the system's monitoring of battery thermal runaway risks, effectively avoiding false alarms and missed alarms.

[0028] Preferably, the alarm level is determined in combination with the predicted battery thermal runaway risk, including: if the battery thermal runaway risk probability is in a first preset interval and the collected data exceeds the trigger threshold of at least one first-level alarm, it is determined as a first-level alarm; if the battery thermal runaway risk probability is in a second preset interval and the collected data meets the trigger threshold of at least one second-level alarm, it is determined as a second-level alarm; if the battery thermal runaway risk probability is in a third preset interval and the collected data meets the trigger threshold of at least one third-level alarm, it is determined as a third-level alarm.

[0029] In a preferred embodiment of the present invention, three preset intervals are divided according to the probability of battery thermal runaway risk, each interval corresponding to a different risk level, and the final alarm level is determined by combining the comparison results of the collected data with the alarm trigger thresholds of each level.

[0030] like Figure 3 As shown, Figure 3 The trigger conditions for each alarm level are displayed. For example, the first preset interval is set for a battery thermal runaway risk probability of 10%-20%, the second preset interval is set for a battery thermal runaway risk probability of 20%-50%, and the third preset interval is set for a battery thermal runaway risk probability above 50%. Assume that in a containerized lithium iron phosphate battery energy storage system, the risk prediction model calculates that the battery thermal runaway risk probability has risen to 30%, which is within the second preset interval. At this time, the data acquisition module records a temperature of 75°C and a hydrogen concentration of 800ppm in the battery compartment. The trigger thresholds for the second alarm level are 500ppm for hydrogen concentration and 70°C for temperature, meeting the second alarm thresholds. The system then determines a second alarm level.

[0031] Preferably, the execution control module is configured as follows: when it is determined to be a level one alarm, the fan is started, and the sound and light alarm is controlled to send out a level one alarm signal; when it is determined to be a level two alarm, the partition isolation valve corresponding to the thermal runaway battery compartment is switched to manual mode, and the spraying of the fire extinguishing agent is delayed, and the sound and light alarm is controlled to send out a level two alarm signal; when it is determined to be a level three alarm, the partition isolation valve corresponding to the thermal runaway battery compartment is opened, the fine water mist system is started, and the spraying of the fire extinguishing agent is delayed, and the sound and light alarm is controlled to send out a level three alarm signal.

[0032] In a preferred embodiment of the present invention, when a Level 1 alarm is determined, the execution control module activates the fan. This fan operation promotes air circulation, promptly dissipating heat generated by the batteries and reducing the temperature around the batteries, thereby alleviating the high-temperature environment that could potentially trigger thermal runaway. Simultaneously, the control module controls the audible and visual alarm to emit a Level 1 alarm signal. This combined audible and visual alarm immediately draws the attention of personnel, alerting them to the risk of thermal runaway, allowing them to conduct prompt inspections and take preliminary preventative measures, such as checking the operating status of the equipment. This operation is relatively basic, but it can provide an effective early warning and initial intervention in the early stages of the risk, preventing further escalation. When a Level 2 alarm is determined, the control module switches the zone isolation valve corresponding to the thermally runaway battery compartment to manual mode. Personnel can manually control the isolation valve based on the actual situation on site. The fire extinguishing agent is sprayed with a delay. This delay strategy allows personnel to conduct targeted firefighting operations after confirming the situation and making relevant preparations, avoiding the adverse effects of indiscriminate spraying. Simultaneously, the control module controls the audible and visual alarm to emit a Level 2 alarm signal, alerting personnel to the critical situation and requiring swift action. When a Level 3 alarm is determined, the execution control module opens the zoned isolation valves corresponding to the thermally runaway battery compartment, directly isolating the runaway area and preventing the fire from spreading to other areas. Simultaneously, the water mist system is activated. This effectively suppresses the fire's growth by absorbing heat, reducing temperatures, and isolating oxygen, rapidly cooling the hot battery compartment and reducing the impact of thermal runaway. The fire extinguishing agent is sprayed with a delayed release to further enhance the firefighting effect. The audible and visual alarms issue a Level 3 alarm, alerting personnel in the strongest possible way that the system is facing a serious risk of thermal runaway and requiring immediate emergency measures to contain the fire and ensure the safety of the entire energy storage system. In summary, the execution control module's policy configurations for different alarm levels are closely aligned with the degree of risk, progressively strengthening response measures from prevention and control to emergency firefighting. This provides a practical and feasible operational plan for ensuring the safety of containerized lithium iron phosphate battery energy storage systems and significantly enhances the system's ability to respond to fire risks.

[0033] Preferably, the re-ignition monitoring module is configured to: analyze the temperature and gas concentration data collected in real time by the data acquisition module within a preset time after the execution of the fire extinguishing strategy; when abnormal temperature rise or sudden change in gas concentration occurs, generate a secondary fire extinguishing instruction, and control the execution control module to execute the fire extinguishing strategy corresponding to the first-level alarm.

[0034] In a preferred embodiment of the present invention, within a preset time after the execution of the fire extinguishing strategy, the re-ignition monitoring module will focus on the temperature and gas concentration data collected in real time by the data acquisition module. This is because abnormal temperature rise and sudden changes in gas concentration are often important precursors to the re-ignition of battery thermal runaway. For example, when the temperature in the battery compartment rises rapidly in a short period of time after the fire is extinguished, it may mean that the thermal reaction inside the battery has not completely stopped and there is a risk of re-ignition; or if the concentration of combustible gases such as hydrogen suddenly rises sharply, it is also very likely that the chemical reaction inside the battery continues to produce more combustible gases, indicating that re-ignition is about to occur.

[0035] For example, at a containerized lithium iron phosphate battery energy storage power station, a fire caused by thermal runaway triggered the fire extinguishing process in the fire control system. After the execution control module completed the fire extinguishing strategy corresponding to the third-level alarm, the fire appeared to be under control and entered the re-ignition monitoring phase. According to the re-ignition monitoring module's settings, within one hour after the fire extinguishing strategy was executed, high-frequency analysis of temperature and gas concentration data transmitted by the data acquisition module was performed. The data acquisition module collected temperature data and concentrations of gases such as hydrogen and carbon monoxide at key locations within the battery compartment every minute. Thirty minutes after the fire was extinguished, data showed that the local temperature in the battery compartment, which had dropped to 50°C, suddenly rose to 65°C within five minutes. Simultaneously, the hydrogen concentration also rapidly climbed from 50 ppm after the fire was extinguished to 200 ppm. The re-ignition monitoring module detected this abnormal temperature and gas concentration increase and immediately generated a secondary fire extinguishing command. Upon receiving this command, the execution control module quickly initiated the fire extinguishing strategy corresponding to the first-level alarm.

[0036] Preferably, the data analysis and decision module is further used to dynamically adjust the alarm level according to the data collected in real time by the data collection module when executing the fire extinguishing strategy.

[0037] In a preferred embodiment of the present invention, the data analysis and decision module can continuously and dynamically adjust the alarm level based on the data collected in real time by the data acquisition module. For example, if, when executing the fire extinguishing strategy corresponding to the second-level alarm, the data shows that the risk of battery thermal runaway has been significantly reduced, the relevant parameters are gradually approaching the normal range, and the collected data no longer meets the second-level alarm threshold, then the data analysis and decision module will promptly lower the alarm level to level one, and the execution control module will also adjust the fire extinguishing operation accordingly. By dynamically adjusting the alarm level during the fire extinguishing process, the fire control system can always accurately implement policies based on the actual situation, maximize the fire extinguishing efficiency, and ensure the safety of the containerized lithium iron phosphate battery energy storage system.

[0038] like Figure 7 As shown, an embodiment of the present invention also provides a fire control method, which is applied to the above-mentioned fire control system. The fire control method includes: S101: Obtaining environmental and battery status data and performing preprocessing; S102: Predicting the risk of battery thermal runaway based on the preprocessed data using a preset risk prediction model; S103: Determine an alarm level based on the predicted battery thermal runaway risk and the trigger thresholds of each alarm level; S104: Execute a corresponding preset fire extinguishing strategy according to the determined alarm level.

[0039] Preferably, before determining the alarm level according to the predicted battery thermal runaway risk and the trigger thresholds of each alarm level, the fire control method further includes: adjusting the trigger threshold based on the collected data using a fuzzy logic algorithm and preset fuzzy rules.

[0040] Further preferably, after executing the corresponding preset fire extinguishing strategy according to the determined alarm level, the fire control method also includes: generating a secondary fire extinguishing instruction within a preset time based on the real-time acquired environment and battery status data; and controlling the execution control module to execute the fire extinguishing strategy corresponding to the first-level alarm according to the secondary fire extinguishing instruction.

[0041] The fire control method provided by the embodiments of the present invention establishes a complete, closed-loop, and intelligent fire protection solution for containerized lithium iron phosphate battery energy storage systems. The method first acquires and preprocesses environmental and battery status data. This step serves as the foundation of the entire process, and the processed data provides reliable support for subsequent risk prediction and decision-making. Based on this data, a risk prediction model constructed using a long-short-term memory network is used to predict the risk of battery thermal runaway. This model effectively captures dynamic changes in battery status and potential thermal runaway trends. Before determining the alarm level, a fuzzy logic algorithm and preset fuzzy rules are used to adjust the trigger threshold. This step comprehensively considers the impact of multiple factors on the alarm threshold, such as battery life, charge and discharge cycles, and ambient temperature. This allows the threshold to be dynamically adjusted based on actual conditions, significantly improving risk monitoring accuracy and avoiding misjudgments caused by traditional fixed thresholds. After determining the alarm level based on the predicted risk and the dynamically adjusted threshold, the execution control module executes the corresponding preset fire extinguishing strategy, ensuring that the system can take targeted measures to respond to fires at different risk levels, improving fire extinguishing efficiency and effectiveness. After the fire extinguishing strategy is implemented, re-ignition monitoring is crucial. Real-time data is continuously analyzed within a preset timeframe. Once signs of re-ignition, such as abnormal temperature rise or sudden changes in gas concentration, are detected, a secondary fire-fighting command is immediately generated and the corresponding fire-fighting strategy for the primary alarm is executed. This step provides dual protection for the firefighting process, reducing the likelihood of re-ignition and maximizing the safety of the energy storage system. The fire control method described above integrates advanced data analysis technology, an intelligent threshold adjustment mechanism, and a comprehensive fire-fighting and re-ignition monitoring process. It can comprehensively, dynamically, and efficiently address fire risks in containerized lithium iron phosphate battery energy storage systems, significantly enhancing system safety and reliability. It is an innovative and practical firefighting solution.

[0042] Example 2: like Figure 4-Figure 6As shown, based on the same inventive concept, the present invention provides a fire control system for a containerized lithium iron phosphate battery energy storage system. When applied to a containerized lithium iron phosphate battery energy storage station, the complete system operation process is as follows: the station data acquisition module uses a distributed sensor group (including temperature sensors evenly distributed between battery modules and key locations in the container, voltage and current sensors connected to each battery group, and gas sensors that detect the concentration of flammable and harmful gases in the container) to collect data every 10 seconds and transmit it to the data analysis and decision module. This module preprocesses the data (abnormal battery voltage data is corrected using a median filter algorithm, and missing temperature data is filled using linear interpolation). Then, using a risk prediction model constructed using a long-short-term memory network, relevant features such as the battery temperature change rate are extracted and, after dimensionality reduction using principal component analysis, the current battery thermal runaway risk probability is calculated to be 35%. At the same time, based on a fuzzy logic algorithm, the battery age, charge and discharge cycles, and ambient temperature are converted into fuzzy quantities. The precise value of the adjustment coefficient is obtained through preset fuzzy rule inference operations and a defuzzification algorithm, and the first-level alarm temperature trigger threshold is adjusted upward. Combining the risk probability with the collected data and the adjusted threshold, it was determined to be a level 2 alarm because the risk probability was in the second preset interval and the hydrogen concentration and temperature in a container exceeded the level 2 alarm trigger threshold. The execution control module switched the isolation valve of the container partition where the thermal runaway battery was located to manual mode, started the aerosol fire extinguishing agent spraying device after a 30-second delay, and the sound and light alarm issued a level 2 alarm signal. Within 1 hour after the fire extinguishing strategy was executed, the re-ignition monitoring module continued to analyze the real-time data. 40 minutes after the fire was extinguished, due to the temperature rise in the thermal runaway area and the sudden increase in carbon monoxide concentration, it was judged that there were signs of re-ignition, and a secondary fire extinguishing instruction was generated. The execution control module started the fire extinguishing strategy corresponding to the level 1 alarm, turned on the fan and issued a level 1 alarm signal again until the risk of re-ignition was eliminated, ensuring the safe and stable operation of the energy storage station.

[0043] In summary, the present invention provides a container-type lithium iron phosphate battery energy storage system, which significantly improves the reliability and handling efficiency of the energy storage fire protection system by constructing a multi-source data fusion analysis architecture and an intelligent hierarchical response system: the system adopts LSTM neural network and fuzzy logic algorithm to collaboratively analyze the multi-dimensional state parameters of the battery, realizes dynamic prediction of the probability of thermal runaway risk, and combines temperature-compensated gas sensors with dynamic threshold adjustment mechanism to reduce the early warning false alarm rate; the innovative design of the zone linkage fire extinguishing strategy delays heat diffusion through intelligent air duct control, and accurately opens and closes the fire extinguishing valve based on fault location information, reducing the loss of fire extinguishing agent; at the same time, the closed-loop re-ignition monitoring network achieves millisecond-level response to secondary fires through high-frequency data feedback and adaptive learning mechanism, forming a safety protection system that integrates precise perception, intelligent decision-making and rapid execution, providing a fire protection solution for container energy storage systems that is both economical and safe.

[0044] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0045] Additionally, the terms "system" and "network" are often used interchangeably. The term "and / or" is simply used to describe a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " generally indicates an "or" relationship between the related objects.

[0046] It should be understood that in the embodiments of the present invention, "B corresponding to A" means that B is associated with A and B can be determined based on A. However, it should also be understood that determining B based on A does not mean determining B based solely on A; B can also be determined based on A and / or other information.

[0047] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0048] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0049] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or can be electrical, mechanical or other forms of connection.

[0050] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the objectives of the embodiments of the present invention.

[0051] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0052] From the above description of the embodiments, it will be apparent to those skilled in the art that the present invention can be implemented using hardware, firmware, or a combination thereof. When implemented using software, the aforementioned functionality may be stored in a computer-readable medium or transmitted as one or more instructions or codes on the computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media includes any medium that facilitates the transfer of computer programs from one location to another. Storage media can be any available medium that can be accessed by a computer. By way of example and not limitation, computer-readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer. Furthermore, any suitable connection may constitute a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of the medium. As used herein, the terms "disk" and "disc" include compact discs (CDs), laser discs, optical discs, digital versatile discs (DVDs), floppy disks, and Blu-ray discs. Disks typically reproduce data magnetically, while discs use lasers to reproduce data optically. Combinations of the above should also be included within the scope of protection for computer-readable media.

[0053] In short, the above description is only a preferred embodiment of the technical solution of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention.

Claims

1. A fire control system for a containerized lithium iron phosphate battery energy storage system, characterized in that: The fire control system includes: Data acquisition module, including a distributed sensor group for collecting environmental and battery status data; The data analysis and decision-making module is used to predict the risk of battery thermal runaway based on the collected data and a preset risk prediction model. It is also used to dynamically adjust the trigger thresholds of each alarm level based on the collected data and determine the alarm level based on the predicted battery thermal runaway risk; An execution control module, configured to execute a corresponding preset fire extinguishing strategy according to the determined alarm level; The re-ignition monitoring module is used to generate a secondary fire extinguishing instruction according to the real-time data collected by the data acquisition module after executing the fire extinguishing strategy, so as to control the execution control module to perform secondary fire extinguishing.

2. The fire control system according to claim 1, characterized in that: The risk prediction model is constructed based on a long short-term memory network. The risk of battery thermal runaway is predicted based on the collected data through a preset risk prediction model, including: Preprocessing the collected data; Extract features related to battery thermal runaway risk based on preprocessed data; The principal component analysis method is used to reduce the dimension of the extracted features; The risk prediction model is used to calculate the risk probability of battery thermal runaway based on the data after dimensionality reduction.

3. The fire control system according to claim 1, characterized in that: The trigger thresholds of each alarm level are dynamically adjusted based on the collected data, including: Through the fuzzy logic algorithm, the battery life data, charge and discharge times data and ambient temperature data are converted into corresponding fuzzy quantities; The converted fuzzy quantity is inferred and operated by using the preset fuzzy rules to obtain the adjustment coefficient fuzzy quantity; The obtained fuzzy value of the adjustment coefficient is converted into an accurate value through a defuzzification algorithm, and the trigger threshold of each alarm level is adjusted according to the converted accurate value.

4. The fire control system according to claim 1, characterized in that: Determining the alarm level based on the predicted battery thermal runaway risk includes: If the battery thermal runaway risk probability is within a first preset interval and the collected data exceeds at least one triggering threshold of a first-level alarm, a first-level alarm is determined; If the battery thermal runaway risk probability is within a second preset interval and the collected data meets at least one triggering threshold of a second-level alarm, a second-level alarm is determined; If the battery thermal runaway risk probability is within a third preset interval and the collected data meets at least one triggering threshold of a third-level alarm, a third-level alarm is determined.

5. The fire control system according to claim 4, characterized in that: The execution control module is configured to: When it is determined to be a level one alarm, the fan is started and the sound and light alarm is controlled to send out a level one alarm signal; When a level 2 alarm is determined, the partition isolation valve corresponding to the thermal runaway battery compartment is switched to manual mode, the fire extinguishing agent is sprayed with a delay, and the sound and light alarm is controlled to issue a level 2 alarm signal; When it is determined to be a level three alarm, the partition isolation valve corresponding to the thermal runaway battery compartment is opened, the fine water mist system is started, the fire extinguishing agent is sprayed with a delay, and the sound and light alarm is controlled to send out a level three alarm signal.

6. The fire control system according to claim 4, characterized in that: The re-ignition monitoring module is configured to: Analyzing the temperature and gas concentration data collected in real time by the data acquisition module within a preset time after executing the fire extinguishing strategy; When abnormal temperature rise or sudden change of gas concentration occurs, a secondary fire extinguishing instruction is generated, and the execution control module is controlled to execute the fire extinguishing strategy corresponding to the first-level alarm.

7. The fire control system according to claim 1, characterized in that: The data analysis and decision module is further configured to dynamically adjust the alarm level according to the data collected in real time by the data collection module when executing the fire extinguishing strategy.

8. A fire control method, characterized in that: Applied to the fire control system according to claims 1 to 7, the fire control method comprises: Obtain environmental and battery status data and perform preprocessing; Based on the pre-processed data, the battery thermal runaway risk is predicted using a preset risk prediction model; Determine the alarm level based on the predicted battery thermal runaway risk and the trigger thresholds of each alarm level; According to the determined alarm level, a corresponding preset fire extinguishing strategy is executed.

9. The fire control method according to claim 8, characterized in that: Before determining the alarm level based on the predicted battery thermal runaway risk and the trigger thresholds of each alarm level, the fire control method further includes: Based on the collected data, the trigger threshold is adjusted using a fuzzy logic algorithm and preset fuzzy rules.

10. The fire control method according to claim 8, characterized in that: After executing the corresponding preset fire extinguishing strategy according to the determined alarm level, the fire control method further includes: Generate a secondary fire extinguishing command within a preset time based on real-time environmental and battery status data; According to the secondary fire extinguishing instruction, the control execution module executes the fire extinguishing strategy corresponding to the first-level alarm.

Images