Thermal runaway risk prevention and control method of container type energy storage system and related equipment

Abstract

The invention discloses a thermal runaway risk prevention and control method of a container type energy storage system and related equipment. The method comprises the following steps: acquiring monitoring data of the container type energy storage system in a monitoring period based on a thermal runaway index; inputting the monitoring data of the thermal runaway index into the index prediction model, and determining the prediction data of the thermal runaway index at the target prediction moment; according to the prediction data of the thermal runaway index, determining the prediction abnormal degree of the thermal runaway index; according to the predicted abnormal degree of the thermal runaway index, determining the predicted total abnormal degree of the container type energy storage system at the target prediction moment; if the predicted total abnormal degree is within a preset early warning range, triggering an early warning operation corresponding to the predicted total abnormal degree; and if the predicted total abnormal degree is greater than the upper limit of the preset early warning range, triggering fire-fighting operation, thereby realizing early warning and effective fire-fighting control of the thermal runaway abnormal condition of the container type energy storage system.

Description

Technical Field

[0001] The present application relates to the field of safety technology, and in particular to a method for preventing and controlling thermal runaway risks of a containerized energy storage system and related equipment. Background Art

[0002] Containerized energy storage integrates multiple components, including lithium-ion batteries and a battery management system, within a standard container. It features flexible configuration, high modularity, strong mobility, and excellent environmental adaptability, making it widely used in renewable energy power generation, grid operations, and user environments. However, due to the compact internal battery layout and the relatively closed container environment, lithium-ion batteries can experience thermal runaway due to overcharge, over-discharge, short circuit, and mechanical impact, leading to chain reactions such as fire and explosion.

[0003] Related technologies rely on a single parameter to monitor containerized energy storage systems. However, containerized energy storage systems are highly complex and prone to false alarms and missed alarms during early warning of thermal runaway. Furthermore, lithium-ion batteries are prone to reignition, making it impossible to reliably prevent the recurrence of thermal runaway and its spread in the battery system. Summary of the Invention

[0004] In view of this, the present application provides a method and related equipment for preventing and controlling the thermal runaway risk of a containerized energy storage system. By monitoring, predicting, and analyzing various thermal runaway indicators of the containerized energy storage system, early warning of abnormal thermal runaway conditions and effective fire control of the containerized energy storage system can be achieved.

[0005] According to one aspect of the present application, a method for preventing and controlling thermal runaway risks of a containerized energy storage system is provided, comprising:

[0006] Acquire monitoring data of the containerized energy storage system within the monitoring period based on thermal runaway indicators;

[0007] Inputting the monitoring data of the thermal runaway indicator into an indicator prediction model to determine the predicted data of the thermal runaway indicator at a target prediction time, wherein the target prediction time is a time after a preset time period after the end of the monitoring period, and the indicator prediction model is determined based on a long short-term memory network and historical data of the thermal runaway indicator;

[0008] determining a predicted abnormality degree of the thermal runaway indicator based on the predicted data of the thermal runaway indicator;

[0009] Determining a predicted total abnormality level of the containerized energy storage system at the target prediction time based on the predicted abnormality level of the thermal runaway indicator;

[0010] If the predicted total abnormality level is within the preset warning range, triggering a warning operation corresponding to the predicted total abnormality level;

[0011] If the predicted total abnormality level is greater than the upper limit of the preset warning range, a firefighting operation is triggered.

[0012] According to another aspect of the present application, a device for preventing and controlling thermal runaway risks of a containerized energy storage system is provided, comprising:

[0013] An acquisition module, used to obtain monitoring data of the containerized energy storage system within a monitoring period based on the thermal runaway indicator;

[0014] a determination module, configured to input the monitoring data of the thermal runaway indicator into an indicator prediction model, determine the predicted data of the thermal runaway indicator at a target prediction time, the target prediction time being a time after a preset period of time after the end of the monitoring period, the indicator prediction model being determined based on a long short-term memory network and historical data of the thermal runaway indicator; and, based on the predicted data of the thermal runaway indicator, determine the predicted abnormality degree of the thermal runaway indicator; and, based on the predicted abnormality degree of the thermal runaway indicator, determine the predicted total abnormality degree of the containerized energy storage system at the target prediction time;

[0015] An operation module is used to trigger an early warning operation corresponding to the predicted total abnormality level if the predicted total abnormality level is within a preset early warning range; and to trigger a fire-fighting operation if the predicted total abnormality level is greater than an upper limit of the preset early warning range.

[0016] According to another aspect of the present application, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the thermal runaway risk prevention and control method of the containerized energy storage system are implemented.

[0017] According to another aspect of the present application, a computer device is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor. When the processor executes the program, the steps of the above-mentioned method for preventing and controlling thermal runaway risks of a containerized energy storage system are implemented.

[0018] By means of the above technical solution, the present application provides a method and related equipment for preventing and controlling the risk of thermal runaway of a containerized energy storage system. The method of the present application integrates a variety of thermal runaway indicators and uses a long-short-term memory network to predict the total abnormality of the containerized energy storage system at a specific time point in the future, thereby identifying potential risks in advance, reducing the risk of fire caused by thermal runaway, improving the safety and reliability of the containerized energy storage system, and reducing potential property losses and casualties. At the same time, based on the predicted total abnormality of the containerized energy storage system, the early warning operation and the firefighting operation are distinguished, and an accurate early warning of thermal runaway is given. When the predicted total abnormality is serious and exceeds the preset warning range, the firefighting operation is triggered in time during the current monitoring cycle to avoid the expansion of thermal runaway, minimize the risk of casualties and property losses, and achieve early warning and effective firefighting control of abnormal thermal runaway conditions in the containerized energy storage system.

[0019] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0021] Figure 1 A schematic diagram of a process for preventing and controlling thermal runaway risks of a containerized energy storage system according to an embodiment of the present application is shown;

[0022] Figure 2 A block diagram showing the relationship between the containerized energy storage system provided in an embodiment of the present application and the early warning system, fire extinguishing system, smoke exhaust system, and fire detection system;

[0023] Figure 3 A structural block diagram of a thermal runaway risk prevention and control device for a containerized energy storage system provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0024] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0025] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and are not to be construed as limiting the present application.

[0026] It will be understood by those skilled in the art that, unless expressly stated otherwise, the singular forms "a", "an", "said" and "the" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the specification of this application refers to the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, or there may be intermediate elements. In addition, "connected" or "connected" as used herein may include wireless connection or wireless fusion. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0027] Now, exemplary embodiments according to the present application will be described in more detail with reference to the accompanying drawings. However, these exemplary embodiments may be implemented in a variety of different forms and should not be construed as being limited to the embodiments set forth herein. It should be understood that these embodiments are provided to make the disclosure of this application thorough and complete and to fully convey the concepts of these exemplary embodiments to those of ordinary skill in the art.

[0028] In this embodiment, a method for preventing and controlling thermal runaway risks of a containerized energy storage system is provided. Figure 1 As shown, the method includes:

[0029] Step 101: Acquire monitoring data of a containerized energy storage system within a monitoring period based on a thermal runaway indicator.

[0030] It should be noted that the thermal runaway process of the containerized energy storage system occurs in the form of a chain reaction. The violent chemical reactions inside it will produce various types of combustible gases, and its characteristic parameters such as voltage and temperature will change significantly.

[0031] Specifically, when thermal runaway occurs in a lithium-ion battery (i.e., a single battery cell) in a containerized energy storage system, the violent chemical reactions within it produce different types of gases. The gas generation mechanism is closely related to the battery temperature. When the internal temperature of a lithium-ion battery exceeds 90°C, the solid electrolyte interface (SEI) decomposes, and the lithium-embedded negative electrode reacts with the SEI film or CO2, producing a large amount of gas (O2, CO2, C2H4). The chemical reaction formula is:

[0032]

[0033] 2Li+(CH2OCO2Li)2→2Li2CO3+C2H4↑

[0034] When the internal temperature of a lithium-ion battery exceeds 120°C, the unprotected lithium reacts with the electrolyte to produce hydrocarbons (C2H4, CH4, C2H6, etc.). The chemical reaction formula is:

[0035] 2Li+C3H4O3(EC)→Li2CO3+C2H4

[0036] 2Li+C3H6O3(DMC)→Li2CO3+C2H6

[0037] 2Li+C4H6O3(PC)→Li2CO3+C3H6

[0038] 2Li+C5H 10 O3(DEC)→Li2CO3+C4H 10

[0039] When the internal temperature of a lithium-ion battery exceeds 180°C, the positive electrode material and the electrolyte react exothermically to produce CO:

[0040] C3H4O3(EC)+Li→CH3OLi+C2H5OLi+CO↑

[0041] When the internal temperature of a lithium-ion battery exceeds 200°C, the O2 generated by the decomposition of the positive electrode material reacts with the electrolyte to produce CO2 when completely burned, and CO when incompletely burned:

[0042]

[0043] 4O2+C4H6O3→4CO2+3H2O

[0044] 6O2+C5H 10 O3→5CO2+5H2O

[0045] 3O2+C3H6O3→3CO2+3H2O

[0046] O2+C3H4O3(EC)→3CO+2H2O

[0047]

[0048] 2O2+C4H6O3(PC)→4CO+3H2O

[0049] When the internal temperature of a lithium-ion battery exceeds 260°C, the battery adhesive reacts with Li and releases H2:

[0050] -CH2-CF2-→-CH=CF-+HF

[0051]

[0052] Here, the main gases produced during battery thermal runaway include O2, CO, CO2, C2H4, H2, and certain hydrocarbons.

[0053] On the other hand, the triggering mode of thermal runaway in lithium-ion batteries is different, and the voltage change pattern is also different. In the case of thermal runaway caused by overcharging, the voltage of the lithium-ion battery will gradually increase until the lithium dendrites pierce the diaphragm, causing a reaction between the positive and negative electrodes. The voltage drops sharply to 0V after reaching the peak. In the case of thermal runaway caused by heating, as the temperature rises, the SEI film gradually dissolves until a reaction occurs between the positive and negative electrodes of the battery, and the voltage gradually drops to 0V. In the case of thermal runaway caused by mechanical abuse, a short circuit occurs inside the battery, and the voltage will drop rapidly.

[0054] On the other hand, the normal operating temperature of lithium-ion batteries is generally between -30°C and 50°C. When the ambient temperature exceeds the normal operating temperature of the battery, the battery capacity will decay and the temperature will slowly rise. This is until the SEI film melts, causing an internal short circuit in the battery. The side reactions intensify, and the temperature rise rate accelerates. Generally, thermal runaway is triggered when the temperature reaches above 120°C. A series of chemical reactions then instantly generate a large amount of heat, causing the temperature to rise rapidly, reaching its highest point. After all the energy is released, the battery gradually cools down.

[0055] In this embodiment, based on the aforementioned variation patterns of characteristic battery thermal runaway parameters, characteristic parameters that show significant changes in the early stages of thermal runaway are selected as thermal runaway indicators. This allows the use of thermal runaway indicators to characterize the operating status of containerized energy storage systems, demonstrating both scientific and practical feasibility. Furthermore, monitoring containerized energy storage systems based on thermal runaway indicators avoids the false alarms and missed alarms that can occur with traditional single-parameter methods.

[0056] For example, based on the thermal runaway index, the monitoring data of the containerized energy storage system within the monitoring period is obtained. For example, CO2, CO, and H2, which have a significant production growth rate during the thermal runaway process, are used as target gases, and the concentration of the target gas is used as the thermal runaway index. At the same time, the voltage and temperature of the single cell in the containerized energy storage system are also used as thermal runaway indicators. The voltage and temperature of the single cell reflect the working status and health status of the battery, while the concentration of CO, CO2, and H2 inside the containerized energy storage system can reflect whether there are potential safety hazards in the containerized energy storage system. Then, starting from the battery module level and the container level, the thermal runaway state of the energy storage battery is monitored in real time.

[0057] For example, the battery management system (BMS) in a containerized energy storage system can collect the voltage and temperature of individual cells to assess their status. Gas sensors can also be installed in the battery compartment of the containerized energy storage system to collect the concentration of target gases.

[0058] Step 102: Input the monitoring data of the thermal runaway index into the index prediction model to determine the prediction data of the thermal runaway index at the target prediction time.

[0059] Among them, the target prediction time is the time after the preset time after the end of the monitoring cycle, and the indicator prediction model is determined based on the long-short-term memory network and the historical data of the thermal runaway indicator.

[0060] The monitoring period is the time interval during which data on thermal runaway indicators of containerized energy storage systems is collected. During this period, data on these indicators is continuously collected. The monitoring period must be appropriately set based on a comprehensive consideration of multiple factors, including system characteristics, data variation patterns, equipment performance, and cost-effectiveness. This balance ensures data timeliness and accuracy, enabling effective monitoring of thermal runaway risks in containerized energy storage systems. The monitoring period can range from seconds to hours. For example, a 10-minute monitoring period is recommended.

[0061] Furthermore, the preset duration is an additional time length set on the basis of the monitoring cycle, so that in the process of continuously monitoring the system operation data, a future time point is set to predict the situation of the thermal runaway index of the containerized energy storage system. When the monitoring cycle ends, the time point reached after this preset duration is the target prediction moment. Here, the setting of the preset duration needs to comprehensively consider factors such as the monitoring cycle, system response speed, accuracy of the prediction model and actual application scenarios to ensure that anomalies can be effectively predicted and measures can be taken in time. The preset duration can range from a few minutes to several hours. For example, when the monitoring cycle is 10 minutes, the preset duration can be set to 5 minutes, that is, based on the monitoring data of the thermal runaway index for 10 minutes within the monitoring cycle, the indicator prediction model is used to predict the predicted data of the thermal runaway index 5 minutes after the end of the monitoring cycle.

[0062] In this embodiment, the indicator prediction model is trained using a long short-term memory (LSTM) network and historical data on thermal runaway indicators. By inputting the monitoring data for each thermal runaway indicator within a monitoring period into the indicator prediction model, the model can output predicted data for each thermal runaway indicator at the target prediction time. The LSTM network can effectively capture long-term dependencies in time series data, improving prediction accuracy and providing a reliable basis for early detection of potential anomalies.

[0063] In one embodiment, the method for preventing and controlling thermal runaway risks of a containerized energy storage system further includes: historical data of a thermal runaway indicator includes first historical data and second historical data; obtaining first historical data of the containerized energy storage system within a historical monitoring period based on the thermal runaway indicator; labeling the first historical data of the thermal runaway indicator based on the second historical data of the thermal runaway indicator at a historical prediction moment, where the historical prediction moment is a moment after a preset period of time after the end of the historical monitoring period; and training a long short-term memory network based on the labeled first historical data of the thermal runaway indicator to obtain an indicator prediction model, so that the indicator prediction model can predict predicted data of the thermal runaway indicator at a target prediction moment based on the input monitoring data of the thermal runaway indicator.

[0064] In this embodiment, historical data of thermal runaway indicators of the containerized energy storage system are combined into time series data in chronological order, which are used as training samples for the LSTM model so that the LSTM model can learn the changing pattern of the thermal runaway indicators over time.

[0065] Specifically, the historical monitoring period can be divided into several consecutive time points. The first historical data point of the thermal runaway indicator at each time point within the historical monitoring period is selected to form a sample. It can be understood that the sample is a matrix, with each row representing a time point and each column representing a thermal runaway indicator. Using these samples as input to the LSTM model, the LSTM model can learn from this historical data the changing trends of each thermal runaway indicator over time and their interrelationships. Here, the historical monitoring period is equal in length to the current monitoring period.

[0066] For example, assuming a 10-minute historical monitoring cycle, divided into 10 consecutive time points, the historical voltage and temperature values of the individual cells, as well as the historical concentrations of CO, CO2, and H2 within the containerized energy storage system, are selected at each time point within the 10-minute period. Thus, a single sample contains information on the five thermal runaway indicators (voltage, temperature, CO concentration, CO2 concentration, and H2 concentration) at these 10 time points. This sample can be viewed as a 10×5 matrix.

[0067] Furthermore, for each input sample, its corresponding label is determined. The label is the second historical data of these thermal runaway indicators N minutes in the future (preset duration). In other words, starting from the last time point covered by the sample and counting N minutes later, the second historical data of the thermal runaway indicator at this historical prediction moment is recorded. These second historical data form a vector of length 5, which serves as the label corresponding to the sample. The labeled samples are then used as training samples for the LSTM model, and the LSTM model is trained to obtain an indicator prediction model.

[0068] For example, if the training sample covers the data from minute 1 to minute 10, N=5, then the label is the voltage, temperature, CO concentration, CO2 concentration, and H2 concentration values at minute 15.

[0069] In this embodiment, the goal of the LSTM model is to learn the mapping relationship between training samples and labels, as well as the mutual influence between various thermal runaway indicators in the training samples, so that when a new input sample is given, the value of the thermal runaway indicator in the next N minutes can be predicted.

[0070] It is understandable that when making a prediction, the monitoring data of the thermal runaway indicator in the current monitoring cycle is first obtained. Then, the monitoring data of the thermal runaway indicator is processed in the same way as during training to ensure that the scale of the data is consistent, and a monitoring sample in the form of a matrix is obtained. Next, the constructed monitoring sample is input into the trained indicator prediction model. The trained indicator prediction model has learned the relationship between the input sample and the thermal runaway indicator value in the next N minutes. It will perform calculations and reasoning based on the input monitoring sample, and finally output the predicted value of the thermal runaway indicator in the next N minutes. Here, the output of the indicator prediction model is also a vector, which includes the predicted data of each thermal runaway indicator at the target prediction moment.

[0071] Step 103: Determine the predicted abnormality degree of the thermal runaway indicator based on the predicted data of the thermal runaway indicator.

[0072] In this embodiment, based on the predicted data of the thermal runaway index, the abnormal degree of the thermal runaway index at a specific time point in the future (i.e., the target prediction moment) is predicted, potential risks are warned in advance, the root cause of the abnormality is accurately located, and a scientific basis is provided for graded warnings and fire-fighting operations, thereby ensuring stable operation of the system and reducing accident losses.

[0073] Furthermore, as a refinement and expansion of the specific implementation methods of the above-mentioned embodiment, in order to fully illustrate the specific implementation process of this embodiment, the thermal runaway indicator includes the voltage of the single cell in the containerized energy storage system. According to the predicted data of the thermal runaway indicator, the predicted abnormality degree of the thermal runaway indicator is determined, specifically including: determining the predicted average voltage value and the predicted minimum voltage value of the single cell according to the predicted data of the voltage of the single cell; determining the predicted voltage deviation of the single cell according to the predicted average voltage value and the predicted minimum voltage value of the single cell; matching the predicted voltage deviation with a preset voltage definition interval, and determining the predicted abnormality degree of the single cell voltage according to the first preset abnormality degree corresponding to the target voltage definition interval matched by the predicted voltage deviation.

[0074] In this embodiment, the voltage of each cell in the thermal runaway indicator is analyzed separately. Specifically, based on the predicted data of the cell voltage, the average voltage value (i.e., the predicted average voltage value) and the minimum voltage value (i.e., the predicted minimum voltage value) among the cells at a specific point in the future are calculated. This allows the cells with sudden voltage drops or mutations to be located, preventing the overall average value from masking local faults.

[0075] Next, based on the difference between the predicted average voltage and the predicted minimum voltage, the voltage deviation between individual cells at a specific future time point (i.e., the predicted voltage deviation) is calculated. This predictive voltage deviation quantifies the degree of cell voltage dispersion. Under normal circumstances, the voltage differences between individual cells are small. If the predicted voltage deviation is large, it indicates that some cell voltages deviate from the average level, potentially indicating overcharging, over-discharging, or internal battery failure. For example, in a battery pack, if the predicted minimum voltage of a cell is much lower than the predicted average voltage, the predicted voltage deviation increases, indicating possible performance degradation or a connection failure.

[0076] The voltage offset between individual cells in actual application scenarios can then be pre-divided into multiple voltage thresholds. Each voltage threshold is pre-assigned a first abnormality level. The larger the first abnormality level, the more likely thermal runaway will occur. The predicted voltage deviation is then determined to match the preset voltage threshold. Based on the target voltage threshold matched by the predicted voltage deviation, the predicted abnormality level corresponding to the thermal runaway indicator, when the voltage of the individual cell is the target voltage, is determined. This clarifies the abnormality level of the battery voltage and provides a basis for subsequent warning and processing.

[0077] For example, the number of preset voltage defining intervals can be set to three. The first preset voltage defining interval is [0V, 0.15V), and the first preset abnormality level value of the first preset voltage defining interval is 0. The second preset voltage defining interval is [0.15V, 6V), and the first preset abnormality level value of the second preset voltage defining interval is 1. The third preset voltage defining interval is [6V, +∞), and the first preset abnormality level value of the third preset voltage defining interval is 2.

[0078] In this embodiment, by predicting the voltage deviation, the risk of internal battery abuse (such as overcharging and short circuit) is identified, and potential thermal runaway is warned in advance.

[0079] Furthermore, as a refinement and expansion of the specific implementation methods of the above-mentioned embodiment, in order to fully illustrate the specific implementation process of this embodiment, the thermal runaway indicator includes the temperature of the single cell in the containerized energy storage system. Based on the predicted data of the thermal runaway indicator, the predicted abnormality degree of the thermal runaway indicator is determined, specifically including: determining the predicted average temperature value and the predicted maximum temperature value of the single cell based on the predicted data of the temperature of the single cell; determining the predicted temperature deviation of the single cell based on the predicted average temperature value and the predicted maximum temperature value of the single cell; matching the predicted temperature deviation with a preset temperature boundary interval, and determining the predicted abnormality degree of the single cell temperature based on a second preset abnormality degree corresponding to the target temperature boundary interval matched by the predicted temperature deviation.

[0080] In this embodiment, the temperature of the individual cells in the thermal runaway indicator is analyzed separately. Specifically, based on the predicted temperature data of the individual cells, the average temperature value (i.e., the predicted temperature and voltage value) and the maximum temperature value (i.e., the predicted maximum temperature value) among the individual cells at a specific point in the future are calculated. This allows the identification of locally overheated cells and the prevention of heat spread.

[0081] Next, based on the predicted average temperature value and the predicted maximum temperature value, the temperature deviation between the single cells at a specific time point in the future (i.e., the predicted temperature deviation) is calculated to quantify the degree of temperature unevenness through the predicted temperature deviation. The larger the deviation, the more urgent the risk of thermal runaway. During normal operation, the temperatures of the single cells in the battery pack are similar. If the predicted temperature deviation is large, it means that the temperature of some cells is too high. This may be caused by poor heat dissipation, abnormal self-heating inside the battery, etc. For example, when the predicted maximum temperature value is significantly higher than the predicted average temperature value, the predicted temperature deviation increases, indicating that there are single cells with too high temperatures, which may cause thermal runaway.

[0082] Similarly, the temperature offset between battery cells in actual application scenarios can be pre-divided into multiple temperature ranges, with each temperature range pre-assigned a corresponding second abnormality level. The larger the second abnormality level, the more likely thermal runaway will occur. The predicted temperature offset is matched with the preset temperature ranges. Based on the second abnormality level corresponding to the matched target temperature range, the predicted abnormality level corresponding to the battery cell temperature is determined, intuitively reflecting the severity of the battery temperature abnormality.

[0083] Exemplarily, the number of preset temperature definition intervals can also be three, the first preset temperature definition interval [0℃, 4℃), the value of the second preset abnormality level of the first preset temperature definition interval is 0, the second preset temperature definition interval [4℃, 11℃), the value of the second preset abnormality level of the second preset temperature definition interval is 1, and the third preset temperature definition interval [11℃, +∞), the value of the second preset abnormality level of the third preset temperature definition interval is 2.

[0084] In this embodiment, by predicting the temperature deviation, the temperature rise trend caused by thermal abuse is captured, and the thermal runaway chain reaction is intervened in advance.

[0085] Furthermore, as a refinement and expansion of the specific implementation methods of the above-mentioned embodiment, in order to fully illustrate the specific implementation process of this embodiment, the thermal runaway indicator includes the concentration of the target gas inside the containerized energy storage system, and the target gases include carbon monoxide, carbon dioxide and hydrogen. According to the predicted data of the thermal runaway indicator, the predicted abnormality degree of the thermal runaway indicator is determined, specifically including: determining the predicted concentration deviation of the target gas based on the predicted data of the target gas concentration at the target prediction time and the monitoring data of the target gas concentration at the initial time in the monitoring cycle; matching the predicted concentration deviation with the preset concentration definition interval corresponding to the target gas, and determining the predicted abnormality degree of the target gas concentration based on the third preset abnormality degree corresponding to the target concentration definition interval matched by the predicted concentration deviation.

[0086] In this embodiment, the concentration of the target gas in the thermal runaway indicator is analyzed separately. Specifically, based on the predicted target gas concentration data within the containerized energy storage system at a specific future time point and the difference between the target gas concentration data at the initial time of the monitoring cycle, the target gas concentration deviation over a period of time in the future (i.e., the predicted concentration deviation) is predicted. This predicted concentration deviation quantifies the gas generation situation and reflects the intensity of the chemical reaction.

[0087] Similarly, the concentration offset of the target gas in actual application scenarios can be pre-divided into multiple concentration ranges, with each concentration range pre-assigned a corresponding third abnormality level, such as 0, 1, or 2. The larger the third abnormality level, the more likely thermal runaway will occur. The predicted concentration deviation of the target gas is matched with the preset concentration range corresponding to the target gas. Based on the third preset abnormality level corresponding to the matched target concentration range, the predicted abnormality level corresponding to the target gas concentration is determined as the thermal runaway indicator, distinguishing normal gas fluctuations from thermal runaway characteristic gases.

[0088] In this embodiment, the intensity of the thermal runaway chemical reaction is monitored by the predicted concentration deviation of the target gas to prevent the risk of explosion.

[0089] Step 104 : Determine the predicted total abnormality level of the containerized energy storage system at the target prediction time based on the predicted abnormality level of the thermal runaway indicator.

[0090] In this embodiment, the predicted abnormality levels of various thermal runaway indicators are combined to determine the total predicted abnormality level of the containerized energy storage system at the target prediction time, comprehensively reflecting the abnormal condition of the entire containerized energy storage system at a specific future time. This allows for dynamic triggering of warnings or firefighting actions based on the predicted total abnormality level, avoiding misjudgments based on a single parameter and improving response rationality.

[0091] For example, after the predicted abnormality level values of the thermal runaway indicators are determined respectively, the predicted total abnormality level value may be calculated by an adder.

[0092] Step 105: If the predicted total abnormality level is within the preset warning range, trigger a warning operation corresponding to the predicted total abnormality level.

[0093] In this embodiment, it is determined whether the predicted total abnormality level is within a preset warning range. When the predicted total abnormality level is within the preset warning range, it is considered that thermal runaway is about to occur, and corresponding warning operations are performed to achieve early warning of the energy storage thermal runaway state.

[0094] Here, the preset warning range can be reasonably set according to the actual application scenario. For example, the preset warning range can be set to 1-5.

[0095] Further, as a refinement and expansion of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process of this embodiment, an early warning system is set on the containerized energy storage system, and the preset early warning range includes a first early warning range, a second early warning range, and a third early warning range. If the predicted total abnormality level is within the preset early warning range, an early warning operation corresponding to the predicted total abnormality level is triggered, specifically including: if the predicted total abnormality level is within the preset early warning range, generating early warning information, and sending the early warning information to the terminal corresponding to the containerized energy storage system; if the predicted total abnormality level is within the first early warning range, controlling the yellow light of the main indicator light in the early warning system to turn on, and controlling the yellow light to flash at a first preset frequency; if the predicted total abnormality level is within the second early warning range, controlling the buzzer in the early warning system to beep according to the first preset early warning time, and controlling the red light of the main indicator light to turn on, and controlling the red light to flash at a second preset frequency; if the predicted total abnormality level is within the third early warning range, controlling the buzzer to beep according to the second preset early warning time, and controlling the red light of the main indicator light to turn on, and controlling the red light to flash at a third preset frequency.

[0096] The first preset frequency, the second preset frequency and the third preset frequency increase in sequence, and the first preset warning time is shorter than the second preset warning time.

[0097] In this embodiment, the preset warning range is further divided into a first warning range, a second warning range, and a third warning range. Based on different warning ranges and corresponding warning operations, a hierarchical warning mechanism is established. This allows operators to intervene and address any abnormalities in the containerized energy storage system at an early stage, preventing minor problems from escalating into major failures. By promptly detecting and addressing abnormalities, the safe and stable operation of the containerized energy storage system is ensured, reducing the probability of serious accidents such as fires and explosions caused by thermal runaway, and protecting personnel, equipment, and property.

[0098] Specifically, such as Figure 2 As shown, an early warning system is installed on the containerized energy storage system, and the early warning system is used to perform corresponding early warning operations. The early warning system includes a buzzer, a main indicator light, and communication equipment. If the predicted overall abnormality level falls within the first early warning range, the buzzer does not activate, the main indicator light turns yellow, and the flashing frequency is 20 times / s (i.e., the first preset frequency). The early warning information is immediately sent to the operator via the communication equipment, alerting them to the presence of a certain system abnormality and requiring attention. If the predicted overall abnormality level falls within the second early warning range, the buzzer beeps briefly, the main indicator light turns red, and the flashing frequency is 40 times / s (i.e., the second preset frequency). The early warning information is immediately sent to the operator via the communication equipment, strengthening the warning and alerting them to the increasing severity of the system abnormality. If the predicted overall abnormality level falls within the third early warning range, the buzzer beeps continuously, the main indicator light turns red, and the flashing frequency is 60 times / s (i.e., the third preset frequency). The early warning information is immediately sent to the operator via the communication equipment, strongly warning them of the serious system abnormality and prompting them to take prompt action.

[0099] For example, the preset warning range can be set to 1-5, the first warning range can be set to 1, the second warning range can be set to 2-3, and the third warning range can be set to 4-5.

[0100] In this embodiment, warning information, indicator lights of varying colors and flashing frequencies, and buzzer beeping durations visually communicate to operators the predicted overall abnormality level of the containerized energy storage system. The differentiated warning operations for different warning ranges help guide operators in adopting appropriate response strategies, enabling hierarchical risk management and improving response efficiency.

[0101] Step 106: If the predicted total abnormality level is greater than the upper limit of the preset warning range, a firefighting operation is triggered.

[0102] In this embodiment, a determination is made as to whether the predicted total abnormality level is within a preset warning range. When the predicted total abnormality level is greater than the upper limit of the preset warning range, it is considered that the containerized energy storage system is likely to have experienced thermal runaway during the current monitoring cycle, and appropriate firefighting operations are performed to prevent accidents caused by the spread of fire.

[0103] Furthermore, as a refinement and expansion of the specific implementation of the above-mentioned embodiment, and to fully illustrate the specific implementation process of this embodiment, a fire extinguishing system, a smoke exhaust system, and a fire detection system are provided on the containerized energy storage system. The fire extinguishing system includes a fire extinguishing agent storage tank, a fire extinguishing agent delivery device, and an electromagnetic initiator. The thermal runaway indicator includes the concentration of the target gas within the containerized energy storage system. If the predicted total abnormality level exceeds the upper limit of the preset warning range, a firefighting operation is triggered. Specifically, the operation includes: if the predicted total abnormality level exceeds the upper limit of the preset warning range, generating firefighting information and sending the firefighting information to the terminal corresponding to the containerized energy storage system; if the predicted total abnormality level exceeds the upper limit of the preset warning range and the fire detection system detects a fire, controlling the electromagnetic initiator in the fire extinguishing system to activate, so that the fire extinguishing system can spray the fire extinguishing agent in the fire extinguishing agent storage tank through the fire extinguishing agent delivery device into the containerized energy storage system to extinguish the fire; if the predicted total abnormality level exceeds the upper limit of the preset warning range and the monitoring data of the combustible gas concentration in the target gas exceeds the preset concentration threshold, controlling the smoke exhaust system to activate to exhaust the gas within the containerized energy storage system.

[0104] Specifically, such as Figure 2 As shown, a fire extinguishing system, a smoke exhaust system, and a fire detection system are installed on the containerized energy storage system. The fire extinguishing system includes a fire extinguishing agent storage tank, a fire extinguishing agent delivery device, and an electromagnetic starter. The smoke exhaust system mainly includes air conditioning and exhaust fans. The fire detection system includes smoke and temperature fire detectors, and cameras are set up for remote monitoring.

[0105] For example, smoke and heat detectors can be placed above the center of the battery compartment in a containerized energy storage system. Combined with air-cooled air conditioning, they effectively monitor the smoke volume fraction and top temperature within the containerized energy storage system. The fire extinguishing system's fire extinguishing agent nozzles are located at the top of the containerized energy storage system to ensure rapid coverage. The smoke exhaust system's air conditioning and exhaust fans work together to control the battery compartment temperature within a range of 10-30°C, ensuring a favorable operating temperature for the containerized energy storage system. In the event of a fire, smoke and gases are promptly exhausted to prevent the spread of the fire.

[0106] Furthermore, if the predicted total abnormality exceeds the upper limit of the preset warning range, and the fire detection system detects a fire during the current monitoring cycle, the electromagnetic initiator of the fire extinguishing agent bottle is activated, spraying a certain concentration of fire extinguishing agent into the containerized energy storage system through the fire extinguishing agent delivery device to extinguish the fire. Firefighting information is immediately transmitted to the operator using the communication equipment in the early warning system. If the predicted total abnormality exceeds the upper limit of the preset warning range, and the concentration of combustible gas in the target gas exceeds the preset concentration threshold during the current monitoring cycle, the air conditioner / exhaust fan is activated to exhaust smoke and gas, preventing the continuous increase in internal pressure of the containerized energy storage system from causing the energy storage battery to explode, ensuring the safety of personnel and equipment. Firefighting information is immediately transmitted to the operator using the communication equipment in the early warning system.

[0107] For example, if the preset warning range is 1-5, when the predicted total abnormality level is greater than 5, it is considered that the containerized energy storage system is likely to have thermal runaway, and corresponding firefighting operations are performed.

[0108] This application analyzes the dynamic evolution of multi-dimensional characteristic signals during the thermal runaway process of containerized energy storage systems, identifies thermal runaway indicators with significant early-stage changes, and constructs a hierarchical thermal runaway warning strategy that couples multiple thermal runaway indicators. Based on abnormal operating conditions of the containerized energy storage system, effective proactive safety warnings and fire control measures are implemented. Multi-sensor fusion is employed to comprehensively identify early-stage thermal runaway states, addressing the false alarm and missed alarm issues common in existing containerized energy storage systems. Effective fire control is achieved through the linkage of early warning systems, fire extinguishing systems, smoke exhaust systems, and fire detection systems.

[0109] It should be noted that the size of the serial numbers of the steps in the above embodiments 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 this application.

[0110] Furthermore, if Figure 3 As shown, as a specific implementation of the thermal runaway risk prevention and control method for the above-mentioned containerized energy storage system, an embodiment of the present application provides a thermal runaway risk prevention and control device 300 for a containerized energy storage system. The thermal runaway risk prevention and control device 300 for a containerized energy storage system includes: an acquisition module 301, a determination module 302, and an operation module 303.

[0111] The acquisition module 301 is configured to acquire monitoring data of the containerized energy storage system within a monitoring period based on the thermal runaway indicator;

[0112] Determination module 302 is configured to input the monitoring data of the thermal runaway indicator into an indicator prediction model to determine the predicted data of the thermal runaway indicator at a target prediction time. The target prediction time is the time after a preset period of time after the end of the monitoring period. The indicator prediction model determines the target time based on the long short-term memory network and the historical data of the thermal runaway indicator; and, based on the predicted data of the thermal runaway indicator, determine the predicted abnormality level of the thermal runaway indicator; and, based on the predicted abnormality level of the thermal runaway indicator, determine the predicted total abnormality level of the containerized energy storage system at the target prediction time.

[0113] The operation module 303 is used to trigger the warning operation corresponding to the predicted total abnormality level if the predicted total abnormality level is within the preset warning range; and to trigger the firefighting operation if the predicted total abnormality level is greater than the upper limit of the preset warning range.

[0114] In one embodiment, the thermal runaway risk prevention and control device 300 of the containerized energy storage system further includes:

[0115] The training module is used to obtain the first historical data of the containerized energy storage system within the historical monitoring period based on the thermal runaway indicator; mark the first historical data of the thermal runaway indicator according to the second historical data of the thermal runaway indicator at the historical prediction moment, and the historical prediction moment is the moment after a preset time after the end of the historical monitoring period; and train the long short-term memory network based on the marked first historical data of the thermal runaway indicator to obtain the indicator prediction model, so that the indicator prediction model can predict the predicted data of the thermal runaway indicator at the target prediction moment based on the input monitoring data of the thermal runaway indicator.

[0116] In one embodiment, the determination module 302 is specifically used to determine the predicted average voltage value and the predicted minimum voltage value of the single cell battery based on the predicted data of the voltage of the single cell battery; determine the predicted voltage deviation of the single cell battery based on the predicted average voltage value and the predicted minimum voltage value of the single cell battery; match the predicted voltage deviation with a preset voltage definition interval, and determine the predicted abnormality degree of the voltage of the single cell battery based on a first preset abnormality degree corresponding to the target voltage definition interval matched by the predicted voltage deviation.

[0117] In one embodiment, the determination module 302 is specifically used to determine the predicted average temperature value and the predicted maximum temperature value of the single cell battery based on the predicted temperature data of the single cell battery; determine the predicted temperature deviation of the single cell battery based on the predicted average temperature value and the predicted maximum temperature value of the single cell battery; match the predicted temperature deviation with a preset temperature definition interval, and determine the predicted abnormality degree of the temperature of the single cell battery based on a second preset abnormality degree corresponding to the target temperature definition interval matched by the predicted temperature deviation.

[0118] In one embodiment, the determination module 302 is specifically used to determine the predicted concentration deviation of the target gas based on the predicted data of the target gas concentration at the target prediction time and the monitoring data of the target gas concentration at the initial time in the monitoring period; match the predicted concentration deviation with the preset concentration definition interval corresponding to the target gas, and determine the predicted abnormality degree of the target gas concentration based on the third preset abnormality degree corresponding to the target concentration definition interval matched by the predicted concentration deviation.

[0119] In one embodiment, the operation module 303 is specifically configured to generate a warning message if the predicted total abnormality level is within a preset warning range, and send the warning message to a terminal corresponding to the containerized energy storage system; if the predicted total abnormality level is within a first warning range, control the yellow light of the main indicator light in the warning system to turn on, and control the yellow light to flash at a first preset frequency; if the predicted total abnormality level is within a second warning range, control the buzzer in the warning system to beep according to the first preset warning time, control the red light of the main indicator light to turn on, and control the red light to flash at a second preset frequency; if the predicted total abnormality level is within a third warning range, control the buzzer to beep according to the second preset warning time, control the red light of the main indicator light to turn on, and control the red light to flash at a third preset frequency; wherein the first preset frequency, the second preset frequency, and the third preset frequency increase in sequence, and the first preset warning time is less than the second preset warning time.

[0120] In one embodiment, the operation module 303 is specifically configured to generate firefighting information and send the firefighting information to a terminal corresponding to the containerized energy storage system if the predicted total abnormality level is greater than the upper limit of the preset warning range. If the predicted total abnormality level is greater than the upper limit of the preset warning range and the fire detection system detects a fire, the electromagnetic starter in the fire extinguishing system is activated to enable the fire extinguishing system to spray the fire extinguishing agent in the fire extinguishing agent storage tank into the interior of the containerized energy storage system through the fire extinguishing agent delivery device to extinguish the fire. If the predicted total abnormality level is greater than the upper limit of the preset warning range and the monitoring data of the combustible gas concentration in the target gas is greater than a preset concentration threshold, the smoke exhaust system is activated to exhaust the gas inside the containerized energy storage system.

[0121] The specific definition of the thermal runaway risk prevention and control device for a containerized energy storage system can be found in the definition of the thermal runaway risk prevention and control method for a containerized energy storage system described above, and will not be repeated here. The various modules in the thermal runaway risk prevention and control device for the containerized energy storage system described above can be implemented in whole or in part through software, hardware, or a combination thereof. The aforementioned modules can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so that the processor can call and execute the operations corresponding to the aforementioned modules.

[0122] Based on the above Figure 1 The method shown in FIG. 1 is a method for performing the above-mentioned operation. Accordingly, the embodiment of the present application further provides a readable storage medium having a computer program stored thereon. When the computer program is executed by the processor, the computer program is executed as shown in FIG. Figure 1 The thermal runaway risk prevention and control method for the containerized energy storage system is shown.

[0123] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each implementation scenario of the present application.

[0124] Based on the above Figure 1 The method shown, and Figure 3 In order to achieve the above-mentioned purpose, the embodiment of the present application further provides a computer device, which can be a personal computer, a server, a network device, etc. The computer device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figure 1 The thermal runaway risk prevention and control method for the containerized energy storage system is shown.

[0125] Optionally, the computer device may further include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a Wi-Fi module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a Bluetooth interface, a Wi-Fi interface), etc.

[0126] Those skilled in the art will understand that the computer device structure provided in this embodiment does not constitute a limitation on the computer device, and may include more or fewer components, or a combination of certain components, or different component arrangements.

[0127] The storage medium may also include an operating system and a network communication module. An operating system is a program that manages and stores the hardware and software resources of a computer device, supporting the execution of information processing programs and other software and / or programs. The network communication module facilitates communication between components within the storage medium, as well as with other hardware and software within the physical device.

[0128] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented with the help of software plus the necessary general hardware platform, and can also implement the embodiments of the present application through hardware.

[0129] Those skilled in the art will understand that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily required to implement the present application. Those skilled in the art will understand that the modules in the devices in the implementation scenario can be distributed in the devices of the implementation scenario according to the implementation scenario description, or can be changed accordingly and located in one or more devices different from the implementation scenario. The modules of the above-mentioned implementation scenario can be combined into one module, or can be further split into multiple sub-modules.

[0130] The serial numbers of the above application are for descriptive purposes only and do not represent the advantages or disadvantages of the implementation scenarios. The above disclosure only discloses several specific implementation scenarios of the present application, but the present application is not limited thereto. Any changes that can be conceived by those skilled in the art should fall within the scope of protection of the present application.

Claims

1. A method for preventing and controlling thermal runaway risks of a containerized energy storage system, characterized in that: The method comprises: Acquire monitoring data of the containerized energy storage system within the monitoring period based on thermal runaway indicators; Inputting the monitoring data of the thermal runaway indicator into an indicator prediction model to determine the predicted data of the thermal runaway indicator at a target prediction time, wherein the target prediction time is a time after a preset time period after the end of the monitoring period, and the indicator prediction model is determined based on a long short-term memory network and historical data of the thermal runaway indicator; determining a predicted abnormality degree of the thermal runaway indicator based on the predicted data of the thermal runaway indicator; Determining a predicted total abnormality level of the containerized energy storage system at the target prediction time based on the predicted abnormality level of the thermal runaway indicator; If the predicted total abnormality level is within the preset warning range, triggering a warning operation corresponding to the predicted total abnormality level; If the predicted total abnormality level is greater than the upper limit of the preset warning range, a firefighting operation is triggered.

2. The method for preventing and controlling thermal runaway risks of a containerized energy storage system according to claim 1, wherein: The historical data of the thermal runaway indicator includes first historical data and second historical data, and the method further includes: Acquire the first historical data of the containerized energy storage system within a historical monitoring period based on the thermal runaway indicator; Marking the first historical data of the thermal runaway indicator according to the second historical data of the thermal runaway indicator at a historical prediction time, where the historical prediction time is a time after the preset time period has elapsed since the end of the historical monitoring period; The long short-term memory network is trained based on the first historical data of the labeled thermal runaway indicator to obtain the indicator prediction model, so that the indicator prediction model can predict the predicted data of the thermal runaway indicator at the target prediction time based on the input monitoring data of the thermal runaway indicator.

3. The method for preventing and controlling thermal runaway risks of a containerized energy storage system according to claim 1, wherein: The thermal runaway indicator includes the voltage of a single battery in the containerized energy storage system. Determining the predicted abnormality degree of the thermal runaway indicator based on the predicted data of the thermal runaway indicator specifically includes: Determining a predicted average voltage value and a predicted minimum voltage value of the single cell according to the predicted data of the voltage of the single cell; Determining a predicted voltage deviation of the single cell according to the predicted average voltage value and the predicted minimum voltage value of the single cell; The predicted voltage deviation is matched with a preset voltage boundary interval, and the predicted abnormality degree of the voltage of the single battery is determined according to a first preset abnormality degree corresponding to the target voltage boundary interval matched with the predicted voltage deviation.

4. The method for preventing and controlling thermal runaway risks of a containerized energy storage system according to claim 1, wherein: The thermal runaway indicator includes the temperature of a single battery in the containerized energy storage system. Determining the predicted abnormality degree of the thermal runaway indicator based on the predicted data of the thermal runaway indicator specifically includes: Determining a predicted average temperature value and a predicted maximum temperature value of the single cell according to the predicted data of the temperature of the single cell; Determining a predicted temperature deviation of the single cell according to the predicted average temperature value and the predicted maximum temperature value of the single cell; The predicted temperature deviation is matched with a preset temperature boundary interval, and the predicted abnormality degree of the temperature of the single battery is determined according to a second preset abnormality degree corresponding to the target temperature boundary interval matched with the predicted temperature deviation.

5. The method for preventing and controlling thermal runaway risks of a containerized energy storage system according to claim 1, wherein: The thermal runaway index includes the concentration of target gases within the containerized energy storage system, where the target gases include carbon monoxide, carbon dioxide, and hydrogen. Determining the predicted abnormality level of the thermal runaway index based on the predicted data of the thermal runaway index specifically includes: determining a deviation of the predicted concentration of the target gas according to predicted data of the concentration of the target gas at the target prediction time and monitored data of the concentration of the target gas at an initial time in the monitoring period; The predicted concentration deviation is matched with a preset concentration boundary interval corresponding to the target gas, and the predicted abnormality degree of the concentration of the target gas is determined according to a third preset abnormality degree corresponding to the target concentration boundary interval matched with the predicted concentration deviation.

6. The method for preventing and controlling thermal runaway risks of a containerized energy storage system according to claim 1, wherein: An early warning system is provided on the containerized energy storage system. The preset early warning range includes a first early warning range, a second early warning range, and a third early warning range. If the predicted total abnormality level is within the preset early warning range, an early warning operation corresponding to the predicted total abnormality level is triggered, specifically including: If the predicted total abnormality level is within the preset warning range, generating warning information, and sending the warning information to the terminal corresponding to the containerized energy storage system; If the predicted total abnormality level is within the first warning range, controlling the yellow light of the main indicator light in the warning system to turn on, and controlling the yellow light to flash at a first preset frequency; If the predicted total abnormality level is within the second warning range, controlling the buzzer in the warning system to emit a buzzer sound according to the first preset warning time, controlling the red light of the main indicator light to turn on, and controlling the red light to flash according to the second preset frequency; If the predicted total abnormality level is within the third warning range, controlling the buzzer to emit a buzzer sound according to the second preset warning time, controlling the red light of the main indicator light to turn on, and controlling the red light to flash according to a third preset frequency; The first preset frequency, the second preset frequency and the third preset frequency increase in sequence, and the first preset warning time is shorter than the second preset warning time.

7. The method for preventing and controlling thermal runaway risks of a containerized energy storage system according to claim 1, wherein: The containerized energy storage system is equipped with a fire extinguishing system, a smoke exhaust system, and a fire detection system. The fire extinguishing system includes a fire extinguishing agent storage tank, a fire extinguishing agent delivery device, and an electromagnetic starter. The thermal runaway indicator includes the concentration of the target gas inside the containerized energy storage system. If the predicted total abnormality level exceeds the upper limit of the preset warning range, a firefighting operation is triggered, specifically including: If the predicted total abnormality level is greater than the upper limit of the preset warning range, firefighting information is generated and sent to a terminal corresponding to the containerized energy storage system; If the predicted total abnormality level is greater than the upper limit of the preset warning range and the fire detection system detects a fire, the electromagnetic starter in the fire extinguishing system is controlled to be activated, so that the fire extinguishing system can spray the fire extinguishing agent in the fire extinguishing agent storage tank into the interior of the containerized energy storage system through the fire extinguishing agent delivery device to extinguish the fire; If the predicted total abnormality level is greater than the upper limit of the preset warning range, and the monitoring data of the concentration of combustible gas in the target gas is greater than the preset concentration threshold, the smoke exhaust system is controlled to start to exhaust the gas inside the containerized energy storage system.

8. A thermal runaway risk prevention and control device for a containerized energy storage system, characterized in that: The device comprises: An acquisition module, used to obtain monitoring data of the containerized energy storage system within a monitoring period based on the thermal runaway indicator; a determination module, configured to input the monitoring data of the thermal runaway indicator into an indicator prediction model, and determine prediction data of the thermal runaway indicator at a target prediction time, wherein the target prediction time is a time after a preset period of time after the end of the monitoring period, and the indicator prediction model is determined based on a long short-term memory network and historical data of the thermal runaway indicator; and Determining the predicted abnormality degree of the thermal runaway indicator based on the predicted data of the thermal runaway indicator; and Determining a predicted total abnormality level of the containerized energy storage system at the target prediction time based on the predicted abnormality level of the thermal runaway indicator; an operation module, configured to trigger an early warning operation corresponding to the predicted total abnormality level if the predicted total abnormality level is within a preset early warning range; and If the predicted total abnormality level is greater than the upper limit of the preset warning range, a firefighting operation is triggered.

9. A readable storage medium having a program or instruction stored thereon, characterized in that: When the program or instruction is executed by the processor, the steps of the thermal runaway risk prevention and control method of the containerized energy storage system as described in any one of claims 1 to 7 are implemented.

10. A computer device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, wherein: When the processor executes the program, the thermal runaway risk prevention and control method for the containerized energy storage system according to any one of claims 1 to 7 is implemented.

Images