An energy storage system thermal runaway early warning method, system, terminal and medium

Abstract

The application provides a kind of energy storage system thermal runaway early warning method, system, terminal and medium, it is related to energy storage system safety monitoring field.The method comprises: the temperature distribution data of each row is collected in real time by temperature sensor array, the average temperature of each row is calculated according to temperature distribution data, the average temperature rise rate of each row is calculated based on the average temperature of each row, and the longitudinal temperature difference gradient between adjacent rows is calculated;The average temperature rise rate of each row and the corresponding longitudinal temperature difference gradient are weighted and fused to calculate the row-level thermal runaway early warning index of the row;The maximum value in all row-level thermal runaway early warning indexes is taken as the system thermal runaway early warning index, and different levels of warning signals are triggered according to the numerical range of the system thermal runaway early warning index.The application realizes early warning of thermal runaway, improves the reliability of early warning and system safety, and has strong compatibility with the immersion cooling system.

Description

Technical Field

[0001] This invention relates to the field of energy storage system safety monitoring, specifically to an early warning method, system, terminal, and medium for thermal runaway in energy storage systems. Background Technology

[0002] Lithium-ion battery energy storage systems are prone to thermal runaway during long-term operation due to factors such as overcharging, thermal abuse, and internal short circuits. This can lead to a rapid increase in temperature, fire, or even explosion, causing serious safety accidents and property damage. Cluster-level immersion cooling, which achieves efficient heat dissipation by immersing the battery modules in insulating cooling oil, has been widely adopted.

[0003] Traditional early warning methods for cluster-level immersion cooling systems mostly rely on individual cell voltage drops, fixed temperature threshold alarms, or gas detection. Voltage signal responses are lagging, meaning they can only be identified after thermal runaway has occurred. Fixed temperature thresholds are easily affected by temperature rises during normal charging and discharging, resulting in a high false alarm rate. Gas sensors have stringent requirements for the airtightness of the immersion system's chamber, limiting their application. More importantly, existing methods are all "post-event detections" after thermal runaway has occurred, failing to identify anomalies in the early stages of localized heat accumulation and struggling to capture the longitudinal temperature distribution changes within the immersion cooling system. This leads to missed opportunities for optimal intervention and fails to meet the safe operation requirements of energy storage systems. Summary of the Invention

[0004] To address the aforementioned issues, this invention provides a method, system, terminal, and medium for early warning of thermal runaway in energy storage systems. By longitudinally deploying a sensor array in the battery immersion chamber to collect temperature distribution data, early warning of thermal runaway is achieved, improving the reliability of the warning and the safety of the system. Furthermore, it exhibits strong compatibility with immersion cooling systems.

[0005] In a first aspect, the technical solution of the present invention provides an early warning method for thermal runaway in an energy storage system. This method is applied to a cluster-level submerged energy storage system and includes the following steps: The temperature distribution data of each row is collected in real time by a temperature sensor array. The temperature sensor array is arranged in the longitudinal direction inside the battery immersion chamber of the energy storage system and includes several temperature sensors installed in each battery module row. Based on the temperature distribution data, calculate the average temperature of each row, calculate the average temperature rise rate of each row based on the average temperature of each row, and calculate the longitudinal temperature gradient between adjacent rows. The average temperature rise rate and the corresponding longitudinal temperature difference gradient of each row are weighted and fused to calculate the row-level thermal runaway early warning index; The maximum value among all row-level thermal runaway warning indices is taken as the system thermal runaway warning index. Based on the numerical range of the system thermal runaway warning index, different levels of warning signals are triggered.

[0006] Secondly, the technical solution of the present invention provides an early warning system for thermal runaway in an energy storage system, implemented based on the above-mentioned method, including: A temperature data acquisition module is used to collect temperature distribution data of each row in real time through a temperature sensor array. The temperature sensor array is arranged in the longitudinal direction inside the battery immersion chamber of the energy storage system and includes several temperature sensors installed in each battery module row. The temperature distribution parameter calculation module is used to calculate the average temperature of each row based on the temperature distribution data, calculate the average temperature rise rate of each row based on the average temperature of each row, and calculate the longitudinal temperature difference gradient between adjacent rows. The row-level early warning index calculation module is used to weight and fuse the average temperature rise rate and the corresponding longitudinal temperature difference gradient of each row to calculate the row-level thermal runaway early warning index of that row. The early warning triggering module is used to take the maximum value among all row-level thermal runaway early warning indices as the system thermal runaway early warning index, and trigger early warning signals of different levels according to the numerical range of the system thermal runaway early warning index.

[0007] Thirdly, the technical solution of the present invention provides a terminal, comprising: The memory is used to store early warning programs for thermal runaway in energy storage systems; A processor is configured to implement the steps of the early warning method for thermal runaway of the energy storage system as described above when executing the early warning program for thermal runaway of the energy storage system.

[0008] Fourthly, the present invention provides a computer-readable storage medium storing an early warning program for thermal runaway of an energy storage system. When the early warning program for thermal runaway of an energy storage system is executed by a processor, it implements the steps of the early warning method for thermal runaway of an energy storage system as described in any of the above claims.

[0009] As can be seen from the above technical solutions, this application has the following advantages: By deploying a temperature sensor array along the longitudinal direction inside the battery immersion chamber, real-time temperature distribution data of each row of battery modules can be collected. This enables rapid detection of abnormal temperature distribution characteristics in the early stages of thermal runaway, before local heat accumulation causes a sharp rise in cell temperature. It does not rely on lagging signals such as voltage drop or temperature over-limit, thus solving the shortcomings of existing detection methods that are slow to respond and can only detect after the fact. This enables early warning of thermal runaway, extends the emergency response window, effectively avoids the expansion of risks, and improves the operational safety of energy storage systems. Based on the overall temperature distribution, combined with the temperature rise change and longitudinal temperature difference characteristics, it can effectively distinguish between reasonable temperature rise under normal charging and discharging conditions and abnormal temperature rise caused by thermal runaway. It gets rid of the dependence on fixed temperature thresholds, reduces the probability of false triggering caused by environmental fluctuations and changes in operating conditions, and avoids risk omissions due to the concealment of local hot spots, thus improving the reliability and stability of early warning. By fully utilizing the inherent characteristics of uniform heat conduction and orderly temperature transfer along the longitudinal direction of the internal cooling oil of the cluster-level immersion cooling system, monitoring is achieved directly based on the longitudinal temperature distribution characteristics of the immersion system itself. This eliminates the need for significant modifications to the existing energy storage system structure and the addition of gas detection devices with high sealing requirements. It solves the problem of limited application of gas sensors in immersion cooling systems, is naturally compatible with immersion cooling systems, can be directly integrated into the existing thermal management architecture, and has low engineering implementation difficulty and strong versatility. Attached Figure Description

[0010] To more clearly illustrate the technical solution of this application, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a schematic flowchart of an early warning method for thermal runaway in an energy storage system provided in an embodiment of the present invention.

[0012] Figure 2 This is a schematic block diagram of an early warning system for thermal runaway in an energy storage system, provided as an embodiment of the present invention.

[0013] Figure 3 This is a schematic diagram of the structure of a terminal provided in an embodiment of the present invention. Detailed Implementation

[0014] To make the purpose, features, and advantages of this application more apparent and understandable, specific embodiments and accompanying drawings will be used to clearly and completely describe the technical solution protected by this application. Obviously, the embodiments described below are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0015] Unless otherwise defined, all technical and scientific terms used in this application have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this application and in the specification of this invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0016] Figure 1 This is a schematic flowchart illustrating an early warning method for thermal runaway in an energy storage system, provided by an embodiment of the present invention. Figure 1 The executing entity can be an early warning system for thermal runaway in an energy storage system. The early warning method for thermal runaway in an energy storage system provided in this embodiment of the invention is executed by a computer device; correspondingly, the early warning system for thermal runaway in an energy storage system runs within the computer device. Depending on different requirements, the order of the steps in this flowchart can be changed, and some steps can be omitted.

[0017] like Figure 1 As shown, the method includes the following steps.

[0018] S1, temperature distribution data of each row is collected in real time through a temperature sensor array. The temperature sensor array is arranged in the longitudinal direction inside the battery immersion chamber of the energy storage system and includes several temperature sensors installed in each battery module row.

[0019] In this embodiment, a temperature sensor array is arranged longitudinally inside the battery immersion chamber (TANK). Specifically, multiple rows of battery modules are arranged vertically within the battery immersion chamber, with each row containing several battery modules. To accurately monitor the temperature distribution of each row, several temperature sensors are installed in the battery module area of ​​each row.

[0020] In one specific implementation, at least three temperature sensors are arranged in each row of battery module areas, with each sensor equally spaced along the horizontal direction of the row. The temperature sensors are attached to the surface of the battery module to collect the surface temperature of the corresponding location; alternatively, the temperature sensors are immersed in cooling oil to collect the cooling oil temperature at the corresponding location. Both methods reflect the thermal state at that location, and the appropriate method can be selected based on actual engineering requirements.

[0021] In one specific implementation, each temperature sensor is connected to the data bus via wired or wireless means, transmitting real-time collected temperature data to the thermal management backend at a preset sampling frequency. Upon receiving the raw data from each temperature sensor, the thermal management backend first verifies the data's validity. Data that clearly exceeds a reasonable range, data with fluctuations exceeding a preset threshold, or data showing no change for multiple consecutive sampling periods is marked as invalid data. When the number of valid temperature sensors in a row is less than half of the total number of sensors in that row, a sensor fault alarm is triggered, and interpolation compensation is performed using historical data or data from adjacent sensors.

[0022] S2, based on the temperature distribution data, calculate the average temperature of each row, calculate the average temperature rise rate of each row based on the average temperature of each row, and calculate the longitudinal temperature gradient between adjacent rows.

[0023] For temperature data that passes the validity check, the average temperature of the i-th row at sampling time t is calculated using the following formula. :

[0024] in, This represents the number of valid temperature sensors in the i-th row. This represents the measured temperature value of the j-th effective temperature sensor in the i-th row.

[0025] Based on the calculated average temperature of each row, the average temperature rise rate of each row is further calculated. The temperature rise rate characterizes how quickly the temperature of that row changes over time and is used to identify local heat accumulation. For the i-th row, let the average temperature at the current sampling time t be... The average temperature at the previous sampling time t-Δt is The average temperature rise rate of that row Calculate using the following formula:

[0026] Where Δt is the sampling interval.

[0027] when A positive value indicates that the temperature of that row is rising; a negative value indicates that the temperature is falling; and zero indicates that the temperature is stable. Under normal operating conditions, the temperature rise rate during battery charging and discharging is at a low level; when local heat accumulation begins to occur in a row, the average temperature rise rate of that row will increase abnormally.

[0028] In an immersion cooling system, the cooling oil naturally forms a longitudinal temperature stratification under gravity—lower temperature at the bottom and higher temperature at the top. Under normal operating conditions, a relatively stable temperature gradient exists between adjacent rows. When localized heat accumulation occurs in a row, its temperature rises abnormally, disrupting the original temperature balance and causing an abnormal change in the longitudinal temperature gradient adjacent to that row. Based on this physical principle, this embodiment calculates the longitudinal temperature gradient between adjacent rows. The calculation formula is:

[0029] The vertical temperature gradient between adjacent rows is calculated as follows: subtract the average temperature of the row below from the average temperature of the row above, and use the difference as the vertical temperature gradient between the adjacent rows. Here, i = 1, 2, ..., m-1, and m is the total number of rows.

[0030] It should be noted that the above formula uses the order of "subtracting the next row from the previous row". This is because, under normal operating conditions, the top temperature is higher than the bottom temperature. (Above row) is usually greater than (below row), therefore Under normal operating conditions, the value is positive. When heat accumulation occurs in a row (such as the row below) causing its temperature to rise abnormally, the positive value will decrease or even become negative, thus effectively identifying abnormal events.

[0031] S3 calculates the row-level thermal runaway early warning index by weighting and fusing the average temperature rise rate and longitudinal temperature difference gradient of each row.

[0032] In this embodiment, after calculating the average temperature rise rate of each row and the vertical temperature gradient between adjacent rows, these two parameters are weighted and fused to calculate the row-level thermal runaway warning index for each row. Specifically, for the i-th row, the row-level thermal runaway warning index is calculated as follows: the average temperature rise rate of the row is multiplied by a first weighting coefficient, and the corresponding vertical temperature gradient is multiplied by a second weighting coefficient. The sum is the row-level thermal runaway warning index for that row, expressed as: The row-level thermal runaway early warning index for the i-th row = α × (average temperature rise rate of the i-th row) + β × (vertical temperature gradient corresponding to the i-th row) Where α is the weighting coefficient for the temperature rise rate and β is the weighting coefficient for the temperature difference gradient, and α+β=1, the weighting coefficients are dynamically adjusted according to the overall operating conditions of the energy storage system.

[0033] Thermal runaway typically follows this process from occurrence to propagation: abnormal heat generation occurs in a local cell → the temperature at that location rises (manifested as an increased rate of temperature rise) → heat is transferred to the surrounding area through cooling oil → affecting the temperature distribution of adjacent rows (manifested as a change in the longitudinal temperature gradient). This process involves both time and spatial dimensions.

[0034] The average temperature rise rate reflects how quickly the temperature of a row changes over time; it is a time-dimensional indicator. When localized heat accumulation occurs within a row, the average temperature rise rate of that row will show an abnormal increase. The advantage of the temperature rise rate is its fast response; it changes in the early stages of heat accumulation, before the temperature has risen significantly. However, monitoring only the temperature rise rate has limitations. During high-rate charging and discharging, the normal temperature rise rate is inherently high, which can easily be confused with abnormal temperature rises, leading to false alarms.

[0035] The longitudinal temperature gradient reflects the temperature difference between a given row and its adjacent rows, and is a spatial dimension indicator. In an immersion cooling system, the cooling oil forms a natural longitudinal temperature stratification under gravity, and a relatively stable temperature gradient exists between adjacent rows under normal operating conditions. When localized heat accumulation occurs in a row, its temperature rises abnormally, disrupting the original temperature balance and causing an abnormal change in the longitudinal temperature gradient associated with that row. The advantage of the longitudinal temperature gradient is that it can eliminate interference from normal operating temperature rises; even if the temperature of the entire system rises due to charging and discharging, as long as the temperatures of each row change synchronously, the longitudinal temperature gradient can remain relatively stable. However, single temperature gradient monitoring also has limitations: when the heat source is at the top or bottom, only the temperature difference in one direction is available for reference; furthermore, the response of the temperature gradient has a certain lag, requiring heat transfer to adjacent rows before it can be detected.

[0036] This embodiment combines the two in a weighted manner, which can simultaneously utilize the rapid response characteristics of the temperature rise rate and the common-mode suppression characteristics of the temperature difference gradient to achieve joint monitoring in both time and space dimensions, thereby improving monitoring reliability and effectively filtering out occasional fluctuations caused by interference in a single parameter.

[0037] It should be noted that step S2 calculates the vertical temperature gradient between adjacent rows, meaning that each pair of adjacent rows corresponds to a temperature gradient value. When calculating the row-level warning index for a particular row (especially the first or last row), it is necessary to specify which temperature gradient should be used for that row. This embodiment adopts the following determination rule.

[0038] (1) For the top row of the battery immersion chamber, the longitudinal temperature difference gradient between the row and the adjacent row below is used as the longitudinal temperature difference gradient of the row.

[0039] Since the first row has no adjacent row above it, only the vertical temperature difference gradient between the first and second rows is used as the temperature difference gradient corresponding to the first row. Specifically, this temperature difference gradient is equal to the average temperature of the first row minus the average temperature of the second row. Under normal operating conditions, since the temperature gradually increases from bottom to top, this difference is a positive value; when the first row generates abnormal heat or is affected by heat from below, this difference will change.

[0040] (2) For the row at the bottom of the battery immersion chamber, the longitudinal temperature difference gradient between the row and the adjacent row above is used as the longitudinal temperature difference gradient of the row.

[0041] Since the last row has no adjacent rows below it, only the vertical temperature gradient between the second-to-last row and the last row is used as the temperature gradient corresponding to the last row. Specifically, this temperature gradient is equal to the average temperature of the second-to-last row minus the average temperature of the last row.

[0042] (3) For each row located in the middle of the battery immersion chamber, the maximum value of the longitudinal temperature difference gradient between the row and the adjacent row above and the row and the adjacent row below is used as the longitudinal temperature difference gradient corresponding to the row.

[0043] For a middle row with adjacent rows above and below, the larger of the temperature difference gradient between the middle row and the adjacent row above and the adjacent row below is taken as the vertical temperature difference gradient of the middle row. This ensures that the most significant temperature difference between the middle row and the adjacent rows is captured, avoiding missed detections due to the selection of a fixed direction.

[0044] In this embodiment, the weighting coefficient α for the temperature rise rate and the weighting coefficient β for the temperature gradient are dynamically adjusted according to the overall operating conditions of the energy storage system. Under different operating conditions, the contribution of the temperature rise rate and the longitudinal temperature gradient to the thermal runaway early warning varies. By dynamically adjusting the weighting coefficients, the early warning method can adapt to different operating conditions, thereby improving the accuracy and reliability of the early warning.

[0045] Specifically, when the energy storage system is in a static state or under low-rate charge / discharge conditions, the battery itself generates relatively little heat, and the temperature rise rate under normal operating conditions is at a low level. Under these conditions, small changes in the temperature rise rate are easily affected by measurement noise, while the longitudinal temperature gradient can more stably reflect abnormal temperature distribution within the battery immersion chamber. Therefore, the weight of the temperature rise rate should be appropriately reduced, while the weight of the temperature gradient should be increased.

[0046] When an energy storage system is under high-rate charge / discharge, the battery itself generates a significant amount of heat, resulting in a high temperature rise rate even under normal operating conditions. Under these conditions, abnormal changes in the temperature rise rate are more sensitive and direct than changes in the temperature gradient, allowing for earlier detection of localized heat accumulation. Therefore, the weight of the temperature rise rate should be appropriately increased, while the weight of the temperature gradient should be decreased.

[0047] When the energy storage system is in a medium-rate charge / discharge state, the rate of temperature rise and the temperature gradient contribute equally to the early warning of thermal runaway, so they should be given the same weight.

[0048] To achieve dynamic adjustment of weighting coefficients, the charge-discharge rate (C-rate) is used as the classification criterion to divide the operating conditions of energy storage systems. The charge-discharge rate refers to the ratio of the battery's charge-discharge current to its rated capacity, which can characterize the battery's operating conditions.

[0049] As a specific implementation method, a first rate threshold and a second rate threshold are set, wherein the first rate threshold is less than the second rate threshold. Based on the relationship between the current charge / discharge rate and the above two thresholds, the operating conditions are divided into the following three states.

[0050] First operating condition (low-rate operating condition): The current charge / discharge rate is less than or equal to the first rate threshold. This operating condition corresponds to the energy storage system in a static state or a low-rate charge / discharge state.

[0051] Second operating condition (medium rate operating condition): The current charge / discharge rate is greater than the first rate threshold and less than the second rate threshold. This operating condition corresponds to the normal charge / discharge state of the energy storage system.

[0052] Third operating condition (high-rate operating condition): The current charge / discharge rate is greater than or equal to the second rate threshold. This operating condition corresponds to the high-rate charge / discharge state of the energy storage system.

[0053] The specific values ​​of the first and second rate thresholds can be calibrated based on factors such as battery type, capacity, and cooling conditions.

[0054] Based on the above working condition classification, the weighting coefficients α and β are determined according to the following rules.

[0055] (a) When the energy storage system is in the first operating condition, the temperature rise rate weighting coefficient is set as the first weighting value, the temperature difference gradient weighting coefficient is set as the second weighting value, and the first weighting value is less than the second weighting value.

[0056] Under this operating condition, due to the relatively small heat generation of the battery and the low normal temperature rise rate, the signal-to-noise ratio of the temperature rise rate is poor, while the longitudinal temperature gradient is more effective in reflecting temperature distribution anomalies. Therefore, α is set as the first weight value, β as the second weight value, and the first weight value is less than the second weight value.

[0057] As a specific implementation method, α=0.4 and β=0.6 are set. In this case, the early warning method focuses more on the change of longitudinal temperature gradient, and small temperature differences under static or low-magnification conditions can often be effectively amplified and identified.

[0058] (b) When the energy storage system is in the second operating condition, the temperature rise rate weighting coefficient is set to be equal to the temperature difference gradient weighting coefficient.

[0059] Under this condition, the battery is in a normal charge-discharge state, and both the temperature rise rate and the longitudinal temperature gradient can effectively reflect the battery's thermal state. Their contributions to thermal runaway early warning are roughly equal. Therefore, α is set to be equal to β.

[0060] As a specific implementation method, α=0.5 and β=0.5 are set. In this case, the early warning method focuses on both the temperature rise rate and the longitudinal temperature gradient.

[0061] (c) When the energy storage system is in the third operating condition, the temperature rise rate weighting coefficient is set as the third weighting value, the temperature difference gradient weighting coefficient is set as the fourth weighting value, and the third weighting value is greater than the fourth weighting value.

[0062] Under these operating conditions, the battery generates significant heat, and the normal temperature rise rate is already at a high level. An abnormal acceleration in the temperature rise rate can reflect the occurrence of local heat accumulation earlier than the temperature gradient. Therefore, α is set as the third weight value, β as the fourth weight value, and the third weight value is greater than the fourth weight value.

[0063] As a specific implementation method, α=0.6 and β=0.4 are set. In this case, the early warning method pays more attention to the change in the rate of temperature rise, so as to ensure that early signs of thermal runaway can still be captured in time under high-rate charge and discharge conditions.

[0064] S4: Take the maximum value among all row-level thermal runaway warning indices as the system thermal runaway warning index, and trigger different levels of warning signals according to the numerical range of the system thermal runaway warning index.

[0065] Since different rows within the battery immersion chamber may be in different thermal states, this embodiment employs a maximum value strategy to determine the system thermal runaway early warning index in order to comprehensively reflect the overall risk level of the system and ensure that the most severe anomalies are not overlooked. Specifically, the maximum value among all row-level thermal runaway early warning indices is taken as the system thermal runaway early warning index. Therefore, when the heat accumulation in a certain row reaches the warning condition, the system can respond promptly even if other rows are in normal condition, avoiding delays in early warning due to local anomalies being masked by the overall average.

[0066] In this embodiment, based on the differences in battery thermal behavior and safety risks under different operating conditions, a corresponding warning threshold group is set for each operating condition. Specifically, when the energy storage system is in the first operating condition, the first threshold group is used for warning judgment and the first response strategy is executed; when the energy storage system is in the second operating condition, the second threshold group is used for warning judgment and the second response strategy is executed; when the energy storage system is in the third operating condition, the third threshold group is used for warning judgment and the third response strategy is executed. Furthermore, in this embodiment, each level of warning signal includes its own first-level warning signal, second-level warning signal, and third-level warning signal.

[0067] (1) Early warning judgment and response under the first working condition.

[0068] When the energy storage system is in the first operating condition, the first threshold group is used. The first threshold group includes a first preset threshold, a second preset threshold, and a third preset threshold, and the first preset threshold < the second preset threshold < the third preset threshold.

[0069] When the first preset threshold < system thermal runaway warning index ≤ second preset threshold, a first-level warning signal for the first operating condition is triggered. This warning signal is sent to the battery management system, instructing the battery management system to reduce the charging and discharging power to slow down the heat accumulation process.

[0070] When the second preset threshold < system thermal runaway warning index ≤ third preset threshold, the first operating condition level 2 warning signal is triggered. This warning signal is sent to the battery management system, instructing the battery management system to suspend charging and discharging operations, so that the system enters a safe standby state.

[0071] When the system thermal runaway warning index exceeds the third preset threshold, a Level 3 warning signal for the first operating condition is triggered. This warning signal is sent to the battery management system, instructing it to disconnect the cluster-level circuit to achieve electrical isolation.

[0072] (2) Early warning judgment and response under the second working condition.

[0073] When the energy storage system is in the second operating condition, the second threshold group is used. The second threshold group includes the fourth preset threshold, the fifth preset threshold, and the sixth preset threshold, and the fourth preset threshold < the fifth preset threshold < the sixth preset threshold.

[0074] When the fourth preset threshold < system thermal runaway warning index ≤ fifth preset threshold, a level one warning signal for the second operating condition is triggered. This warning signal is sent to the battery management system, instructing it to reduce charging and discharging power and enter enhanced monitoring mode, while simultaneously increasing the frequency of temperature data acquisition and recording.

[0075] When the fifth preset threshold < the system thermal runaway warning index ≤ the sixth preset threshold, a second-level warning signal for the second operating condition is triggered. Upon receiving this warning signal, the battery management system and the thermal management controller are instructed to suspend charging and discharging operations, and simultaneously instruct the thermal management controller to reduce the coolant supply temperature to enhance heat dissipation.

[0076] When the system thermal runaway early warning index exceeds the sixth preset threshold, a level three early warning signal for the second operating condition is triggered. Upon receiving this early warning signal, the battery management system and the thermal management controller are instructed to disconnect the cluster-level circuit and simultaneously instruct the fire-fighting linkage device to enter the standby state, preparing to initiate fire-fighting operations.

[0077] (3) Early warning judgment and response under the third working condition.

[0078] When the energy storage system is in the third operating condition, the third threshold group is used. The third threshold group includes the seventh preset threshold, the eighth preset threshold, and the ninth preset threshold, and the seventh preset threshold < the eighth preset threshold < the ninth preset threshold.

[0079] When the seventh preset threshold < system thermal runaway warning index ≤ eighth preset threshold, a level one warning signal for the third operating condition is triggered. This warning signal is sent to the battery management system, instructing the battery management system to immediately reduce the charging and discharging power and activate enhanced cooling to suppress heat accumulation as quickly as possible.

[0080] When the eighth preset threshold < the system thermal runaway warning index ≤ the ninth preset threshold, the third operating condition level two warning signal is triggered. Upon receiving this warning signal, the battery management system and the thermal management controller are instructed to immediately suspend charging and discharging operations, and at the same time, the thermal management controller is instructed to operate in the maximum cooling mode to remove heat to the maximum extent.

[0081] When the system thermal runaway early warning index exceeds the ninth preset threshold, a level 3 early warning signal for the third operating condition is triggered. Upon receiving this early warning signal, the battery management system, thermal management controller, and fire alarm linkage device are instructed to immediately disconnect the cluster-level circuit, the fire alarm linkage device is instructed to enter the standby state, and an audible and visual alarm is issued simultaneously.

[0082] In one specific implementation, the threshold groups for different operating conditions increase progressively, i.e., the first threshold group < the second threshold group < the third threshold group. The warning thresholds at the same level satisfy the following conditions: fourth preset threshold > first preset threshold, seventh preset threshold > fourth preset threshold, fifth preset threshold > second preset threshold, eighth preset threshold > fifth preset threshold, sixth preset threshold > third preset threshold, and ninth preset threshold > sixth preset threshold. Under the first operating condition, battery heat generation is relatively low, and the normal line-level thermal runaway warning index value is low, allowing for earlier detection of anomalies using a lower threshold. Under the second operating condition, the battery is in normal working condition, and a moderate threshold is used. Under the third operating condition, battery heat generation is relatively high, and the normal line-level thermal runaway warning index value is high, requiring a higher threshold to avoid frequent false alarms. Furthermore, due to the higher risk under this condition, more aggressive response measures are needed immediately once the threshold is exceeded.

[0083] In this embodiment, each preset threshold can be obtained through thermal runaway propagation experiments. A localized heat accumulation process is simulated on a real submerged energy storage system, and temperature data is recorded throughout the entire process from the start of heat accumulation to the occurrence of thermal runaway. The system thermal runaway early warning index at each moment is calculated, and the system thermal runaway early warning index at each stage boundary is determined as the preset threshold based on the actual progress of thermal runaway. The above describes a detailed embodiment of an early warning method for thermal runaway in an energy storage system. Based on the early warning method for thermal runaway in an energy storage system described in the above embodiment, this invention also provides an early warning system for thermal runaway in an energy storage system corresponding to this method.

[0084] Figure 2 This invention provides a schematic block diagram of an early warning system for thermal runaway in an energy storage system, implemented based on the aforementioned early warning method for thermal runaway in an energy storage system. In this embodiment, the early warning system for thermal runaway in an energy storage system can be divided into multiple functional modules according to its functions. A module, as referred to in this invention, is a series of computer program segments that can be executed by at least one processor and perform a fixed function, stored in memory.

[0085] The temperature data acquisition module is used to collect temperature distribution data of each row in real time through a temperature sensor array. The temperature sensor array is arranged longitudinally inside the battery immersion chamber of the energy storage system and includes several temperature sensors installed in each battery module row.

[0086] The temperature distribution parameter calculation module is used to calculate the average temperature of each row based on the temperature distribution data, calculate the average temperature rise rate of each row based on the average temperature of each row, and calculate the longitudinal temperature difference gradient between adjacent rows.

[0087] The row-level early warning index calculation module is used to weight and fuse the average temperature rise rate and the corresponding longitudinal temperature difference gradient of each row to calculate the row-level thermal runaway early warning index.

[0088] The early warning triggering module is used to take the maximum value among all row-level thermal runaway early warning indices as the system thermal runaway early warning index, and trigger early warning signals of different levels according to the numerical range of the system thermal runaway early warning index.

[0089] The thermal runaway early warning system of the energy storage system in this embodiment is used to implement the aforementioned thermal runaway early warning method of the energy storage system. Therefore, the specific implementation of this system can be found in the embodiment section of the thermal runaway early warning method of the energy storage system above. So, the specific implementation can be referred to the description of the corresponding embodiments, and will not be described in detail here.

[0090] Furthermore, since the early warning system for thermal runaway of the energy storage system in this embodiment is used to implement the aforementioned early warning method for thermal runaway of the energy storage system, its function corresponds to the function of the above method, and will not be repeated here.

[0091] Figure 3 This is a schematic diagram of a terminal 300 provided in an embodiment of the present invention, including: a processor 310, a memory 320, and a communication unit 330. The processor 310 is used to implement the flow steps of the above-described embodiment of the early warning method for thermal runaway of an energy storage system when implementing the early warning program for thermal runaway of an energy storage system stored in the memory 320.

[0092] This invention also provides a computer storage medium, which may be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc. The computer storage medium stores an early warning program for thermal runaway in an energy storage system. When the processor executes the early warning program for thermal runaway in an energy storage system, it implements the process steps of the above-described embodiment of the early warning method for thermal runaway in an energy storage system.

[0093] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for early warning of thermal runaway in an energy storage system, characterized in that, This method is applied to cluster-level submerged energy storage systems and includes the following steps: The temperature distribution data of each row is collected in real time by a temperature sensor array. The temperature sensor array is arranged in the longitudinal direction inside the battery immersion chamber of the energy storage system and includes several temperature sensors installed in each battery module row. Based on the temperature distribution data, calculate the average temperature of each row, calculate the average temperature rise rate of each row based on the average temperature of each row, and calculate the longitudinal temperature gradient between adjacent rows. The average temperature rise rate and the corresponding longitudinal temperature difference gradient of each row are weighted and fused to calculate the row-level thermal runaway early warning index for that row. The maximum value among all row-level thermal runaway warning indices is taken as the system thermal runaway warning index. Based on the numerical range of the system thermal runaway warning index, different levels of warning signals are triggered.

2. The method for early warning of thermal runaway in an energy storage system according to claim 1, characterized in that, The average temperature rise rate of each row is calculated as follows: subtract the average temperature of the row at the previous sampling time from the average temperature of the row at the current sampling time, divide the difference by the sampling interval, and obtain the average temperature rise rate of the row. The vertical temperature gradient between adjacent rows is calculated by subtracting the average temperature of the lower row from the average temperature of the upper row, and the difference is taken as the vertical temperature gradient between the adjacent rows.

3. The method for early warning of thermal runaway in an energy storage system according to claim 1, characterized in that, The longitudinal temperature gradient for calculating the row-level thermal runaway early warning index is determined according to the following rules: For the top row of the battery immersion chamber, the longitudinal temperature difference gradient between that row and the adjacent row below it is used as the longitudinal temperature difference gradient for that row. For the row at the bottom of the battery immersion chamber, the longitudinal temperature difference gradient between this row and the adjacent row above it is used as the longitudinal temperature difference gradient for this row. For each row located in the middle of the battery immersion chamber, the maximum value of the longitudinal temperature difference gradient between the row and the adjacent row above and the row and the adjacent row below is used as the longitudinal temperature difference gradient corresponding to that row.

4. The method for early warning of thermal runaway in an energy storage system according to claim 1, characterized in that, The row-level thermal runaway early warning index of the i-th row = α × (average temperature rise rate of the i-th row) + β × (vertical temperature gradient corresponding to the i-th row). Where α is the weighting coefficient for the temperature rise rate and β is the weighting coefficient for the temperature difference gradient, and α+β=1, the weighting coefficients are dynamically adjusted according to the overall operating conditions of the energy storage system.

5. The method for early warning of thermal runaway in an energy storage system according to claim 4, characterized in that, The overall operating conditions of the energy storage system include: the first operating condition when the charge / discharge rate is less than or equal to the first rate threshold, the second operating condition when the charge / discharge rate is greater than the first rate threshold and less than the second rate threshold, and the third operating condition when the charge / discharge rate is greater than or equal to the second rate threshold. The weighting coefficients are dynamically adjusted based on the overall operating conditions of the energy storage system, specifically including: When the energy storage system is in the first operating condition, the temperature rise rate weighting coefficient is set as the first weighting value, the temperature difference gradient weighting coefficient is set as the second weighting value, and the first weighting value is less than the second weighting value. When the energy storage system is in the second operating condition, the temperature rise rate weighting coefficient is set to be equal to the temperature difference gradient weighting coefficient. When the energy storage system is in the third operating condition, the temperature rise rate weighting coefficient is set as the third weighting value, the temperature difference gradient weighting coefficient is set as the fourth weighting value, and the third weighting value is greater than the fourth weighting value.

6. The method for early warning of thermal runaway in an energy storage system according to claim 5, characterized in that, Based on the numerical range of the system thermal runaway early warning index, when different levels of early warning signals are triggered, early warning threshold groups and early warning response strategies are set according to the operating conditions of the energy storage system for each operating condition: When the energy storage system is in the first operating condition, the first threshold group is used for early warning judgment and the first response strategy is executed; When the energy storage system is in the second operating condition, the second threshold group is used for early warning judgment and the second response strategy is executed; When the energy storage system is in the third operating condition, the third threshold group is used for early warning judgment and the third response strategy is executed.

7. The method for early warning of thermal runaway in an energy storage system according to claim 6, characterized in that, The first threshold group includes a first preset threshold, a second preset threshold, and a third preset threshold. The first response strategy is: When the system thermal runaway warning index is greater than the first preset threshold and less than or equal to the second preset threshold, the first operating condition level one warning signal is triggered, instructing the battery management system to reduce the charging and discharging power. When the system thermal runaway warning index is greater than the second preset threshold and less than or equal to the third preset threshold, the first operating condition level two warning signal is triggered, instructing the battery management system to suspend charging and discharging operations. When the system thermal runaway early warning index is greater than the third preset threshold, the first operating condition level three early warning signal is triggered, instructing the battery management system to disconnect the cluster-level circuit; The second threshold group includes a fourth preset threshold, a fifth preset threshold, and a sixth preset threshold. The second response strategy is as follows: When the system thermal runaway warning index is greater than the fourth preset threshold and less than or equal to the fifth preset threshold, the second operating condition level one warning signal is triggered, instructing the battery management system to reduce the charging and discharging power and enter the enhanced monitoring mode. When the system thermal runaway warning index is greater than the fifth preset threshold and less than or equal to the sixth preset threshold, the second operating condition level 2 warning signal is triggered, instructing the battery management system to suspend charging and discharging operations and instructing the thermal management controller to reduce the coolant supply temperature. When the system thermal runaway early warning index is greater than the sixth preset threshold, the second working condition level three early warning signal is triggered, instructing the battery management system to disconnect the cluster-level circuit and instructing the fire-fighting linkage device to enter the standby state. The third threshold group includes the seventh preset threshold, the eighth preset threshold, and the ninth preset threshold. The third response strategy is: When the system thermal runaway warning index is greater than the seventh preset threshold and less than or equal to the eighth preset threshold, the third operating condition level one warning signal is triggered, instructing the battery management system to immediately reduce the charging and discharging power and start enhanced cooling. When the system thermal runaway warning index is greater than the eighth preset threshold and less than or equal to the ninth preset threshold, the third operating condition level two warning signal is triggered, instructing the battery management system to immediately suspend charging and discharging operations and instructing the thermal management controller to operate in the maximum cooling mode. When the system thermal runaway early warning index exceeds the ninth preset threshold, the third working condition level three early warning signal is triggered, instructing the battery management system to immediately disconnect the cluster-level circuit, instructing the fire-fighting linkage device to enter the standby state, and issuing an audible and visual alarm.

8. An early warning system for thermal runaway in an energy storage system, characterized in that, The method is implemented based on any one of claims 1 to 7, comprising: A temperature data acquisition module is used to collect temperature distribution data of each row in real time through a temperature sensor array. The temperature sensor array is arranged in the longitudinal direction inside the battery immersion chamber of the energy storage system and includes several temperature sensors installed in each battery module row. The temperature distribution parameter calculation module is used to calculate the average temperature of each row based on the temperature distribution data, calculate the average temperature rise rate of each row based on the average temperature of each row, and calculate the longitudinal temperature difference gradient between adjacent rows. The row-level early warning index calculation module is used to weight and fuse the average temperature rise rate and the corresponding longitudinal temperature difference gradient of each row to calculate the row-level thermal runaway early warning index of that row. The early warning triggering module is used to take the maximum value among all row-level thermal runaway early warning indices as the system thermal runaway early warning index, and trigger early warning signals of different levels according to the numerical range of the system thermal runaway early warning index.

9. A terminal, characterized in that, include: The memory is used to store early warning programs for thermal runaway in energy storage systems; A processor is configured to implement the steps of the early warning method for thermal runaway of an energy storage system as described in any one of claims 1 to 7 when executing the early warning program for thermal runaway of the energy storage system.

10. A computer-readable storage medium, characterized in that, The readable storage medium stores an early warning program for thermal runaway of an energy storage system, which, when executed by a processor, implements the steps of the early warning method for thermal runaway of an energy storage system as described in any one of claims 1 to 7.

Images