A method and device for risk assessment and fire-fighting configuration of an energy storage battery cabin

Abstract

This invention relates to the field of energy storage battery safety technology, and particularly to a method, apparatus, equipment, and computer-readable storage medium for risk assessment and fire protection configuration of energy storage battery compartments. The method includes: collecting and preprocessing operational data of the energy storage battery compartment; calculating a comprehensive risk score for each battery module based on the preprocessed operational data, and constructing a comprehensive risk ranking list based on the comprehensive risk scores; and dynamically configuring fire safety strategies and assessing heat distribution based on the comprehensive risk ranking list. By introducing a dynamic grouping mechanism based on health status and a spatiotemporal risk index, a spatial context risk index and a temporal dynamic enhancement factor are constructed, significantly improving the accuracy of fire risk assessment for non-uniformly aging battery compartments.

Description

Technical Field

[0001] This application relates to the field of energy storage battery safety technology, and in particular to a method, apparatus, electronic device and computer-readable storage medium for risk assessment and fire protection configuration of an energy storage battery compartment. Background Technology

[0002] As a key energy storage unit in a power system, the safe and stable operation of the energy storage battery compartment is crucial. Lithium-ion batteries are widely used due to their high energy density and long cycle life, but they are prone to thermal runaway under abnormal operating conditions such as overcharging, over-discharging, and internal short circuits, which can lead to fires or even explosions. To ensure the safety of energy storage systems, fire warning and extinguishing systems are typically deployed.

[0003] Existing technologies have significant drawbacks when applied to long-term energy storage battery compartments, especially when battery modules exhibit non-uniform aging. Due to differences in manufacturing processes and uneven thermal field distribution within the compartment, the state of health (SoH) of battery modules varies. Some modules with lower SoH, due to increased internal resistance, will have a systematically higher temperature rise rate during charging and discharging compared to healthy modules. When multiple such sub-healthy modules coexist, their temperature rise rate data form a cluster characterized by "collectively high values ​​and small internal differences," resulting in a high value and low dispersion in the global data distribution. In this case, the entropy weight method may determine that the indicator has little information content due to its low data dispersion, thus assigning it an excessively low weight. This weight allocation result is seriously inconsistent with the importance of the temperature rise rate in actual physical terms, weakening the true thermal risk of sub-healthy modules in subsequent risk assessments, reducing the monitoring priority of high-risk modules, and potentially delaying the detection of early signs of thermal runaway, thus creating potential safety hazards.

[0004] Therefore, there is an urgent need for a risk assessment and fire protection configuration method for energy storage battery compartments that can accurately identify high-risk modules under non-uniform battery aging scenarios and achieve dynamic and precise allocation of fire protection resources and visualized assessment of heat distribution. Summary of the Invention

[0005] This application aims to at least partially address one of the technical problems in the related art.

[0006] Therefore, the first objective of this application is to propose a risk assessment and fire protection configuration method for energy storage battery compartments, in order to solve the problems of poor accuracy and low efficiency in risk assessment of energy storage battery compartments using existing technologies.

[0007] The second objective of this application is to provide an apparatus.

[0008] The third objective of this application is to propose an electronic device.

[0009] The fourth objective of this application is to provide a computer-readable storage medium.

[0010] To achieve the above objectives, the first aspect of this application proposes a method for risk assessment and fire protection configuration of an energy storage battery compartment, including:

[0011] Collect and preprocess operational data from the energy storage battery compartment; Based on the preprocessed battery compartment operation data, the comprehensive risk score of each battery module is calculated, and a comprehensive risk ranking list is constructed based on the comprehensive risk score. Based on the comprehensive risk ranking list, fire safety strategies are dynamically configured and heat distribution is assessed.

[0012] Preferably, the collection and preprocessing of the energy storage battery compartment operation data includes: The operating status parameters of each battery module are collected synchronously at a preset time frequency, and the operating status parameters are timestamped, validated, and outlier removed. The operating status parameters include: real-time temperature, health status value, real-time current, DC internal resistance of each battery module, real-time voltage of each individual cell, and characteristic gas concentration in the energy storage battery compartment.

[0013] Preferably, the step of calculating the comprehensive risk score of each battery module based on the preprocessed battery compartment operation data, and constructing a comprehensive risk ranking list based on the comprehensive risk scores, includes: Based on the health status values ​​of each battery module, the modules are dynamically grouped, and the spatial context risk index is calculated based on the real-time temperature rise rate, average temperature rise rate and standard deviation of each module, as well as the instantaneous power loss of the module. Calculate the time-series dynamic enhancement factor based on the spatial context risk index; The spatiotemporal risk index is calculated based on the spatial context risk index and the temporal dynamic enhancement factor. Based on the spatiotemporal risk index and the operating status parameters, the comprehensive risk score of each battery module is calculated using the entropy weight method, and a comprehensive risk ranking list is constructed based on the comprehensive risk score.

[0014] Preferably, the calculation of the time-series dynamic enhancement factor based on the spatial context risk index includes: Based on the historical sequence of the spatial context risk index of each battery module, the time-series dynamic enhancement factor is calculated by comparing the abnormal accumulation in the first preset time window with the behavioral fluctuation baseline in the second preset time window.

[0015] Preferably, the preset first time window is smaller than the preset second time window.

[0016] Preferably, the step of calculating the comprehensive risk score of each battery module using the entropy weight method based on the spatiotemporal risk index and the operating status parameters, and constructing a comprehensive risk ranking list based on the comprehensive risk scores, includes: A multi-index evaluation matrix is ​​constructed based on the spatiotemporal risk index, the real-time temperature of each battery module, the maximum single-cell voltage difference within the module, and the concentration of characteristic gases. The weight of each index in the multi-index evaluation matrix is ​​determined using the entropy weight method. Based on the index weights, the comprehensive risk score of each battery module is calculated using the approximation ideal solution ranking method. The comprehensive risk score is then used to generate a comprehensive risk ranking list.

[0017] Preferably, the step of dynamically configuring fire safety strategies and assessing heat distribution based on the comprehensive risk ranking list includes: The battery modules that rank at the top of the comprehensive risk ranking list by a predetermined proportion are identified as high-risk monitoring areas, and instructions are generated to prioritize fire-fighting resources for the high-risk monitoring areas. The risk information in the comprehensive risk ranking list is mapped onto the physical layout diagram of the energy storage battery compartment to generate a risk distribution heat map, and the heat distribution is evaluated based on the risk distribution heat map.

[0018] To achieve the above objectives, a second aspect of this application provides a risk assessment and fire protection configuration device for an energy storage battery compartment, comprising: The data acquisition module collects and preprocesses the operating data of the energy storage battery compartment; The risk calculation module calculates the comprehensive risk score of each battery module based on the preprocessed battery compartment operation data, and constructs a comprehensive risk ranking list based on the comprehensive risk score. The dynamic configuration module dynamically configures fire safety strategies and assesses heat distribution based on the comprehensive risk ranking list.

[0019] To achieve the above objectives, a third aspect of this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method described in any of the preceding descriptions.

[0020] To achieve the above objectives, a fourth aspect of this application provides a computer-readable storage medium, comprising computer-executable instructions stored therein, which, when executed by a processor, are used to implement the method described in any of the above embodiments.

[0021] This application provides a risk assessment and fire protection configuration method for energy storage battery compartments. It introduces a dynamic grouping mechanism based on health status and a spatiotemporal risk index, fundamentally addressing the technical shortcomings of existing entropy weight methods in assessing non-uniformly aging battery clusters, particularly regarding the inaccurate weighting of key indicators such as temperature rise rate. By evaluating the temperature rise behavior of modules within a similar context and dynamically weighting it based on their historical behavior, it can accurately identify truly high-risk modules, significantly improving the accuracy of fire risk assessment for non-uniformly aging battery compartments. Based on a comprehensive risk ranking list, the fire protection system can target limited, directional fire protection resources precisely and in real-time to the modules or areas with the highest risk levels, enabling the most effective intervention at the initial fire stage, greatly improving fire suppression efficiency and reducing the risk of accident escalation due to resource misallocation or response delays. Furthermore, it constructs a spatial context risk index and a temporal dynamic enhancement factor, establishing a dynamic and personalized risk assessment benchmark for each module.

[0022] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0023] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 A flowchart of a first specific embodiment of a risk assessment and fire protection configuration method for an energy storage battery compartment provided by the present invention; Figure 2 This is a structural block diagram of a risk assessment and fire protection configuration device for an energy storage battery compartment, provided as an embodiment of the present invention. Detailed Implementation

[0024] The core of this invention is to provide a method, device, electronic device and computer-readable storage medium for risk assessment and fire protection configuration of energy storage battery compartments. By introducing a dynamic grouping mechanism based on health status and a spatiotemporal risk index, a spatial context risk index and a temporal dynamic enhancement factor are constructed, which significantly improves the accuracy of fire risk assessment for non-uniformly aging battery compartments.

[0025] To enable those skilled in the art to better understand the present invention, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] Please refer to Figure 1 , Figure 1This is a flowchart of a first specific embodiment of a risk assessment and fire protection configuration method for an energy storage battery compartment provided by the present invention; the specific operation steps are as follows: Step S101: Collect and preprocess the operating data of the energy storage battery compartment; Step S102: Based on the preprocessed battery compartment operation data, calculate the comprehensive risk score of each battery module, and construct a comprehensive risk ranking list based on the comprehensive risk score; Step S103: Based on the comprehensive risk ranking list, dynamically configure the fire safety strategy and assess the heat distribution.

[0027] Based on the above embodiments, this embodiment will provide a detailed description of step S101: In one embodiment, the operating status parameters of each battery module are synchronously collected at a preset time frequency, and the operating status parameters are timestamped, validated, and outlier removed. The operating status parameters include: real-time temperature, health status value, real-time current, DC internal resistance of each battery module, real-time voltage of each individual cell, and characteristic gas concentration in the energy storage battery compartment.

[0028] Specifically, the energy storage battery compartment operation data includes two categories. The first category is data used to calculate the core risk index of this invention. Real-time temperature sequence of each battery module: collected by temperature sensors located at key positions in each battery module; The health status values ​​of each battery module are estimated and provided online by the battery management system. Real-time current of each battery module: measured by Hall sensors or shunts and recorded by the battery management system (BMS); The DC internal resistance of each battery module is estimated and provided by the BMS through an online identification algorithm; The second category: Other indicator data used to construct the final multi-indicator evaluation matrix: The real-time voltage of each individual cell within each battery module is measured and reported by the voltage acquisition unit (CMU) of the battery management system (BMS). Characteristic gas concentrations within the energy storage battery compartment: collected by gas sensors deployed within the compartment; After data acquisition, preprocessing operations are performed, including timestamp alignment of the acquired data to ensure that all parameters correspond at the same time; and data validity verification to remove outliers caused by obvious communication errors or sensor malfunctions, ensuring the quality of data input for subsequent calculations.

[0029] Based on the above embodiments, this embodiment will provide a detailed description of step S102: In one embodiment, the battery modules are dynamically grouped based on their health status values, and the spatial context risk index is calculated based on the real-time temperature rise rate, average temperature rise rate and standard deviation of each module, as well as the instantaneous power loss of that module. Specifically, we first construct a risk characteristic indicator, called the spatial context risk index. The rate of temperature rise of each battery module is comprehensively evaluated within its spatial context. This spatial context includes three dimensions: first, the relative deviation of the module's thermal behavior from that of similar modules in a similar health state; second, the real-time electrical stress currently experienced by the module; and third, the overall behavioral stability of the group to which the module belongs.

[0030] By building The index transforms the original measurement into a comprehensive risk measure that integrates status information, operating condition information, and group behavior information. This new index no longer simply reflects how much the temperature has risen, but also whether the current rate of temperature rise is abnormal, and how severe the abnormality is, given the current health status of the module, the electrical load, and the performance of similar modules. Using sequences as input to the entropy weight method allows it to break free from its dependence on the absolute value distribution of the original data and instead evaluate the true anomaly distribution. This corrects the weight suppression effect and ensures that high-risk modules can be accurately identified. The formula for calculating its spatial context risk index is as follows:

[0031] in, Indicates the first Spatial context risk index of a battery module Indicates the first The real-time temperature rise rate of each battery module. This value is determined by the temperature sensor within a preset time window (in this embodiment, the past). The temperature sequence collected within a few seconds was obtained by performing a least-squares linear fit. Indicates the first Health status of each battery module ( This value is determined by the battery management system (BMS). )supply, Dynamic grouping method: In this embodiment, Grouping is dynamically performed based on preset fixed intervals. (Settings) Interval width is Then all battery modules are divided into Multiple groups are involved. In each computation cycle, the real-time dynamics of each module are adjusted. The value is assigned to the corresponding group. Indicates the relationship with the first Battery modules belong to the same The arithmetic average rate of temperature rise of all battery modules in the group at the current moment. Indicates the first The instantaneous power loss of each battery module. In this embodiment, this value is determined by... Calculation, where This is the real-time current flowing through the module. For the reason The given module DC internal resistance. This represents a preset nominal power reference value, which is used to normalize the real-time power loss to reflect its relative relationship with the heat generation level under normal operating conditions. In this embodiment, The value is taken as the power loss value of this model of battery module under rated operating conditions. It is represented by a... indivual Lithium iron phosphate cells connected in series have a rated charge / discharge rate of [missing information]. Taking a typical energy storage battery module as an example, its rated operating current ( Under these conditions, considering that the DC internal resistance of the new battery cell at room temperature is approximately... The total internal resistance of the module is approximately Then its rated power loss In this embodiment, Set as .

[0032] Indicates the relationship with the first Each battery module belongs to the same The sample standard deviation of the temperature rise rate of all battery modules in the group at the current moment.

[0033] This represents a very small positive number used to prevent the denominator from being zero. In this embodiment, Values .

[0034] in, The index is calculated by multiplying three key risk dimensions: individual deviation, electrical stress, and group instability.

[0035] Specifically, The normalized deviation (NDR) is the basis for identifying individual anomalies. In the actual operation of energy storage modules, batteries at different aging stages have different heat generation characteristics, and directly comparing their absolute temperature rise rates can be misleading. This method measures the temperature rise rate of each module... Same as Group average By making comparisons, the evaluation benchmark is transformed from a globally uniform scale to a similar scale based on the health status of each entity. This allows true outliers to emerge, initially solving the identification difficulties caused by data clustering.

[0036] This refers to energy loss sensitivity, which introduces an electrical dimension to the risk assessment. Temperature rise is a direct result of electrical energy loss and its conversion into heat. This ensures that, for the same deviation in temperature rise, a module experiencing greater power loss will have its risk index amplified accordingly, making the assessment results more consistent with physical reality.

[0037] This refers to the group instability gain term, which is a design feature of this invention for assessing the risk state of a group. High dispersion of temperature rise rate within groups (i.e., standard deviation) A large value (in itself) is a sign that the group has entered an unstable state. Therefore, this term was designed as a gain factor. When a The group's behavior was highly consistent. When it is very small, the gain term is close to This has no additional impact on the individual risk index. However, when a Grouping behavior became chaotic. When the value is very large, the gain term will be greater than [a certain value]. , and with The risk level increases proportionally with the risk level of the individual within the unstable group. An individual from a high-risk group should have a higher base risk. Furthermore, if the individual's own deviation (the first factor) is still significant, then their final risk level will increase accordingly. The value will be further amplified on a high-risk basis, thereby enabling precise targeting of the most dangerous targets.

[0038] In one embodiment, a temporal dynamic enhancement factor is calculated based on the spatial context risk index; Based on the historical sequence of the spatial context risk index of each battery module, a time-series dynamic enhancement factor is calculated by comparing the cumulative abnormal amount within a preset first time window with the baseline of behavioral fluctuations within a preset second time window. The preset first time window is shorter than the preset second time window.

[0039] Specifically, in order to solve To address the problem of indices lacking dynamic information over time, this method proposes constructing a time-series dynamic enhancement factor. This factor establishes a dynamic time series for each battery module and uses this as a basis to assess the dynamic characteristics of its current risk status. By establishing a long-term baseline describing the historical abnormal behavior of each module and comparing its recent abnormal behavior with this baseline in real time, the degree of deviation of the current risk status from its own historical behavior pattern is quantified. This degree of deviation is the dynamic attribute of the current risk status.

[0040] Will Factors are used to enhance The index elevates the final risk assessment result from a single static risk value to a comprehensive indicator that simultaneously incorporates static spatial context and dynamic temporal evolution characteristics. This enables the system to quantify and distinguish various dynamic patterns of risk. For example, it can identify whether the current risk is a sudden event deviating from historical norms or a regular event conforming to its historical fluctuation patterns. This provides a more refined basis for subsequent risk classification and fire protection strategy configuration. The formula for calculating its time-series dynamic enhancement factor is as follows:

[0041] in, Indicates the first Timing dynamic enhancement factor for each battery module. : Represents the timestamp of the current calculation period. Indicates the first The abnormal accumulation amount of each battery module within a preset first time window. In this embodiment, the preset first time window... Set to look backwards from the current time t Seconds. This value is derived from the spatial context risk index. The historical absolute value sequence is obtained by numerical integration using the trapezoidal rule within this time window, and its calculation formula is:

[0042] Indicates the first The baseline of behavior fluctuation of each battery module within a preset second time window. In this embodiment, the preset second time window... Set as from the current time Starting from the past Hours. This value is... The integral form of the root mean square error of the historical sequence within this time window is calculated using the following formula:

[0043] in, for Historical sequences in long time windows The integral is the arithmetic mean within the range. The trapezoidal rule is also used for numerical calculation.

[0044] Analysis of the function of each part of the formula: The above The construction of factors is intended to provide a basis for the steps Static risk index calculated in The core logic of injecting dynamic information over time is to quantify the dynamic attributes of the current risk status of each battery module by comparing its recent and long-term behavior patterns.

[0045] In the actual operation of energy storage battery compartments, risk assessment cannot rely solely on instantaneous states. Therefore, this invention constructs two time-series feature quantities. and .That, That is, the short-term abnormal accumulation, through analysis of past data. Within minutes Integrating the absolute value captures the recent risk exposure intensity of the module. Using integration instead of instantaneous values ​​smooths out occasional signal spikes, providing a more stable reflection of the overall recent risk level. If a module experiences a rapid deterioration in its internal state, its... The value will remain high for a short period of time, thus leading to... The value increased significantly.

[0046] Correspondingly, That is, the long-term behavioral fluctuation baseline, through analysis of past... Hours The sequence calculates its integral form of the root mean square error, establishing a dynamic profile for each module that reflects its long-term behavioral pattern. This profile quantifies the inherent instability or volatility level of the module during long-term operation. For example, a module with stable performance and consistent state has a... It fluctuates slightly around zero for a long time. The value will be very low. Another module, which has some kind of long-term defect, has... It has been in a state of high volatility for a long time. The value will remain at a high level.

[0047] final, Factors through Function structure will and A comparison was made, and the comparison results were converted into enhancement coefficients. Ratio inside the function Essentially, it calculates the normalized deviation of recent risk accumulation from the long-term behavioral baseline. When a long-term stable module ( Low) risk suddenly appears ( When there is a surge, the deviation is positive and tends to be close to , The factor then approaches This indicates that the system has identified a sudden risk that deviates from its historical pattern. Conversely, if a module's recent risk performance ( ) and its long-standing inherent volatility level ( If they match, then the deviation approaches zero. The factor also tends to be This indicates that the system has identified the current risk state as belonging to its inertial anomalous pattern. This design enables... Factors can objectively assign dynamic attribute labels to the risk status of each module, solving the problem of... The inability of indices to distinguish between different risk evolution patterns provides crucial time-dimensional information for building a more comprehensive risk assessment model.

[0048] In one embodiment, a spatiotemporal risk index is calculated based on the spatial context risk index and the temporal dynamic enhancement factor; Specifically, the final risk index is constructed and called the spatiotemporal risk index. This index reflects the degree of deviation of a battery module from its peers, the electrical stress it withstands, and the stability of its group. It can also dynamically adjust its sensitivity to current deviation based on its historical behavior patterns. For example, for a battery module that has been subjected to... Events identified by factors as having a mutation risk. The calculation of the exponent will exponentially amplify the deviation of this event; while for an event identified as an inertial anomaly pattern, The sensitivity of the index remains at the baseline level. The formula for calculating the spatiotemporal risk index is as follows:

[0049] in, Indicates the first The final spatiotemporal risk index of each battery module. Indicates according to steps The Middle Timing dynamic enhancement factor for each battery module.

[0050] Analysis of the function of each part of the formula: This refers to the nonlinear deviation term weighted by historical confidence levels. This structure incorporates time-series dynamic enhancement factors. As a power index Deviation rate from the normalized state of the baseline Nonlinear modulation is performed. It is itself a A variable that changes continuously within a range quantifies the degree to which the module's recent risk behavior deviates from its long-term historical baseline. Therefore, This power term also follows It changes continuously within the interval.

[0051] In real-world operating scenarios, this dynamic sensitivity adjuster will adjust according to... Different values, for The calculation produces an adaptive modulation effect: when the recent risk accumulation of a module ( ) is much larger than its long-term behavioral baseline ( When this occurs, it indicates that its current state deviates significantly from historical norms. The value will approach At this point, the power index It also approaches its maximum value. This will lead to The index amplifies the normalized deviation ratio of the current state, thus exhibiting the highest sensitivity to sudden signals that indicate a rapid deterioration in the state. When the recent risk accumulation of a module ( ) and its long-term behavioral baseline ( When the patterns are largely consistent, it indicates that the current risk behavior conforms to its historical patterns. The value will approach At this point, the power index Approaching This makes The index calculation reverts to a linear deviation form without additional dynamic adjustments. When the recent risk accumulation of a module ( ) is much smaller than its long-term behavioral baseline ( When this occurs, it indicates that the module's state is transitioning from fluctuation to stability. The value will approach At this point, the power index Approaching its minimum value This is equivalent to suppressing or attenuating the state normalization deviation ratio, reducing its impact on the final risk index. By constructing... This method integrates static spatial context risk with dynamic temporal evolution characteristics into a single risk index. This index can adaptively adjust its risk assessment sensitivity based on the historical behavior of each battery module, ultimately providing input data that reflects the essence of the risk for subsequent entropy weighting and risk assessment.

[0052] In one embodiment, based on the spatiotemporal risk index and the operating status parameters, the comprehensive risk score of each battery module is calculated using the entropy weight method, and a comprehensive risk ranking list is constructed based on the comprehensive risk score.

[0053] Specifically, a multi-index evaluation matrix is ​​constructed based on the spatiotemporal risk index, the real-time temperature of each battery module, the maximum single-cell voltage difference within the module, and the concentration of characteristic gases. The entropy weight method is used to determine the weight of each index in the multi-index evaluation matrix. Based on the index weights, the comprehensive risk score of each battery module is calculated using the approximation ideal solution ranking method. The comprehensive risk score is then used to generate a comprehensive risk ranking list.

[0054] First, a multi-index evaluation matrix is ​​constructed. The rows of this matrix represent the individual battery modules within the energy storage battery compartment, and the columns represent various indicators used for risk assessment. These include: replacing the traditional temperature rise rate indicator with a spatiotemporal risk index γ, while retaining indicators directly obtained or calculated from the collected data; using the latest real-time temperature sequence value as the current module temperature; the maximum single-cell voltage difference within the module calculated based on the voltage of each individual cell; and the concentration of characteristic gases, etc. Subsequently, the evaluation matrix is ​​processed using the entropy weight method to calculate the weights of each evaluation indicator, including the γ index. Finally, combining the weights calculated by the entropy weight method with the normalized evaluation matrix, the Top-Approximation Ideal Solution Ranking Method (TOPSIS) is used to calculate the comprehensive risk score for each battery module. Based on this score, all battery modules are sorted in descending order to obtain a dynamically updated ranking list that reflects the real-time comprehensive fire risk level of each module.

[0055] Based on the above embodiments, this embodiment will provide a detailed description of step S103: In one embodiment, the battery modules with the highest preset proportion in the comprehensive risk ranking list are identified as high-risk monitoring areas, and instructions are generated to prioritize fire-fighting resources in the high-risk monitoring areas; the risk information in the comprehensive risk ranking list is mapped onto the physical layout diagram of the energy storage battery compartment to generate a risk distribution heat map, and the heat distribution is assessed based on the risk distribution heat map.

[0056] Specifically, the system identifies the top area of ​​the sorted list, i.e., the battery modules with the highest risk ranking (in this embodiment, the top 5% of modules are selected), as a high-risk monitoring area. For this area, the method outputs configuration suggestions, guiding the fire protection system to prioritize and continuously aim the physical orientation of directional fire-fighting resources (directional fire extinguishing heads) at the battery modules in the high-risk monitoring area.

[0057] The risk ranking of each battery module or its overall risk score is visualized and mapped onto the physical layout of the energy storage battery compartment, generating a risk distribution map. By observing this map, maintenance personnel can intuitively identify areas of concentrated risk. For example, if the map shows a continuous area composed of multiple high-risk modules, the assessment result indicates that this area has systemic thermal management deficiencies or collective battery aging issues, and should be listed as the highest priority area for thermal management strategy optimization and offline maintenance.

[0058] This embodiment provides a risk assessment and fire protection configuration method for energy storage battery compartments. It introduces a dynamic grouping mechanism based on health status and a spatiotemporal risk index, fundamentally addressing the technical shortcomings of existing entropy weight methods in assessing non-uniformly aging battery clusters, particularly regarding the inaccurate weighting of key indicators such as temperature rise rate. By evaluating the temperature rise behavior of modules within a similar context and dynamically weighting it based on their historical behavior, truly high-risk modules can be accurately identified, significantly improving the accuracy of fire risk assessment for non-uniformly aging battery compartments. Based on a comprehensive risk ranking list, the fire protection system can target limited, directional fire protection resources precisely and in real-time to the modules or areas with the highest risk levels, enabling the most effective intervention at the initial fire stage, greatly improving fire suppression efficiency and reducing the risk of accident escalation due to resource misallocation or response delays. A spatial context risk index and a temporal dynamic enhancement factor are constructed to establish a dynamic and personalized risk assessment benchmark for each module.

[0059] Please refer to Figure 2 , Figure 2 A structural block diagram of a risk assessment and fire protection configuration device for an energy storage battery compartment provided in an embodiment of the present invention; the specific device may include: Data acquisition module 100 collects and preprocesses the operating data of the energy storage battery compartment; The risk calculation module 200 calculates the comprehensive risk score of each battery module based on the preprocessed battery compartment operation data, and constructs a comprehensive risk ranking list based on the comprehensive risk score. The dynamic configuration module 300 dynamically configures the fire safety strategy and evaluates the heat distribution based on the comprehensive risk ranking list.

[0060] This embodiment provides a risk assessment and fire protection configuration device for an energy storage battery compartment, which is used to implement the aforementioned risk assessment and fire protection configuration method for an energy storage battery compartment. Therefore, the specific implementation of the risk assessment and fire protection configuration device for an energy storage battery compartment can be found in the embodiment section of the aforementioned risk assessment and fire protection configuration method for an energy storage battery compartment. For example, the data acquisition module 100, the risk calculation module 200, and the dynamic configuration module 300 are respectively used to implement steps S101, S102, and S103 in the aforementioned risk assessment and fire protection configuration method for an energy storage battery compartment. Therefore, the specific implementation can be referred to the description of the corresponding embodiments, which will not be repeated here.

[0061] To implement the above embodiments, this application also proposes an electronic device, including: a processor and a memory communicatively connected to the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method provided in the foregoing embodiments.

[0062] To implement the above embodiments, this application also proposes a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided in the foregoing embodiments.

[0063] To implement the above embodiments, this application also proposes a computer program product, including a computer program that, when executed by a processor, implements the methods provided in the foregoing embodiments.

[0064] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0065] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0066] This application is intended to provide an implementation scheme for users to selectively prevent the use or access to their personal information data. Specifically, this disclosure is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information is de-identified to protect user privacy.

[0067] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0068] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0069] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0070] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0071] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0072] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0073] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0074] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for risk assessment and fire protection configuration of an energy storage battery compartment, characterized in that, include: Collect and preprocess operational data from the energy storage battery compartment; Based on the preprocessed battery compartment operation data, the comprehensive risk score of each battery module is calculated, and a comprehensive risk ranking list is constructed based on the comprehensive risk score. Based on the comprehensive risk ranking list, fire safety strategies are dynamically configured and heat distribution is assessed.

2. The risk assessment and fire protection configuration method for the energy storage battery compartment according to claim 1, characterized in that, The collection and preprocessing of energy storage battery compartment operation data includes: The operating status parameters of each battery module are collected synchronously at a preset time frequency, and the operating status parameters are timestamped, validated, and outlier removed. The operating status parameters include: real-time temperature, health status value, real-time current, DC internal resistance of each battery module, real-time voltage of each individual cell, and characteristic gas concentration in the energy storage battery compartment.

3. The risk assessment and fire protection configuration method for the energy storage battery compartment according to claim 2, characterized in that, The process of calculating the comprehensive risk score for each battery module based on the preprocessed battery compartment operation data, and constructing a comprehensive risk ranking list based on the comprehensive risk scores, includes: Based on the health status values ​​of each battery module, the modules are dynamically grouped, and the spatial context risk index is calculated based on the real-time temperature rise rate, average temperature rise rate and standard deviation of each module, as well as the instantaneous power loss of the module. Calculate the time-series dynamic enhancement factor based on the spatial context risk index; The spatiotemporal risk index is calculated based on the spatial context risk index and the temporal dynamic enhancement factor. Based on the spatiotemporal risk index and the operating status parameters, the comprehensive risk score of each battery module is calculated using the entropy weight method, and a comprehensive risk ranking list is constructed based on the comprehensive risk score.

4. The risk assessment and fire protection configuration method for the energy storage battery compartment according to claim 3, characterized in that, The calculation of the time-series dynamic enhancement factor based on the spatial context risk index includes: Based on the historical sequence of the spatial context risk index of each battery module, the time-series dynamic enhancement factor is calculated by comparing the abnormal accumulation in the first preset time window with the behavioral fluctuation baseline in the second preset time window.

5. The risk assessment and fire protection configuration method for the energy storage battery compartment according to claim 4, characterized in that, The preset first time window is smaller than the preset second time window.

6. The risk assessment and fire protection configuration method for the energy storage battery compartment according to claim 3, characterized in that, The process of calculating the comprehensive risk score of each battery module using the entropy weight method based on the spatiotemporal risk index and the operating status parameters, and constructing a comprehensive risk ranking list based on the comprehensive risk scores, includes: A multi-index evaluation matrix is ​​constructed based on the spatiotemporal risk index, the real-time temperature of each battery module, the maximum single-cell voltage difference within the module, and the concentration of characteristic gases. The weight of each index in the multi-index evaluation matrix is ​​determined using the entropy weight method. Based on the index weights, the comprehensive risk score of each battery module is calculated using the approximation ideal solution ranking method. The comprehensive risk score is then used to generate a comprehensive risk ranking list.

7. The method for risk assessment and fire protection configuration of the energy storage battery compartment according to claim 1, characterized in that, The dynamic configuration of fire safety strategies and the assessment of heat distribution based on the comprehensive risk ranking list include: The battery modules that rank at the top of the comprehensive risk ranking list by a predetermined proportion are identified as high-risk monitoring areas, and instructions are generated to prioritize fire-fighting resources for the high-risk monitoring areas. The risk information in the comprehensive risk ranking list is mapped onto the physical layout diagram of the energy storage battery compartment to generate a risk distribution heat map, and the heat distribution is evaluated based on the risk distribution heat map.

8. A risk assessment and fire-fighting configuration device for an energy storage battery compartment, characterized in that, include: The data acquisition module collects and preprocesses the operating data of the energy storage battery compartment; The risk calculation module calculates the comprehensive risk score of each battery module based on the preprocessed battery compartment operation data, and constructs a comprehensive risk ranking list based on the comprehensive risk score. The dynamic configuration module dynamically configures fire safety strategies and assesses heat distribution based on the comprehensive risk ranking list.

9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

Images