Thermal runaway risk management method and equipment for energy storage system

Abstract

The invention discloses an energy storage system thermal runaway risk management method and equipment, and belongs to the technical field of energy storage system risk management. Real-time monitoring data and state data in the operation process of an energy storage system are periodically acquired, and then the data are identified through a thermal runaway risk classification model trained by big data; therefore, which risk state that the energy storage system is in thermal runaway is determined, early warning is carried out, synchronous management is carried out, and the possibility of thermal risk occurrence is reduced.

Description

Technical Field

[0001] This invention belongs to the field of energy storage system risk management technology, specifically relating to a method and device for thermal runaway risk management of energy storage systems. Background Technology

[0002] Thermal runaway risk in energy storage systems refers to the phenomenon where, during charging or discharging, the battery temperature rises sharply due to internal short circuits or other reasons, leading to uncontrolled battery performance. When thermal runaway occurs in a battery within an energy storage system, the battery releases a large amount of heat and flammable gases, which can easily cause fires or even explosions, resulting in serious casualties and property damage. Simultaneously, thermal runaway leads to excessively high battery temperatures, accelerating battery aging and performance degradation. Therefore, managing thermal runaway risk can effectively prevent and control the occurrence of such accidents.

[0003] Existing methods for managing thermal runaway in energy storage systems mainly rely on fixed temperature thresholds and simple sensor monitoring, making it difficult to provide early warnings and precise management of thermal runaway risks. Summary of the Invention

[0004] The purpose of this invention is to provide a method and device for thermal runaway risk management in energy storage systems, aiming to solve the technical problem that existing thermal runaway management methods for batteries in energy storage systems are unable to provide early warning and accurate management of thermal runaway risks.

[0005] To solve the above problems, the present invention adopts the following technical solution: A method for managing thermal runaway risk in an energy storage system includes the following steps: Acquire monitoring and status data of the energy storage system; The monitoring data of the energy storage system is preprocessed and then input together with the state data into a pre-trained thermal runaway risk classification model for further processing to obtain the risk level identification results. The energy storage system is intelligently adjusted based on the risk level identification results.

[0006] Furthermore, the training method for the thermal runaway risk classification model includes: Acquire thermal runaway data from several energy storage systems; the thermal runaway data includes: monitoring data and status data of the energy storage system. The monitoring data of the energy storage system is preprocessed and classified according to risk level to obtain the corresponding risk level identification results; The monitoring data, risk level identification results, and corresponding state data of the classified energy storage system are input into the initial neural network for training until convergence, thus obtaining the thermal runaway risk classification model.

[0007] Furthermore, the risk level identification results include: low-risk status, medium-risk status, and high-risk status; Based on the risk level identification results, the energy storage system is intelligently adjusted, including: If the risk level identification result is low risk, the monitoring data and status data of the energy storage system will be reacquired after a preset time for judgment. If the risk level identification result is medium risk, an early warning will be activated and adjustments will be made to the energy storage system based on monitoring data; If the risk level identification result is high risk, immediately disconnect the power to the energy storage system and start the cooling system to cool it down.

[0008] Furthermore, the acquisition of monitoring data for the energy storage system includes: Based on image acquisition methods, image data and standard image data of the energy storage system are obtained; the image data includes external images and internal images; the standard image data includes standard images and standard internal images at different power levels. The appearance image and the standard image are partitioned according to the same preset rules to obtain several sub-appearance images and several sub-standard images; Several sub-appearance images and several sub-standard images are matched one-to-one and their image similarity is calculated. Based on the image similarity, the deformed sub-appearance image of the sub-appearance image relative to the sub-standard image is determined. The damage data of the external lines is determined based on the location corresponding to the appearance image of the deformable element and the preset energy storage line and appearance mapping table. Acquire line operation data, system power, and status data of the energy storage system; Determine the standard internal image corresponding to the current internal image based on system power and status data; Internal anomaly data is determined based on internal images, standard internal images corresponding to the internal images, and a preset energy storage line and appearance mapping table. Monitoring data is determined based on external line damage data, internal anomaly data, line operation data, and system power.

[0009] Furthermore, internal anomaly data is determined based on the internal image, the corresponding standard internal image, and a preset energy storage line and appearance mapping table, including: The internal image and the standard internal image are partitioned according to the same preset rules to obtain several sub-internal images and several sub-standard internal images; Calculate the difference between the pixel value of each pixel in each sub-internal image and the pixel value of the same coordinate in the corresponding sub-standard internal image to obtain the pixel difference; Pixels in each sub-image whose pixel difference is greater than a preset pixel value are identified as abnormal pixels. The sub-internal image is determined as an abnormal sub-internal image based on the proportion of abnormal pixels in each sub-internal image; if it is an abnormal sub-internal image, the internal abnormal data is determined based on the location of the abnormal sub-internal image and the preset energy storage line and appearance mapping table.

[0010] Furthermore, based on the risk level identification results, the energy storage system is intelligently adjusted, including: Obtain the output power and the area division data of the energy storage system based on the division of each line; The heat generation of each zone is determined based on the zone data; it is then determined whether there are any zones with heat generation greater than the preset heat generation; if so, the power is immediately cut off and the cooling system is activated to cool down the zones with heat generation greater than the preset heat generation. If it does not exist, calculate the heat potential value based on the regional data and calorific value, using the following formula:

[0011] in, For the first The potential heat values ​​of each divided region In order to be with the first The total number of adjacent partitioned regions. For the first The first division region and the first The shortest distance between adjacent partitioned regions, These are hot pixel values. For the first The area of ​​each divided region; The heat display value is calculated based on the heat potential value of each divided region and its corresponding adjacent divided regions. The calculation formula is as follows:

[0012] in, This is the thermal display value. For the first The first partitioned region The heat potential value of each adjacent partitioned region, For the first The potential heat values ​​of each divided region; The reduced power distribution factor is calculated based on the thermal potential value, using the following formula:

[0013] in, For the first The power allocation coefficient of each partitioned region is reduced. For the first The first partitioned region The heat display value of each adjacent divided region; The output power is allocated based on the reduced power allocation factor.

[0014] Furthermore, the allocation of the output power to be allocated according to the reduced power allocation coefficient includes: Based on the reduction of the power allocation coefficient, the power allocation is layered into different regions to obtain the power allocation layering results for each region. Based on the power allocation hierarchy results, the output power to be allocated is obtained to obtain the preliminary power allocation results; Based on statistical principles, the initial power allocation results are fine-tuned to obtain the final power allocation result.

[0015] Secondly, a thermal runaway risk management system for an energy storage system is provided, comprising an acquisition module, an output module, and an adjustment module, wherein: Acquisition module: Used to acquire monitoring and status data of the energy storage system; Output module: Used to preprocess the monitoring data of the energy storage system and input it together with the state data into the trained thermal runaway risk classification model for processing to obtain the risk level identification result; Adjustment module: Used to intelligently adjust the energy storage system based on the risk level identification results.

[0016] Thirdly, a terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method.

[0017] Fourthly, a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method.

[0018] Compared with the prior art, the present invention has the following beneficial technical effects: This invention provides a method for thermal runaway risk management of energy storage systems. By periodically acquiring real-time monitoring data and status data during the operation of the energy storage system, and then using a thermal runaway risk classification model trained with big data to identify these data, the method determines which risk state the energy storage system is in, thereby providing early warning and enabling synchronous management to reduce the possibility of thermal risk.

[0019] Preferably, the present invention optimizes the power allocation scheme of the current energy storage system by calculating the reduced power allocation coefficient and performing power allocation layering for each divided area, thereby avoiding an increase in the probability of thermal runaway; at the same time, by assessing the thermal situation of each divided area, the heat accumulation on each line is reduced; thus, the heat distribution of the entire energy storage system is controlled more accurately, improving the overall performance and safety of the system. Attached Figure Description

[0020] Figure 1 This is a flowchart of a thermal runaway risk management method for an energy storage system according to an embodiment of the present invention; Figure 2 This is a flowchart illustrating the monitoring data acquisition process in an embodiment of the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. 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.

[0022] In the description of this invention, it should be understood that the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0023] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0024] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Additionally, the character " / " in this invention generally indicates that the preceding and following objects have an "or" relationship.

[0025] It should be understood that although terms such as first, second, third, etc., may be used in the embodiments of the present invention to describe the preset range, these preset ranges should not be limited to these terms. These terms are only used to distinguish the preset ranges from one another. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0026] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0027] The accompanying drawings illustrate various structural schematic diagrams according to embodiments disclosed in this invention. These drawings are not to scale, and some details have been enlarged for clarity, and some details may have been omitted. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.

[0028] A method for managing the thermal runaway risk of an energy storage system, such as Figure 1 As shown, it includes the following steps: S1: Obtain monitoring and status data of the energy storage system; S2: Preprocess the monitoring data of the energy storage system and input it along with the state data into the trained thermal runaway risk classification model for further processing to obtain the risk level identification result: S3: Intelligent adjustment of the energy storage system based on the risk level identification results; The training methods for the thermal runaway risk classification model include: Acquire thermal runaway data from several energy storage systems; the thermal runaway data includes: monitoring data and status data of the energy storage system. The monitoring data of the energy storage system is preprocessed and classified according to risk level to obtain the corresponding risk level identification results; The monitoring data, risk level identification results, and corresponding state data of the classified energy storage system are input into the initial neural network for training until convergence, thus obtaining the thermal runaway risk classification model. Existing electrochemical energy storage systems typically include multiple battery packs, battery energy output lines, battery charging lines, a battery management system (BMS), a cooling system, and external wiring interfaces. When energy storage is needed, the system outputs energy from the batteries through the pre-connected external wiring interfaces and battery energy output lines. Simultaneously, batteries with insufficient charge are charged via the charging lines. All these charging and discharging processes are controlled by the BMS. However, during operation, various factors can lead to battery thermal runaway. When thermal runaway occurs, the battery releases a large amount of heat and flammable gases, which can easily cause spontaneous combustion. Furthermore... When a battery in an energy storage system experiences thermal runaway, the excessively high temperature accelerates battery aging and performance degradation, reducing the system's lifespan. Therefore, thermal runaway management is necessary to ensure the system's safety and lifespan. Thermal runaway management begins with data collection from various sensors installed throughout the system. This data includes internal and external images, and measurements of current, voltage, and temperature at different locations. Simultaneously, the Battery Management System (BMS) determines the state of each battery within the system, providing status data. For example, battery A... The system is in a charging state, with the battery level at 60%. Then, the monitoring data for current and voltage in the energy storage system undergoes preprocessing such as anomaly removal and normalization. For example, if the voltage data at a certain moment differs significantly from the current data, that data is deleted and replaced with data from the previous moment. Simultaneously, the hardware structure of the energy storage system is determined using internal and external images. The preprocessed monitoring data and hardware structure information are then input into a trained thermal runaway risk classification model for evaluation. The model comprehensively assesses various types of data to obtain the risk level identification result. The risk level identification result includes: low risk... The system is classified into three risk states: high-risk, medium-risk, and medium-risk. The system determines which state of thermal runaway risk it is currently in and adopts corresponding countermeasures. During the training of the thermal runaway risk classification model, various operational data of the energy storage system stored in the database are acquired. This data is preprocessed to determine the battery status, current, and other data during system operation, as well as the risk level identification result under the current data. Then, the battery status, current, and other data, along with the risk level identification result, are used as sample data and input into the initial neural network model for training until convergence, resulting in a well-trained thermal runaway risk classification model. By periodically acquiring real-time monitoring and status data during the operation of the energy storage system, and then using a thermal runaway risk classification model trained with big data to identify these data, the system can determine which risk state of thermal runaway it is in, thus enabling early warning and synchronous management to reduce the possibility of thermal risks.

[0029] In one embodiment, the risk level identification results include: low-risk status, medium-risk status, and high-risk status; The energy storage system is intelligently adjusted based on the risk level identification results, including: If the risk level identification result is low risk, the monitoring data and status data of the energy storage system will be reacquired after a preset time for judgment. If the risk level identification result is medium risk, an early warning will be activated and adjustments will be made to the energy storage system based on monitoring data; If the risk level identification result is high risk, immediately disconnect the power to the energy storage system and start the cooling system to cool it down.

[0030] After determining the current thermal runaway risk status of the energy storage system using the thermal runaway risk classification model, i.e., the risk level identification result, if the risk level identification result is low risk, it indicates that the energy storage system is currently operating normally, the probability of thermal runaway is extremely small, and no management or adjustment is required. Then, after a preset time, the monitoring data and status data of the energy storage system are reacquired for judgment. If the risk level identification result is medium risk, it indicates that the energy storage system has a not low probability of thermal runaway risk. If left unattended, there is a certain safety hazard. Therefore, a reminder will be issued to the maintenance personnel so that they can make some preparations. At the same time, the current operation plan of the energy storage system will be adjusted according to the monitoring data of the energy storage system to avoid the continued operation of the current plan leading to an increase in the risk of thermal runaway. If the risk level identification result is high risk, it indicates that there is already a location in the energy storage system with an abnormal temperature rise, and there is a high probability of thermal runaway risk. The charging and discharging of the battery controlling the energy storage system will be stopped immediately, and an alarm will be issued to remind the maintenance personnel to manage it. At the same time, the internal cooling system will be started at maximum power to cool down the energy storage system and prevent thermal runaway from occurring. By accurately identifying the low-risk state of thermal runaway in energy storage systems, unnecessary intervention is avoided, reducing other safety risks that may be introduced due to excessive intervention. Simultaneously, it ensures that the normal operation of the energy storage system is not disrupted by misjudgments when the system is running normally. Furthermore, when the energy storage system is identified as being in a medium-risk state, early warnings and adjustments to the operating plan can effectively curb the further development of thermal runaway risks. This early intervention can nip thermal runaway accidents in the bud, preventing uncontrollable thermal runaway. When the energy storage system is detected to be in a high-risk state, battery charging and discharging are immediately stopped and cooling measures are initiated—an emergency response to thermal runaway risks. This rapid response can prevent the spread of thermal runaway, avoiding serious damage to the battery pack or even more serious safety accidents such as fires, greatly ensuring the safe operation of the energy storage system. At the same time, by identifying risks in advance and taking measures, the probability of thermal runaway accidents is reduced. Once a thermal runaway accident occurs, it may lead to a series of problems such as battery damage and system failure, resulting in extremely high repair costs. The application of this model can effectively avoid this situation, reducing the costs of component replacement and equipment repair required for accident maintenance.

[0031] In one embodiment, the method for obtaining monitoring data of the energy storage system is as follows: Figure 2 As shown, it includes: S11: Based on image acquisition methods, acquire image data and standard image data of the energy storage system; wherein, the image data includes: external images and internal images; the standard image data includes: standard images and standard internal images at different power levels; S12: Divide the appearance image and the standard image into several sub-appearance images and several sub-standard images according to the same preset rules; S13: Match several sub-appearance images with several sub-standard images one by one and calculate their image similarity. Determine the deformed sub-appearance image of the sub-appearance image relative to the sub-standard image based on the image similarity. S14: Determine the external line damage data based on the location corresponding to the deformable appearance image and the preset energy storage line and appearance mapping table; S15: Obtain line operation data, system power, and status data of the energy storage system; S16: Determine the standard internal image corresponding to the current internal image based on system power and status data; S17: Determine internal anomaly data based on internal images, standard internal images corresponding to internal images, and preset energy storage lines and appearance mapping tables; S18: Determine monitoring data based on external line damage data, internal anomaly data, line operation data, and system power; During data acquisition from the energy storage system, various sensors installed within the system collect operational data such as current, voltage, temperature, and system power. System power refers to the output power of each battery during operation. The Battery Management System (BMS) also determines the status data of each battery. Image acquisition involves using cameras installed within the system to photograph the circuit components and batteries, obtaining both external and internal images. For example, external images are obtained by photographing the circuit components, while X-ray images are obtained by photographing the internal components. The battery is photographed to obtain an internal image. This internal image is then compared with a standard internal image, determined based on system power and status data, and internal anomalies are identified according to the comparison results and a pre-defined energy storage circuit-to-exterior mapping table. Simultaneously, the exterior image and the standard image are partitioned according to the same pre-defined rules, resulting in several sub-exterior images and several sub-standard images. The pre-defined rules divide the area based on the region occupied by a single component in the circuit, ensuring that each sub-exterior image and sub-standard image contains only one component. Then, these sub-exterior images and sub-standard images are mapped one-to-one, and their image similarity is calculated. The calculation method for similarity is existing technology and will not be elaborated here. A similarity value is obtained for each sub-appearance image. Sub-appearance images with similarity values ​​less than a preset similarity value are selected as deformed sub-appearance images. Then, based on the position of the deformed sub-appearance image in the appearance image and a preset energy storage line-appearance mapping table, the specific component in the line that has suffered mechanical damage is determined, obtaining external line damage data. Then, monitoring data is determined based on the external line damage data, internal anomaly data, line operation data, and system power. The standard image includes a standard image and standard internal images at different power levels. The standard image is obtained after the energy storage system is installed, through phase... Images captured by the camera show the energy storage system when it is operating normally; standard internal images at different power levels are internal images captured by an infrared camera during the initial operation of the energy storage system; a pre-set mapping table between energy storage lines and the external appearance is used to determine which specific line and which specific component is damaged, based on the location of components in the specific energy storage system structure and the corresponding components in the energy storage system lines; to reduce operational data, maintenance personnel can automatically adjust the acquisition frequency of external and internal images as needed; and when assessing risk levels, the corresponding line damage data and internal anomaly data use the data from the previous acquisition. By collecting operational data such as current, voltage, temperature, and system power, and combining this with battery status data determined by the BMS, a comprehensive understanding of the energy storage system's operating status can be achieved. Simultaneously, by comparing internal images with standard internal images, abnormal internal data can be accurately identified, allowing for timely detection of potential thermal runaway risks. Furthermore, by comparing external images with standard images in different zones, deformable external images can be accurately filtered out, and a mapping table can be used to determine the mechanical damage of specific components. This multi-dimensional data acquisition and analysis method can comprehensively and accurately identify potential fault points in the energy storage system, effectively reducing the probability of safety accidents such as thermal runaway and mechanical failures. Moreover, by comparing internal images with standard internal images, and by applying external image zone comparison and mapping tables, faulty components can be precisely located. Maintenance personnel can quickly locate fault points based on this information without needing to conduct a comprehensive inspection of the entire system, greatly improving maintenance efficiency and reducing operating and maintenance costs.

[0032] In one embodiment, internal anomaly data is determined based on an internal image, a standard internal image corresponding to the internal image, and a preset energy storage line-appearance mapping table, including: S171: Divide the internal image and the standard internal image into several sub-internal images and several sub-standard internal images according to the same preset rules; S172: Calculate the difference between the pixel value of each pixel in each sub-internal image and the pixel value of the same coordinate in the corresponding sub-standard internal image to obtain the pixel difference; S173: Identify pixels in each sub-image whose pixel difference is greater than a preset pixel value as abnormal pixels; S174: Determine whether a sub-internal image is an abnormal sub-internal image based on the proportion of abnormal pixels in each sub-internal image; if it is an abnormal sub-internal image, determine the internal abnormal data based on the location of the abnormal sub-internal image and the preset energy storage line and appearance mapping table.

[0033] In the process of identifying internal anomaly data through internal images, the internal images and standard internal images are partitioned according to the same preset rules to obtain several sub-internal images and several sub-standard internal images. The preset rules are based on the area occupied by a single battery in the circuit, ensuring that each sub-exterior image and sub-standard image contains only one battery. Then, the difference between the pixel value of each pixel in each sub-internal image and the pixel value at the same coordinate in the corresponding sub-standard internal image is calculated. Pixels in each sub-internal image whose pixel difference is greater than a preset pixel value are identified as anomaly pixels. The proportion of anomalous pixels in each sub-internal image is then calculated (proportion = number of anomalous pixels / total number of pixels). If the proportion is less than a preset proportion, the sub-internal image is considered normal; if the proportion is greater than a preset proportion, it is considered an anomalous sub-internal image. If it is an anomalous sub-internal image, the battery with the internal anomaly is determined based on the location of the anomalous sub-internal image and a preset energy storage circuit-exterior mapping table, thus obtaining the internal anomaly data. By partitioning the internal image and the standard internal image according to preset rules, each sub-internal image and sub-standard internal image contains only one battery. This precise partitioning method can ensure that the abnormal state of each battery can be analyzed separately, thereby determining which battery has a discharge problem.

[0034] In one embodiment, intelligent adjustment of the energy storage system based on risk level identification results includes: S321: Obtain the output power and the division area data of the energy storage system based on the division of each line; S322: Determine the heat generation of each zone based on the zone division data; and determine whether there are any zones with heat generation greater than the preset heat generation; if so, immediately cut off the power and start the cooling system to cool down the zones with heat generation greater than the preset heat generation. S323: If it does not exist, calculate the heat potential value based on the regional data and calorific value. The calculation formula is as follows:

[0035] in, For the first The potential heat values ​​of each divided region In order to be with the first The total number of adjacent partitioned regions. For the first The first division region and the first The shortest distance between adjacent partitioned regions, These are hot pixel values. For the first The area of ​​each divided region; S324: Calculate the heat display value based on the heat potential value of each divided region and its corresponding adjacent divided regions. The calculation formula is as follows:

[0036] in, This is the thermal display value. For the first The first partitioned region The heat potential value of each adjacent partitioned region, For the first The potential heat values ​​of each divided region; S325: Calculate the reduced power distribution factor based on the thermal potential value, using the following formula:

[0037] in, For the first The power allocation coefficient of each partitioned region is reduced. For the first The first partitioned region The heat display value of each adjacent divided region; S326: Allocate the output power according to the reduced power allocation factor; The process of allocating the output power according to the reduced power allocation factor includes: Based on the reduction of the power allocation coefficient, the power allocation is layered into different regions to obtain the power allocation layering results for each region. Based on the power allocation hierarchy results, the output power to be allocated is obtained to obtain the preliminary power allocation results; Based on statistical principles, the initial power allocation results are fine-tuned to obtain the final power allocation result.

[0038] When an energy storage system outputs power, the BMS (Battery Management System) typically controls the power output ratio of each battery in the system to achieve the required output power. When a single battery outputs power, it is usually through a corresponding circuit. When the energy storage system is in a medium-risk state, it indicates a certain risk of thermal runaway. To reduce the probability of thermal runaway, the operating scheme of the energy storage system is adjusted. Before adjusting the scheme, damage data is used to determine which circuits in the energy storage system are damaged, and damaged circuits are eliminated, i.e., charging and discharging are stopped. Then, the remaining circuits are divided into zones, with each circuit serving as a separate zone. The system divides the system into multiple regions and acquires voltage and current data from monitoring data within each region. This data is then combined with preset resistance values ​​for each component as the region's data. Based on the current and resistance data within each region, the system calculates the heat dissipation per unit time for each component under its current operating condition. The heat generated per unit time by all components within a given line is summed to obtain the heat output of that region. The system then determines whether any region has a heat output exceeding a preset limit. If such a region exists, it is powered off and excluded from subsequent power allocation planning. If not, the system calculates the thermal potential value of the current region to determine the current energy storage system's operating plan. The potential heat accumulation level (heat potential value) within the divided area is then calculated. Based on the heat potential value, a heat display value is calculated, and then a power reduction coefficient for each divided area is calculated. Next, power allocation is stratified for each divided area based on the power reduction coefficient, resulting in a stratified power allocation result for each area. Specifically, the divided areas are sorted according to the magnitude of the power reduction coefficient, and then multiple divided areas are stratified, ensuring that the number of lines in each layer is as similar as possible. Each layer corresponds to a certain output power. The total output power ratio is calculated based on the output power and line data of each layer to obtain a preliminary power allocation result. Finally, based on statistical principles, the preliminary power allocation is further refined. The allocation results are fine-tuned to obtain the final power allocation result. Specifically, if the initial power allocation result is greater than 100%, the excess proportion is subtracted from the line with the highest power reduction allocation coefficient; if the initial power allocation result is less than 100%, the difference proportion is allocated to the line with the smallest power reduction allocation coefficient, thus obtaining the final power allocation result. The operation plan of the energy storage system is then adjusted based on this result. In calculating the thermal potential value and thermal representation, the closest values ​​of components between two adjacent lines are incorporated to account for the heat generated by adjacent lines, reducing heat accumulation on each line. The larger the calculated power reduction allocation coefficient, the more the allocated output power needs to be reduced in that area. By acquiring line damage data, it is possible to accurately identify which lines in the energy storage system are damaged. This allows for targeted cessation of charging and discharging operations on damaged lines, preventing further escalation of potential short circuits, overheating, and other abnormalities, thus effectively reducing the risk of thermal runaway. When a region is found to have heat generation exceeding a preset threshold per unit time, timely intervention can effectively prevent excessive local heat accumulation and avoid heat diffusion leading to wider thermal runaway. Furthermore, by calculating a reduced power allocation coefficient, power allocation can be stratified across different regions, optimizing the current power distribution scheme of the energy storage system and preventing an increase in the probability of thermal runaway. Simultaneously, by assessing the heat conditions in each region, heat accumulation on each line can be reduced. This allows for more accurate control of the heat distribution throughout the energy storage system, improving overall system performance and safety.

[0039] This invention also provides a thermal runaway risk management system for an energy storage system, comprising an acquisition module, an output module, and an adjustment module, wherein: Acquisition module: Used to acquire monitoring and status data of the energy storage system; Output module: Used to preprocess the monitoring data of the energy storage system and input it together with the state data into the trained thermal runaway risk classification model for processing to obtain the risk level identification result; Adjustment module: Used to intelligently adjust the energy storage system based on the risk level identification results.

[0040] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can be implemented in one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs) containing computer-usable program code. The form of a computer program product implemented on ROM, optical memory, etc.

[0041] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0042] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0043] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0044] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit its scope of protection. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that after reading the present invention, they can still make various changes, modifications or equivalent substitutions to the specific implementation of the invention, but these changes, modifications or equivalent substitutions are all within the scope of protection of the pending claims of the invention.

Claims

1. A method for managing thermal runaway risk in an energy storage system, characterized in that, Includes the following steps: Acquire monitoring and status data of the energy storage system; The monitoring data of the energy storage system is preprocessed and then input together with the state data into a pre-trained thermal runaway risk classification model for further processing to obtain the risk level identification results. The energy storage system is intelligently adjusted based on the risk level identification results.

2. The method for managing thermal runaway risk in an energy storage system according to claim 1, characterized in that, The training method for the thermal runaway risk classification model includes: Acquire thermal runaway data from several energy storage systems; the thermal runaway data includes: monitoring data and status data of the energy storage system. The monitoring data of the energy storage system is preprocessed and classified according to risk level to obtain the corresponding risk level identification results; The monitoring data, risk level identification results, and corresponding state data of the classified energy storage system are input into the initial neural network for training until convergence, thus obtaining the thermal runaway risk classification model.

3. The method for managing thermal runaway risk in an energy storage system according to claim 1, characterized in that, The risk level identification results include: low risk status, medium risk status, and high risk status; Based on the risk level identification results, the energy storage system is intelligently adjusted, including: If the risk level identification result is low risk, the monitoring data and status data of the energy storage system will be reacquired after a preset time for judgment. If the risk level identification result is medium risk, an early warning will be activated and adjustments will be made to the energy storage system based on monitoring data; If the risk level is identified as high-risk, immediately disconnect the power to the energy storage system and activate the cooling system to reduce the temperature.

4. The method for managing thermal runaway risk in an energy storage system according to claim 1, characterized in that, The acquisition of monitoring data for the energy storage system includes: Based on image acquisition methods, image data and standard image data of the energy storage system are obtained; the image data includes external images and internal images; the standard image data includes standard images and standard internal images at different power levels. The appearance image and the standard image are partitioned according to the same preset rules to obtain several sub-appearance images and several sub-standard images; Several sub-appearance images and several sub-standard images are matched one-to-one and their image similarity is calculated. Based on the image similarity, the deformed sub-appearance image of the sub-appearance image relative to the sub-standard image is determined. The external line damage data is determined based on the location corresponding to the deformable image and the preset energy storage line and appearance mapping table. Acquire line operation data, system power, and status data of the energy storage system; Determine the standard internal image corresponding to the current internal image based on system power and status data; Internal anomaly data is determined based on internal images, standard internal images corresponding to the internal images, and a preset energy storage line and appearance mapping table. Monitoring data is determined based on external line damage data, internal anomaly data, line operation data, and system power.

5. The method for managing thermal runaway risk in an energy storage system according to claim 4, characterized in that, Internal anomaly data is determined based on the internal image, the corresponding standard internal image, and a preset energy storage line and appearance mapping table, including: The internal image and the standard internal image are partitioned according to the same preset rules to obtain several sub-internal images and several sub-standard internal images; Calculate the difference between the pixel value of each pixel in each sub-internal image and the pixel value of the same coordinate in the corresponding sub-standard internal image to obtain the pixel difference; Pixels in each sub-image whose pixel difference is greater than a preset pixel value are identified as abnormal pixels. The sub-internal image is determined as an abnormal sub-internal image based on the proportion of abnormal pixels in each sub-internal image; if it is an abnormal sub-internal image, the internal abnormal data is determined based on the location of the abnormal sub-internal image and the preset energy storage line and appearance mapping table.

6. The method for managing thermal runaway risk in an energy storage system according to claim 1, characterized in that, Based on the risk level identification results, the energy storage system is intelligently adjusted, including: Obtain the output power and the area division data of the energy storage system based on the division of each line; The heat generation of each zone is determined based on the zone data; it is then determined whether there are any zones with heat generation greater than the preset heat generation; if so, the power is immediately cut off and the cooling system is activated to cool down the zones with heat generation greater than the preset heat generation. If it does not exist, calculate the heat potential value based on the regional data and calorific value, using the following formula: in, For the first The potential heat values ​​of each divided region In order to be with the first The total number of adjacent partitioned regions. For the first The first division region and the first The shortest distance between adjacent partitioned regions, These are hot pixel values. For the first The area of ​​each divided region; The heat display value is calculated based on the heat potential value of each divided region and its corresponding adjacent divided regions. The calculation formula is as follows: in, This is the thermal display value. For the first The first partitioned region The heat potential value of each adjacent partitioned region, For the first The potential heat values ​​of each divided region; The reduced power distribution factor is calculated based on the thermal potential value, using the following formula: in, For the first The power allocation coefficient of each partitioned region is reduced. For the first The first partitioned region The heat display value of each adjacent divided region; The output power is allocated based on the reduced power allocation factor.

7. The method for managing thermal runaway risk in an energy storage system according to claim 6, characterized in that, The power to be distributed according to the reduced power distribution factor includes: Based on the reduction of the power allocation coefficient, the power allocation is layered into different regions to obtain the power allocation layering results for each region. Based on the power allocation hierarchy results, the output power to be allocated is obtained to obtain the preliminary power allocation results; Based on statistical principles, the initial power allocation results are fine-tuned to obtain the final power allocation result.

8. A thermal runaway risk management system for an energy storage system, characterized in that, It includes an acquisition module, an output module, and an adjustment module, among which: Acquisition module: Used to acquire monitoring and status data of the energy storage system; Output module: Used to preprocess the monitoring data of the energy storage system and input it together with the state data into the trained thermal runaway risk classification model for processing to obtain the risk level identification result; Adjustment module: Used to intelligently adjust the energy storage system based on the risk level identification results.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements as claimed in claim 1.

7. The steps of any of the methods described.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements as described in claim 1.

7. The steps of any of the methods described.

Images