Multi-stage linkage fire extinguishing method and system for energy storage system

Abstract

The invention relates to the technical field of data processing, in particular to a multi-level linkage fire extinguishing method and system for an energy storage system, and the method comprises the steps that monitoring data of all levels in the energy storage system are collected, the monitoring data comprise the temperature and the combustible gas concentration, and all the levels comprise the module level, the cluster level and the cabin level; and for a target hierarchy, carrying out denoising processing on the monitoring data, and calculating an abnormal value of the target hierarchy based on the denoised monitoring data at the current moment. According to the method, the monitoring data in the energy storage system is monitored, the abnormal value of the target level is calculated according to the similarity between the current monitoring data and the historical monitoring data, the correction factor of the monitoring data is calculated according to the change trend of the temperature and the combustible gas concentration, and the abnormal value is corrected by using the correction factor of the monitoring data; according to the method, the accuracy of the calculation process is improved, and the danger degree of each level can be accurately reflected.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology. More specifically, the present invention relates to a multi-stage linkage fire extinguishing method and system for an energy storage system. Background Art

[0002] Lithium-ion battery technology continues to evolve and innovate. Today, thanks to its high energy density, low self-discharge rate, long cycle life, and environmentally friendly advantages, it is widely used in various portable electronic products, electric vehicles, and energy storage power stations. However, due to the presence of reactive electrode materials and flammable electrolytes within them, lithium-ion batteries are prone to overheating under abuse, such as overheating, overcharging, and mechanical compression. Furthermore, due to the pursuit of high energy density, single cells are often connected in series and parallel to form modules, battery packs, and battery clusters. This spatial limitation creates a harsher heat dissipation environment, making it more likely for heat to accumulate within the battery, triggering thermal runaway. Thermal runaway can then propagate between modules and battery clusters, leading to larger-scale fires and explosions.

[0003] Most existing early warning systems monitor characteristics such as temperature and combustible gas concentration in the energy storage system. Whether a fire has occurred in the entire energy storage system is reflected based on whether these characteristics have reached a set threshold. However, they cannot accurately determine at which specific level the fire has occurred. Furthermore, when temperature sensors and gas sensors are located at different levels, they are affected by different factors in the surrounding environment. Therefore, judging whether a fire has occurred in the entire energy storage system solely by the data collected by temperature sensors and gas sensors results in unclear levels of judgment, low accuracy, and large errors, making it impossible to extinguish the fire in a timely manner. Summary of the Invention

[0004] The present invention provides a multi-level linkage fire extinguishing method and system for an energy storage system, aiming to solve the problem in the related art that only the data collected by temperature sensors and gas sensors are used to judge whether a fire has occurred in the entire energy storage system, resulting in unclear judgment levels, low accuracy and large errors.

[0005] In a first aspect, the present invention provides a multi-level linkage fire extinguishing method for an energy storage system, comprising: collecting monitoring data from each level in the energy storage system, wherein the monitoring data includes temperature and combustible gas concentration, and each level includes module level and cluster level; for a target level, performing denoising on the monitoring data, and calculating an abnormal value of the target level based on the denoised monitoring data at the current moment, wherein the abnormal value is positively correlated with the temperature and combustible gas concentration; correcting the abnormal value using a correction factor of the monitoring data at the current moment to obtain a danger level of the target level, wherein the correction factor reflects a changing trend of the temperature and combustible gas concentration within a preset time period; determining a fire extinguishing level according to the degree of danger of each level, and initiating linkage fire extinguishing according to the fire extinguishing level.

[0006] Further: calculating the danger level of the target level, including: multiplying the abnormal value of the target level by the correction factor of the monitoring data at the current moment, and taking the value of the normalized product as the danger level of the target level

[0007] Further: calculate the outlier value of the target level, the calculation formula is: Where α represents the outlier value of the target level Z, W i Indicates the i-th temperature value before the current moment, W′ i represents the i-th temperature value before the historical fire alarm moment, N represents the number of data points before the current moment; Q represents the combustible gas concentration value at the current moment, Q 安 Indicates the safe combustible gas concentration value for target level Z.

[0008] Furthermore, the correction factor of the monitoring data at the current moment is calculated, including: taking the current moment as a node, obtaining the temperature and combustible gas concentration in a preset time period before the node; calculating the correction factor of the monitoring data at the current moment, and the correction factor is positively correlated with the change amplitude of the temperature and combustible gas concentration in the preset time period.

[0009] Furthermore, the temperature and combustible gas concentration are subjected to denoising processing, including: establishing a target window with any data point in the temperature as the center, and for any data point in the target window, calculating the abnormality of the data point, wherein the abnormality is positively correlated with the difference between the variance of all data points in the target window and the variance of all data points in the target window after removing the data point; and correcting the size of the filter window according to the abnormality, and filtering the data using the corrected filter window.

[0010] Furthermore, the fire extinguishing level is determined according to the danger level of the target level, including: in response to the danger level of the module level being greater than a first threshold, the fire extinguishing level is a low level; in response to the sum of the danger level of the module level and the danger level of the cluster level being greater than a second threshold, the fire extinguishing level is a high level.

[0011] Furthermore, the linked fire extinguishing is initiated according to the fire extinguishing level, including: in response to the fire extinguishing level being a low level, only the module-level fire extinguishing device is activated; in response to the fire extinguishing level being a high level, both the module-level and cluster-level fire extinguishing devices are activated.

[0012] Furthermore, the empirical value of the first threshold is 0.7, and the empirical value of the second threshold is 0.8.

[0013] Furthermore, each level also includes cabin class.

[0014] In a second aspect, the present invention further provides a multi-stage linkage fire extinguishing system for an energy storage system, comprising a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to implement the multi-stage linkage fire extinguishing method for an energy storage system described in any one of the above methods.

[0015] Beneficial effects:

[0016] (1) First, the temperature and combustible gas concentration are subjected to denoising processing, the degree of abnormality of the data point is calculated by calculating the degree of fluctuation of the data point within the target window, and the size of the filter window is adjusted according to the degree of abnormality, thereby improving the accuracy of the filtering.

[0017] (2) By monitoring the monitoring data in the energy storage system, the abnormal value of the target level is calculated according to the similarity between the current monitoring data and the historical monitoring data, and the correction factor of the monitoring data is calculated according to the changing trend of temperature and combustible gas concentration. The correction factor of the monitoring data is used to correct the abnormal value to obtain the danger level of the target level, which improves the accuracy of the calculation process and can accurately reflect the danger level of each level. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an illustrative and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0019] Figure 1 FIG. 4 is a flow chart schematically illustrating a method for determining a fire extinguishing level according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0021] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0022] In one embodiment, most existing early warning systems monitor characteristics such as temperature and combustible gas concentration in the energy storage system. Whether a fire has occurred in the entire energy storage system is reflected based on whether the temperature and combustible gas concentration characteristics have reached a set threshold. However, it is impossible to accurately determine at which specific level the fire has occurred. Moreover, when temperature sensors and gas sensors are located at different levels, they are affected by different factors in the surrounding environment. Therefore, only using the data collected by the temperature sensors and gas sensors to determine whether a fire has occurred in the entire energy storage system, the judgment level is unclear, the accuracy is low, the error is large, and timely fire extinguishing cannot be achieved.

[0023] In one embodiment, monitoring temperature and combustible gas concentration is crucial in energy storage systems, particularly battery energy storage systems (such as lithium-ion batteries). This helps improve system safety by preventing fires or explosions caused by issues like excessive temperatures or gas leaks. Therefore, monitoring the safety of battery energy storage systems is crucial. The following steps can be performed to monitor the safety of the energy storage system and provide timely alarms in the event of a fire.

[0024] S101: Collect monitoring data at all levels in the energy storage system.

[0025] In one embodiment, monitoring data is collected at each level of the energy storage system, including temperature and combustible gas concentration. Each level includes the module level and the cluster level. The levels in the energy storage system are divided into the module level, cluster level, and cabin level. Specifically, in the energy storage system, multiple battery module levels constitute a cluster level, and a cabin level contains multiple cluster levels. At the cluster level, multiple temperature sensors are installed to monitor temperature changes within the cluster. Temperature sensors can be distributed at different locations in the cluster to monitor the overall thermal state. Commonly used temperature sensors include thermocouples, thermistors (NTC / PTC), infrared sensors, etc. These sensors are selected based on specific requirements such as accuracy, response speed, and high temperature resistance. The method for collecting combustible gas concentration at the cluster level is similar to the method for monitoring temperature at the cluster level. Typically, the cluster level is equipped with multiple gas sensors, among which the gas sensors are combustible gas sensors that monitor the distribution and concentration of gases. In particular, when multiple modules fail, cluster-level combustible gas concentration sensors can help to promptly detect leaks of toxic or combustible gases.

[0026] S102: De-noising the monitoring data.

[0027] In one embodiment, any level in the energy storage system is used as the target level, and for the target level, the temperature and combustible gas concentration monitored in the target level are denoised. The reason is that the data collected by the temperature and combustible gas concentration sensors are often affected by factors such as the external environment, sensor quality, and installation location. Noise may cause data fluctuations or even false alarms. If the data is not denoised, it may lead to wrong judgments. For example, if there are large noise fluctuations in the temperature data, the system may misjudge whether the temperature is abnormal, and thus fail to respond in time. The noise in the combustible gas concentration data may make it impossible for the system to accurately identify the actual situation of the gas leak, delaying the time to take emergency measures. Through denoising, unnecessary interference can be removed to ensure the accuracy of the data.

[0028] In one embodiment, the temperature and combustible gas concentration are denoised, including: establishing a target window centered on any data point in the temperature or combustible gas concentration, wherein the size of the target window can be 7 or 8, etc., for any data point in the target window, calculating the abnormality of the data point, the abnormality and the difference between the variance of all data points in the target window and the variance of all data points in the target window after removing the data point are positively correlated, and the normalized difference is used as the abnormality of the data point; the size of the filter window is corrected according to the abnormality, and the temperature or combustible gas concentration is filtered using the corrected filter window.

[0029] In one embodiment, the size of the filter window is modified according to the abnormality level, including: multiplying the filter window by the abnormality level, and rounding up the result of the multiplication to obtain a modified filter window.

[0030] S103: Calculate the abnormal value of the target level.

[0031] In one embodiment, based on the denoised temperature and combustible gas concentration at the current moment, an abnormal value of the target level is calculated, and the abnormal value is positively correlated with the temperature and the combustible gas concentration.

[0032] In one embodiment, the outlier value of the target level is calculated using the following formula: Where α represents the outlier value of level Z, W i Indicates the i-th temperature value before the current moment, W′ i represents the i-th temperature value before the historical fire alarm moment, N represents the number of data points before the current moment; Q represents the combustible gas concentration value at the current moment, Q 安 Indicates the safe combustible gas concentration value for target level Z. In other words, if the currently monitored temperature data is close to the temperature monitored during historical fire alarms, the likelihood of a fire occurring at the current moment is high, and the larger the target level abnormal value. The larger the ratio of the current combustible gas concentration value to the safe combustible gas concentration value for the target level, the closer the current combustible gas concentration value is to or greater than the safe combustible gas concentration value for the target level, indicating a higher likelihood of a fire occurring at the current moment, and the larger the target level abnormal value.

[0033] It should be noted that the lowest temperature value at the moment of a fire in the energy storage system's history is used as the historical fire alarm time. For example, if there have been two fires in the energy storage system in the past, the temperature sensor recorded a temperature of W1 during the first fire and a temperature of W2 during the second fire, with W2 being lower than W1. In this case, the temperature and combustible gas concentration at the second fire are compared with the current data.

[0034] S104: Calculate the correction factor of the monitoring data at the current moment.

[0035] In one embodiment, when a fire occurs, due to the high temperature triggering a combustion reaction, the surrounding combustible materials (such as wood, plastic, oil, gas, etc.) will be heated and may undergo pyrolysis or combustion, producing a large amount of combustible gas. These gases enter the air, causing the concentration of combustible gas detected by the gas monitoring equipment to increase sharply. Common combustible gases include methane, ethane, propane, ethylene, carbon monoxide (CO), etc. And when a fire occurs, due to the high temperature triggering a combustion reaction, the surrounding combustible materials will be heated and may undergo pyrolysis or combustion, producing a large amount of combustible gas. These gases enter the air, causing the concentration of combustible gas detected by the gas monitoring equipment to increase sharply. Common combustible gases include methane, ethane, propane, ethylene, carbon monoxide (CO), etc. Therefore, the correction factor can be calculated based on the changing trend of temperature and combustible gas concentration within a preset time period to correct the abnormal value of the target level.

[0036] In one embodiment, calculating the correction factor for the monitoring data at the current moment includes: taking the current moment as a node, obtaining the temperature and combustible gas concentration for a preset time period before the node; and calculating the correction factor for the monitoring data at the current moment, wherein the correction factor is positively correlated with the magnitude of the change in temperature and combustible gas concentration within the preset time period. Specifically, the greater the magnitude of the temperature change within the preset time period, the higher the likelihood of a fire occurring at the current moment, and the greater the degree of correction for the abnormal value of the target level. The greater the magnitude of the combustible gas concentration change within the preset time period, the higher the likelihood of a fire occurring at the current moment, and the greater the degree of correction for the abnormal value of the target level.

[0037] In one embodiment, the correction factor of the monitoring data at the current moment is calculated using the following formula: Where W i Indicates the temperature value at the current time i within the preset time period, W min Indicates the minimum value of all temperature values ​​within the preset time period, W max Indicates the maximum value of all temperature values ​​within the preset time period, Q i Indicates the combustible gas concentration at the current time i within the preset time period, Q min Indicates the minimum value of all combustible gas concentrations within the preset time period, Q maxIndicates the maximum value of all combustible gas concentrations within the preset time period. In other words, the higher the temperature at the current moment within the preset time period, and the greater the difference between the temperature and the minimum temperature collected within the preset time period, the faster the temperature rose within the preset time period. At this time, the possibility of a fire at the target level is also greater, and therefore the degree of correction to the abnormal value of the target level is also greater. Similarly, the higher the combustible gas concentration at the current moment within the preset time period, and the greater the difference between the combustible gas concentration and the minimum combustible gas concentration collected within the preset time period, the faster the combustible gas concentration rose within the preset time period. At this time, the possibility of a fire at the target level is also greater, and therefore the degree of correction to the abnormal value of the target level is also greater.

[0038] S105: Correct the abnormal value to obtain the danger level of the target level.

[0039] In one embodiment, the abnormal value is corrected using the correction factor of the current monitoring data to obtain the target level of danger. Specifically, the abnormal value of the target level is multiplied by the correction factor of the current monitoring data, and the result of the multiplication is used as the target level of danger.

[0040] S106: Determine the fire extinguishing level according to the degree of danger at each level.

[0041] In one embodiment, if the module-level danger level is greater than a first threshold, the fire extinguishing level is low; if the sum of the module-level danger level and the cluster-level danger level is greater than a second threshold, the fire extinguishing level is high; if the cabin-level danger level is greater than a third threshold, the fire extinguishing level is extremely high. If the fire extinguishing level is low, only the module-level fire extinguishing device is activated; if the fire extinguishing level is high, both the module-level and cluster-level fire extinguishing devices are activated; if the fire extinguishing level is extremely high, only the cabin-level fire extinguishing device is activated. In this embodiment, the empirical value of the first threshold is 0.7, the empirical value of the second threshold is 0.8, and the empirical value of the third threshold is 0.85. In other embodiments, the empirical values ​​of the first, second, and third thresholds can be set according to the specific implementation situation. It should be noted that fire extinguishing devices at different levels can be linked through a network or control system to ensure that they can respond quickly and accurately locate the fire source when a fire occurs, thereby minimizing fire losses. In other embodiments, it is also possible to determine which fire extinguishing devices need to be activated based on the danger level of each level.

[0042] For example, when the danger level at a certain module level is greater than the first threshold, the system can activate the local fire extinguishing device (such as a fire extinguisher, sprinkler system, etc.) at the module level, or activate the isolation device to isolate it from other modules or clusters to prevent the spread of fire. When the sum of the danger level at the module level and the danger level at the cluster level is greater than the second threshold, the cluster-level fire extinguishing device and the module-level local fire extinguishing device will be automatically activated. Gas fire extinguishing, foam fire extinguishing, etc. can be used. At the same time, the cooling system may be activated to reduce the temperature. For example, a liquid cooling system or an air cooling system can be activated to reduce the temperature around the fire source and slow down the spread of the fire. When the fire extinguishing level is extremely high, the cabin-level fire extinguishing device will be activated, and a gas fire extinguishing system (such as carbon dioxide, aerosol fire extinguishing, etc.) or a foam fire extinguishing system is usually used to extinguish the fire to achieve multi-stage linkage fire extinguishing.

[0043] Through these steps, the linkage mechanism ensures accurate and rapid fire suppression responses to fire risks at varying levels through data collection, intelligent decision-making, and automated control. Through sensor networks, intelligent algorithms, device linkage, and remote monitoring, the energy storage system can minimize fire losses and improve safety.

[0044] The present invention also provides a multi-stage linkage fire extinguishing system for an energy storage system. The system includes a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, the multi-stage linkage fire extinguishing method for an energy storage system according to the first aspect of the present invention is implemented.

[0045] In one embodiment, the present invention provides a computer device. The computer device includes a processor, memory, a communication interface, a display screen, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities and may be a CPU, single-chip microcomputer, DSP, or FPGA. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. When the computer program is executed, the steps described in the above method embodiment, such as steps S101 to S106, can be completed. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal via wired or wireless communication, where the wireless communication may be achieved via Wi-Fi, a carrier network, NFC (near-field communication), or other technologies. When the computer program is executed by the processor, a multi-stage linkage fire extinguishing method for an energy storage system is implemented. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen. The input device of the computer device may be a touch screen covering the display screen, or may be a key, trackball, or touchpad provided on the computer device housing, or may be an external keyboard, touchpad, or mouse.

[0046] The system further includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and thus will not be described in detail here.

[0047] In the present invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, the computer-readable storage medium can be any suitable magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible or connectable to a device. Any application or module described in the present invention can be implemented using computer-readable / executable instructions that can be stored or otherwise retained by such a computer-readable medium.

[0048] In the description of this specification, "multiple" and "several" mean at least two, such as two, three or more, etc., unless otherwise clearly defined.

[0049] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0050] The above-described embodiments merely represent several implementation methods of the present invention. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that a person skilled in the art would be able to make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the patent for this invention shall be determined by the appended claims.

Claims

1. A multi-stage linkage fire extinguishing method for an energy storage system, characterized in that: include: Collect monitoring data from all levels of the energy storage system, including temperature and combustible gas concentration, at both the module and cluster levels; For the target level, the monitoring data is denoised, and based on the denoised monitoring data at the current moment, an abnormal value of the target level is calculated, wherein the abnormal value is positively correlated with the temperature and the combustible gas concentration; Correcting the abnormal value using the correction factor of the current monitoring data to obtain the target level of danger, wherein the correction factor reflects the changing trend of the temperature and combustible gas concentration within a preset time period; The fire extinguishing level is determined according to the degree of danger at each level, and linked fire extinguishing is initiated according to the fire extinguishing level.

2. The multi-stage linkage fire extinguishing method for an energy storage system according to claim 1, characterized in that: Calculate the risk level of the target level, including: The abnormal value of the target level is multiplied by the correction factor of the monitoring data at the current moment, and the value of the product after normalization is used as the danger level of the target level.

3. The multi-stage linkage fire extinguishing method for an energy storage system according to claim 2, characterized in that: Calculate the outlier value of the target level using the following formula: Where α represents the outlier value of the target level Z, W i Indicates the i-th temperature value before the current moment, W ′i represents the i-th temperature value before the historical fire alarm moment, N represents the number of data points before the current moment; Q represents the combustible gas concentration value at the current moment, Q 安 Indicates the safe combustible gas concentration value for target level Z.

4. The multi-stage linkage fire extinguishing method for an energy storage system according to claim 3, characterized in that: Calculate the correction factor of the monitoring data at the current moment, including: Taking the current moment as a node, obtaining the temperature and combustible gas concentration for a preset time period before the node; A correction factor of the monitoring data at the current moment is calculated, and the correction factor is positively correlated with the variation range of the temperature and the combustible gas concentration within a preset time period.

5. The multi-stage linkage fire extinguishing method for an energy storage system according to claim 1, characterized in that: De-noising the temperature and the combustible gas concentration includes: A target window is established with any temperature data point as the center. For any data point in the target window, the abnormality of the data point is calculated. The abnormality is positively correlated with the difference between the variance of all data points in the target window and the variance of all data points in the target window after removing the data point. The size of the filter window is modified according to the abnormality degree, and the data is filtered using the modified filter window.

6. The multi-stage linkage fire extinguishing method for an energy storage system according to claim 1, characterized in that: The fire extinguishing level is determined according to the degree of danger of the target level, including: In response to the module-level danger level being greater than a first threshold, the fire extinguishing level is set to a low level; In response to the sum of the module-level danger level and the cluster-level danger level being greater than a second threshold, the fire extinguishing level is a high level.

7. The multi-stage linkage fire extinguishing method for an energy storage system according to claim 1, characterized in that: Initiate linked fire extinguishing for the fire extinguishing level, including: In response to the fire extinguishing level being a low level, only the module-level fire extinguishing device is activated; In response to the fire extinguishing level being a high level, both the module-level and cluster-level fire extinguishing devices are activated.

8. The multi-stage linkage fire extinguishing method for an energy storage system according to claim 6, characterized in that: The empirical value of the first threshold is 0.7, and the empirical value of the second threshold is 0.

8.

9. The multi-stage linkage fire extinguishing method for an energy storage system according to claim 6, characterized in that: Each tier also includes cabin class.

10. A multi-stage linkage fire extinguishing system for an energy storage system, comprising a processor and a memory, wherein the memory stores a computer program, characterized in that: The processor executes the computer program to implement the multi-stage linkage fire extinguishing method for an energy storage system as described in any one of claims 1 to 9.

Images