An automated energy storage cabinet fire safety system

Abstract

The present disclosure provides an automated energy storage cabinet fire safety system, which relates to the field of energy storage cabinet fire safety. Among them, the system includes: a collection module, a processing module, a warning module, and an execution module. The collection module collects target data of multiple monitoring points in the energy storage cabinet in real time; the processing module analyzes the target data set based on the density clustering algorithm, combines the three-dimensional space model, physical structure information, and electrical connection relationship information of the energy storage cabinet to determine the first target area and extract target features; the warning module generates multi-level warning information based on the target features; the execution module triggers the cooling system, local fire protection system, or full-cabinet fire protection system according to the warning level and sends an emergency alarm. By dynamically adjusting the clustering parameters, combining multi-dimensional data analysis and the internal environment constraints of the energy storage cabinet, the present invention accurately identifies abnormal areas, generates warning information, and optimizes fire protection measures, significantly improving the safety, reliability, and resource utilization efficiency of the operation of the energy storage cabinet.

Description

Technical Field

[0001] The present disclosure relates to the field of fire safety for energy storage cabinets, and more particularly, to an automated energy storage cabinet fire safety system. Background Art

[0002] With the rapid development of energy storage technology, energy storage devices are widely used in power systems to regulate peak and valley loads and improve energy utilization efficiency. However, during operation, energy storage devices are often accompanied by high temperatures, smoke, and other potential risks. In particular, the thermal runaway problem of lithium batteries is an important challenge in the current safety management of energy storage devices.

[0003] For example, Chinese Patent Application No. CN118230486A discloses an electro-chemical energy storage intelligent fire protection system and method. Through a cloud monitoring platform combined with a communication protocol, this system can achieve real-time monitoring, alarming, and remote control of each component in the electro-chemical energy storage device, and at the same time support threshold setting and alarm data reporting.

[0004] The above methods have the problems raised in this background art. Existing technologies lack flexibility and accuracy in identifying abnormal areas within energy storage devices and cannot dynamically adjust the identification range to adapt to the complex physical and electrical environments inside energy storage systems. Secondly, the abnormal detection and early warning mechanisms are single, usually based on simple fixed-threshold monitoring, and do not fully utilize multi-dimensional data (such as temperature, smoke concentration, distribution density, etc.) within the energy storage system for comprehensive analysis. In addition, the fire protection treatment measures lack in-depth integration with the actual physical and electrical layout of the energy storage device, which easily leads to waste of resources or insufficient treatment effects. Summary of the Invention

[0005] In view of the deficiencies of the prior art, the present application discloses an automated energy storage cabinet fire safety system, which includes:

[0006] A collection module for real-time collecting target data at preset monitoring points of the energy storage cabinet to generate a target data set;

[0007] A processing module for, after screening the data in the target data set based on a temperature threshold and / or a smoke threshold and a time threshold, performing clustering analysis on the target data set based on the density clustering method to determine a first target area of the energy storage cabinet, and extracting target features from the first target area;

[0008] Wherein, the density clustering method includes: expanding the initial clustering range based on the spatial coordinates, the physical area and components to which each target data point in the initial clustering range belongs, and spatial constraint conditions; and dynamically adjusting the minimum point number threshold and the neighborhood distance threshold in the density clustering method based on the abnormality degree index of the target data point.

[0009] An early warning module, based on a preset early warning mechanism, matches corresponding early warning information for the target feature;

[0010] An execution module, configured to perform fire protection processing corresponding to the early warning information in the first target area based on the early warning information.

[0011] As an alternative implementation, the acquisition module further includes:

[0012] A sensor network, configured to collect the target data of each preset monitoring point in the energy storage cabinet in real time; wherein, the sensor network includes at least one sensor;

[0013] A preprocessing unit, configured to perform data screening on the target data of each preset monitoring point in the energy storage cabinet based on a temperature threshold and / or a smoke threshold and a time threshold in the target data set, and then preprocess the target data to generate the target data set.

[0014] As an alternative implementation, the density clustering method includes:

[0015] Setting a minimum number of points threshold and a neighborhood distance threshold, wherein the minimum number of points threshold is used to define the number of target data required to form a cluster; the neighborhood distance threshold is used to define the maximum distance between target data points to determine the neighborhood range; the neighborhood range is an area centered on each target data and with a radius equal to the neighborhood distance threshold;

[0016] Based on the neighborhood range, determining the core data in the target data set, where the core data is the target data whose number of target data within its neighborhood range is greater than or equal to the minimum number of points threshold;

[0017] Based on the neighborhood range of the core data, determining an initial cluster, and classifying all target data within the neighborhood range of the core data into the initial cluster;

[0018] Wherein, the target data set includes multiple target data points.

[0019] As an alternative implementation, the density clustering method further includes:

[0020] Under the condition of meeting the preset spatial constraint conditions, incorporating the boundary data within the neighborhood range of the core data into the cluster;

[0021] For the newly incorporated boundary data, if it meets the core data conditions and conforms to the spatial constraints, continue to expand the target data within its neighborhood range;

[0022] Iteratively expand the cluster until no new target data is incorporated into the cluster range.

[0023] As an alternative implementation, data screening based on temperature thresholds and / or smoke thresholds and time thresholds in the target data set includes:

[0024] Set a time threshold;

[0025] Screen the target data set based on the time threshold, including:

[0026] Determine whether the target data point is greater than the temperature threshold and / or smoke threshold and continues to exceed the time threshold;

[0027] In response to the target data point being greater than the temperature threshold and / or smoke threshold but not exceeding the time threshold, exclude it from the target data set.

[0028] As an alternative implementation, setting the minimum number of points threshold and neighborhood distance threshold includes:

[0029] Dynamically adjust the minimum number of points threshold and the neighborhood distance threshold based on the abnormality degree index of the target data point;

[0030] Among them, the determination of the abnormality degree index includes:

[0031] Quantify the difference between the temperature value of the target data point and the temperature threshold to obtain a temperature overlimit measure;

[0032] Monitor the change rate of the smoke concentration of the target data point and determine the smoke concentration change gradient of the target data point;

[0033] Input the temperature overlimit measure and the smoke concentration change gradient into a preset abnormality degree evaluation model to output the corresponding abnormality degree index;

[0034] The dynamic adjustment of the minimum number of points threshold and the neighborhood distance threshold includes:

[0035] When the abnormality degree index is greater than or equal to a preset abnormality degree index threshold, increase the neighborhood distance threshold and decrease the minimum number of points threshold to expand the clustering range;

[0036] When the abnormality degree index is less than the preset abnormality degree index threshold, decrease the neighborhood distance threshold and increase the minimum number of points threshold to narrow the clustering range.

[0037] As an alternative implementation, determining the first target area of the energy storage cabinet based on the clustering result includes: determining the spatial range of the first target area based on the core data and boundary data in the target data set;

[0038] Extracting target features from the first target area includes:

[0039] Extract the highest temperature value of the target data;

[0040] Extract the rate of change of the smoke concentration of the target data;

[0041] Extract the spatial distribution density of the target data;

[0042] Extract the proportion of the number of abnormal points in the target data.

[0043] As an optional implementation manner, the density clustering method further includes:

[0044] Based on the three-dimensional space model of the energy storage cabinet, determine the spatial coordinates of each target data point;

[0045] Based on the spatial coordinates of the target data points, determine the physical regions and components to which each target data point belongs;

[0046] Based on the physical structure information and electrical connection relationship information of the energy storage cabinet, determine the spatial constraint conditions;

[0047] Based on the spatial coordinates, the physical regions and components to which the target data points in the initial clustering range belong, and the spatial constraint conditions, expand the initial clustering range, including:

[0048] For the target data points to be expanded that are not within the initial clustering range, determine whether the following conditions are simultaneously satisfied:

[0049] The physical region to which the target data point to be expanded belongs is directly adjacent in structure to the physical region to which at least one target data point within the current clustering range belongs, and there is no physical partition between them;

[0050] The component to which the target data point to be expanded belongs is directly electrically connected to the component to which at least one target data point within the current clustering range belongs;

[0051] If the above conditions are all satisfied, include the target data point to be expanded in the clustering range.

[0052] As an optional implementation manner, the matching of the corresponding warning information for the target feature based on a preset warning mechanism includes:

[0053] Based on the target feature, classify the first target area into different warning levels; wherein, the warning levels include: first-level warning, second-level warning, and third-level warning;

[0054] Based on the warning level, generate the warning information corresponding to this warning level.

[0055] Performing fire handling corresponding to the warning information in the first target area based on the warning information includes:

[0056] In response to the warning level being the first-level warning, triggering the cooling system in the energy storage cabinet to reduce the temperature in the first target area;

[0057] In response to the warning level being the second-level warning, triggering the local fire-fighting system of the energy storage cabinet to spray fire extinguishing medium towards the first target area;

[0058] In response to the warning level being the third-level warning, triggering the full-cabinet fire-fighting system of the energy storage cabinet, simultaneously spraying fire extinguishing medium towards the first target area, and sending out an emergency alarm signal to notify the external control center.

[0059] Compared with the prior art, the beneficial effects of the present invention are as follows: By combining the comprehensive application of multi-dimensional data analysis, dynamic clustering algorithm, and the physical and electrical constraints of the energy storage cabinet, the intelligent and precise level of fire safety management of the energy storage cabinet is significantly improved. Specifically, the present invention introduces a dynamic adjustment mechanism based on density clustering in the process of abnormal area identification, which can flexibly adjust the clustering parameters according to the abnormal degree index of the target data points, enabling the system to accurately locate potential abnormal areas in the complex energy storage cabinet environment and trigger alarms in a timely manner. In addition, by combining the three-dimensional space model, physical structure information, and electrical connection relationship information of the energy storage cabinet, the present invention effectively overcomes the identification errors caused by simple threshold monitoring and fixed range limitations in traditional methods, ensuring that the determination of abnormal areas is more scientific and reasonable. Brief Description of the Drawings

[0060] Figure 1 A schematic diagram of an automated energy storage cabinet fire safety system provided by an embodiment of the present disclosure;

[0061] Figure 2 A schematic diagram of a collection module provided by an embodiment of the present disclosure;

[0062] Figure 3 A three-dimensional structure schematic diagram of an energy storage cabinet provided by an embodiment of the present disclosure;

[0063] Figure 4 A schematic diagram of the front structure inside the cabinet provided by an embodiment of the present disclosure;

[0064] Figure 5 A schematic diagram of the back structure inside the cabinet provided by an embodiment of the present disclosure.

[0065] Reference numerals: 100, acquisition module; 200, processing module; 300, warning module; 400, execution module; 110, sensor network; 120, preprocessing unit; 1, water pump; 2, fire water inlet pipe; 3, refrigerant tank; 4, main water inlet pipe; 5, refrigerant tank inlet; 6, main water return pipe; 7, battery PACK box; 8, water return branch pipe; 9, water return sub-branch pipe; 10, water inlet branch pipe; 11, water inlet sub-branch pipe; 12, fire check valve; 13, fire spray pipe; 14, fire sprinkler head. Detailed implementation manners

[0066] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments.

[0067] See Figure 1 As shown in the figure, it is a schematic diagram of an automated energy storage cabinet fire safety system provided by an embodiment of the present disclosure. The present invention provides an automated energy storage cabinet fire safety system, which realizes efficient management of the fire safety of the energy storage cabinet through modular design. The system includes an acquisition module 100, a processing module 200, a warning module 300, and an execution module 400. The modules cooperate with each other, can monitor the operation status of the energy storage cabinet in real time, analyze potential risks, and take timely fire treatment measures.

[0068] Among them:

[0069] The acquisition module 100 is used to collect target data of the energy storage cabinet at preset monitoring points in real time and generate a target data set;

[0070] The processing module 200 is used to perform data screening on the target data set based on a temperature threshold and / or a smoke threshold and a time threshold, and then perform clustering analysis on the target data set based on the density clustering method to determine the first target area of the energy storage cabinet and extract target features from the first target area; wherein, the density clustering method includes: expanding the initial clustering range based on the spatial coordinates, the physical area and components to which each target data point belongs, and the spatial constraint conditions in the initial clustering range; and dynamically adjusting the minimum point number threshold and the neighborhood distance threshold in the density clustering method based on the abnormality degree index of the target data point.

[0071] The warning module 300 matches corresponding warning information for the target features based on a preset warning mechanism;

[0072] The execution module 400 is used to perform fire treatment corresponding to the warning information in the first target area based on the warning information.

[0073] In the present disclosure, an energy storage cabinet refers to a device for storing electrical energy, which includes battery units, control circuits, cooling systems, etc. inside. During its operation, abnormal situations such as temperature rise and smoke generation may occur, and real-time monitoring and safety management are required.

[0074] Target data refers to the monitoring data related to the operation status of the energy storage cabinet obtained by the acquisition module 100, including but not limited to parameters such as temperature, smoke concentration, voltage, and current.

[0075] The target data set refers to the set of target data at multiple preset monitoring points, which is used for subsequent analysis by the processing module 200.

[0076] The first target area refers to the internal space range of the energy storage cabinet determined by the processing module 200 through clustering analysis of the target data set, where abnormalities may exist or key attention is required.

[0077] Target features refer to specific data features extracted by the processing module 200 from the first target area, including but not limited to the highest temperature value, the rate of change of smoke concentration, spatial distribution density, etc., which are used for subsequent early warning and fire protection processing.

[0078] Early warning information refers to the warning information generated based on the target features, which identifies the abnormal risk level and the specific location, and is used to guide the execution module 400 to take corresponding measures.

[0079] In the present invention, the acquisition module 100 deploys a variety of sensors to comprehensively acquire the target data at each preset monitoring point of the energy storage cabinet, forming a target data set, which provides a data basis for subsequent risk analysis. The processing module 200 performs intelligent clustering analysis on the target data set to determine the first target area. This analysis process can dynamically identify abnormal areas and avoid misjudgment caused by simple threshold monitoring. The early warning module 300 generates early warning information of different levels based on the extracted target features, guiding the execution module 400 to accurately perform fire protection processing within the corresponding first target area, and avoiding unnecessary resource consumption caused by triggering the entire cabinet.

[0080] In a specific implementation, the acquisition module 100 deploys a sensor network 110 at multiple preset monitoring points inside the energy storage cabinet to acquire the target data of the energy storage cabinet. The target data includes but not limited to operation parameters such as temperature, smoke concentration, voltage, and current. Each monitoring point corresponds to at least one sensor. For example, temperature sensors and smoke sensors deployed near the battery units are used to sense the changes in the operation status in real time. The sensor network 110 transmits the acquired data to the processing module 200 through wired or wireless means.

[0081] The function of the processing module 200 is to perform clustering analysis on the target data set provided by the acquisition module 100 and determine the first target area. The clustering analysis uses intelligent algorithms (such as density clustering algorithms) that can accurately locate areas that may pose risks in terms of data characteristics. The first target area can be represented as one or more areas in the three-dimensional space of the energy storage cabinet. For example, if the temperatures of two groups of battery units in a certain energy storage cabinet are found to have abnormally increased, then these two groups of battery units can be marked as the first target area.

[0082] It should be noted that the first target area is only an initially or preferentially discovered abnormal area; if new data is detected that meets the clustering conditions, second and third target areas will be generated.

[0083] The warning module 300 stores a multi-level warning mechanism. This module matches target features (such as the maximum temperature value, the rate of change of smoke concentration, etc.) with preset rules to generate corresponding warning information. For example, when the temperature in a certain area exceeds the safety threshold and the smoke concentration rises rapidly, the system will generate a second-level or third-level warning message to remind the execution module 400 to take more stringent fire protection measures.

[0084] The execution module 400 takes precise fire protection treatment measures according to the warning information generated by the warning module 300. For example, when a first-level warning is generated, only the cooling system is triggered to cool down the first target area; while when a third-level warning is generated, the full-cabinet fire protection system is triggered, including starting the injection of fire extinguishing medium and sending out an emergency alarm to notify the external control center.

[0085] In a specific implementation, the processing module 200 performs data screening in the target data set based on a temperature threshold and / or a smoke threshold and a time threshold, including:

[0086] Set the temperature threshold and the smoke threshold;

[0087] Screen the target data set based on the temperature threshold and / or the smoke threshold.

[0088] As an alternative implementation, screening the target data set based on the temperature threshold and / or the smoke threshold further includes:

[0089] Set the time threshold;

[0090] Screening the target data set based on the time threshold includes:

[0091] Determine whether the target data point is greater than the temperature threshold and / or the smoke threshold and lasts for more than the time threshold;

[0092] In response to the target data point being greater than the temperature threshold and / or the smoke threshold but not exceeding the time threshold, exclude it from the target data set.

[0093] In the operation status monitoring of the energy storage cabinet, the collected target data set may contain a large amount of redundant or noisy data. These data not only increase the computational complexity of subsequent analysis but also may interfere with the positioning accuracy of abnormal areas. For example, due to sensor errors or short-term fluctuations, some target data points may temporarily exceed the threshold, but this does not represent a real anomaly.

[0094] The present invention significantly improves the quality of the target data set by adding a screening process based on temperature threshold and smoke threshold before determining the core data, initially filtering out obviously irrelevant data points. At the same time, a time threshold screening is introduced to address the problem of anomaly persistence, further ensuring that target data points are regarded as anomalies only when they meet the persistence condition. This dual screening mechanism effectively solves the misjudgment problem caused by short-term fluctuations and provides more accurate data input for subsequent density clustering analysis.

[0095] In a specific implementation, before density clustering analysis, the target data set is screened by temperature threshold, smoke threshold, and time threshold. Among them, the temperature threshold can be set according to the safe operation requirements inside the energy storage cabinet. For example, according to the heat resistance performance of battery cells and electrical equipment in different regions, the temperature threshold range can be set from 50°C to 70°C; the smoke threshold is set according to the possible smoke concentration range inside the energy storage cabinet. For example, referring to the reference value of the smoke sensor in the normal operation environment of the energy storage cabinet, the smoke threshold range can be set from 20 ppm to 50 ppm.

[0096] In a specific implementation, for each target data point in the target data set generated by the acquisition module 100, it is determined one by one whether it exceeds the temperature threshold and / or the smoke threshold:

[0097] For example, if the temperature value of a target data point exceeds the temperature threshold, or its smoke concentration value exceeds the smoke threshold, it can be marked as a data point "to be further screened";

[0098] If the temperature value and the smoke concentration value of a target data point do not exceed the corresponding thresholds, it is directly excluded from the target data set.

[0099] In addition, the time threshold is used to determine whether the abnormal state of the target data point is persistent. For example, the time threshold can be set to 5 seconds, indicating that the abnormal state of the target data point needs to last for more than 5 seconds to be regarded as a valid anomaly. For the data points marked as "to be further screened", analyze the duration of their exceeding the temperature threshold or the smoke threshold:

[0100] If the abnormal state (such as the temperature or smoke concentration value exceeding the threshold) of the target data point lasts for more than the time threshold, retain this data point;

[0101] If the abnormal state of the target data point does not persist for more than the time threshold, it is excluded from the target data set.

[0102] Through the above screening steps, the processing module 200 finally generates an optimized target data set for subsequent density clustering analysis.

[0103] In this way, the present invention effectively filters out irrelevant or short-term fluctuating target data points by adding a dual screening mechanism based on temperature threshold, smoke threshold and time threshold before density clustering analysis, significantly improving the quality of the target data set and the accuracy of subsequent clustering analysis. The temperature threshold and smoke threshold are flexibly adjusted according to the actual operating environment of the energy storage cabinet, and the introduction of the time threshold further ensures the reliability of abnormal data, thereby reducing the misjudgment rate and computational complexity, and providing more accurate basic support for the fire safety management of the energy storage cabinet.

[0104] It should be noted that since the target data includes but is not limited to parameters such as temperature, smoke concentration, voltage, and current, in addition to temperature and smoke, parameters such as voltage and current can also be used for screening abnormal data.

[0105] Exemplarily, an energy storage station consists of multiple energy storage cabinets, and multiple temperature sensors and smoke sensors are installed inside each energy storage cabinet. The acquisition module 100 acquires data in real time. The processing module 200 discovers that the temperatures in two areas of an energy storage cabinet have risen abnormally (65°C and 70°C respectively), but the smoke concentration has not yet reached the alarm threshold. The early warning module 300 generates a first-level early warning message, and the system triggers the cooling system to cool the abnormal area. Subsequently, if the smoke concentration continues to rise, the system automatically upgrades to a second-level early warning and triggers the local fire extinguishing system to spray fire extinguishing medium on the abnormal area. Through precise monitoring and processing, the risk is controlled in time to avoid the occurrence of fire.

[0106] In this way, through modular design, functions such as multi-point real-time acquisition, clustering analysis and area positioning, hierarchical early warning, and precise fire protection processing are integrated, which can quickly respond to abnormal changes in the energy storage cabinet, effectively cover the operating status of the entire energy storage cabinet, and realize the full-process automatic management from monitoring to processing. Compared with the traditional single-point monitoring and full-cabinet trigger-type fire protection system, the present invention significantly improves the response speed and abnormal positioning accuracy, while greatly reducing resource consumption and equipment loss, and improving the operating safety and system intelligence level of the energy storage cabinet.

[0107] See Figure 2 As shown in the figure, it is a schematic diagram of an acquisition module 100 provided by an embodiment of the present disclosure. As an optional implementation manner, the acquisition module 100 further includes:

[0108] A sensor network 110 for collecting the target data of each preset monitoring point in the energy storage cabinet in real time; wherein, the sensor network 110 includes at least one sensor;

[0109] A preprocessing unit 120 for preprocessing the target data of each preset monitoring point in the energy storage cabinet to generate the target data set.

[0110] The present disclosure proposes an improved design of the acquisition module 100, adding two core functions of the sensor network 110 and the preprocessing unit 120. The sensor network 110 realizes the full-coverage acquisition of multiple monitoring points in the energy storage cabinet, ensuring the comprehensiveness of monitoring and the integrity of data; the preprocessing unit 120 then performs preliminary cleaning and optimization on the acquired target data, providing data input that meets expectations for the clustering analysis of the subsequent processing module 200.

[0111] In a specific implementation, the sensor network 110 is composed of various types of sensors deployed at different positions inside the energy storage cabinet. Specifically, the sensors include but are not limited to temperature sensors, smoke sensors, current sensors, voltage sensors, etc. These sensors can be connected to the preprocessing unit 120 in a wired manner (such as CAN bus) or a wireless manner (such as ZigBee protocol), and transmit the target data in real time according to the set sampling period. For example, temperature sensors and smoke sensors are arranged near the battery unit of the energy storage cabinet to monitor temperature changes and abnormal smoke concentrations in real time, while current sensors and voltage sensors are arranged at the cable connection to monitor current overload and voltage fluctuations.

[0112] It can be understood that in some cases, the data of the energy storage cabinet can also be collected by external sensors. In this implementation manner, for example, only one infrared sensor can also obtain the temperature data on the surface and / or inside of the entire energy storage cabinet. At this time, it can also be linked with the processing module 200, the warning module 300, and the execution module 400 to implement the present disclosure. Therefore, in the sensor network 110, at least one sensor can be included.

[0113] In a specific implementation, the role of the preprocessing unit 120 is to perform preliminary processing on the target data transmitted by the sensor network 110 to improve the data quality and usability. Specifically, the functions of the preprocessing unit 120 can include: data cleaning, data denoising, data formatting, and data integration.

[0114] Exemplarily, the preprocessing unit 120 may remove invalid data points in the target data, such as abnormal readings caused by sensor failures; the preprocessing unit 120 may smooth the target data using a filtering algorithm (such as low-pass filtering) to reduce noise introduced by external interference; the preprocessing unit 120 may uniformly convert the target data into a preset format for subsequent parsing and analysis by the processing module 200; the preprocessing unit 120 may classify and integrate the target data from different monitoring points according to the spatial distribution of the energy storage cabinets to generate a target data set.

[0115] Exemplarily, in the actual application of an energy storage station, the sensor network 110 of the acquisition module 100 includes the following configuration: 20 sensors (16 temperature sensors and 4 smoke sensors) are arranged in each energy storage cabinet, distributed near the battery unit, bus connection, and ventilation opening. The sensors are connected to the preprocessing unit 120 through the CAN bus. The target data is collected once per second and transmitted to the preprocessing unit 120 in real time. The preprocessing unit 120 performs noise reduction processing on the target data transmitted by the sensor network 110. For example, the short-term fluctuations of the temperature sensors are eliminated through the Kalman filtering algorithm, and then the cleaned data is integrated into a target data set, including the temperature values, smoke concentration values, and their corresponding time and spatial position information of each monitoring point.

[0116] In this way, by introducing the sensor network 110 and the preprocessing unit 120 in the acquisition module 100, the present invention not only realizes the comprehensive monitoring of multiple points in the energy storage cabinet, but also significantly improves the data quality through preprocessing technologies such as data cleaning and noise reduction, avoiding misjudgment or missed reports caused by monitoring blind spots or data noise. The target data set generated by the acquisition module 100 provides reliable data support for the subsequent processing module 200, enabling the overall system to have higher accuracy and response capabilities, thereby effectively improving the real-time performance and reliability of the fire safety management of the energy storage cabinet.

[0117] In a specific implementation, the density clustering method includes:

[0118] Setting a minimum point number threshold and a neighborhood distance threshold, where the minimum point number threshold is used to limit the number of target data required to form a cluster; the neighborhood distance threshold is used to limit the maximum distance between target data points to determine the neighborhood range; the neighborhood range is an area centered on each target data with a radius equal to the neighborhood distance threshold;

[0119] Based on the neighborhood range, determining the core data in the target data set, where the core data is the target data whose number of target data within its neighborhood range is greater than or equal to the minimum point number threshold;

[0120] Based on the neighborhood range of the core data, determine the initial clustering, and assign all target data within the neighborhood range of the core data to the initial clustering.

[0121] The present invention introduces a density clustering method (such as the DBSCAN algorithm) in the processing module 200. By comprehensively analyzing the target data set, it accurately identifies areas that may be abnormal. The density clustering method defines the relevance of target data by setting a minimum number of points threshold and a neighborhood distance threshold, can dynamically discover abnormal areas, avoids misjudgments caused by simple threshold monitoring, and improves the positioning accuracy of multi-point linkage anomalies.

[0122] The core of the density clustering method is to use the neighborhood range to determine the core data points and their associated points, and expand the clustering range through the core data points. By adopting this method, the present invention realizes efficient positioning of abnormal areas in the energy storage cabinet, providing accurate input for subsequent early warning and fire protection processing.

[0123] In a specific implementation, the processing module 200 first sets the key parameters of clustering: the minimum number of points threshold (MinPts) and the neighborhood distance threshold (Eps).

[0124] The minimum number of points threshold is used to limit the number of target data points required to form a clustering. The specific value setting can be based on the following factors:

[0125] The distribution characteristics of the target data: for example, the average number of target data points in a certain area;

[0126] The scale definition of the abnormal area: such as containing at least a certain number of sensors or data points.

[0127] The neighborhood distance threshold is used to limit the maximum distance between target data points to determine the neighborhood range of the target data points. The specific value setting can be based on the following factors:

[0128] The physical layout inside the energy storage cabinet: for example, the average spacing or arrangement density between sensors;

[0129] The spatial range monitored by the sensor: such as the effective sensing radius of the temperature sensor (unit: meter or millimeter).

[0130] For each data point in the target data set, the processing module 200 calculates its neighborhood range according to the neighborhood distance threshold (Eps). If the number of target data within the neighborhood range of a data point is greater than or equal to the minimum number of points threshold (MinPts), then this data point is determined as a core data point. The core data point is the key to clustering and represents an area with a high density of target data.

[0131] The processing module 200 classifies each core data point and all target data points within its neighborhood range into an initial cluster. If there are other core data points within the neighborhood range of a certain core data point, it will continue to expand and merge these core data points and the target data points within their neighborhood ranges to form a larger cluster.

[0132] Exemplarily, during the actual operation of a certain energy storage cabinet, the acquisition module 100 transmitted data of 20 monitoring points, including temperature data (unit: °C) and smoke concentration data (unit: ppm). The processing module 200 analyzes these target data using the density clustering method, and the specific steps are as follows:

[0133] Neighborhood distance threshold (Eps): Set to 0.5 meters, based on the average spacing (0.5 meters) of the internal sensors of the energy storage cabinet;

[0134] Minimum number of points threshold (MinPts): Set to 4, based on the definition that at least 4 target data points in a certain area can characterize it as an abnormal area.

[0135] Calculate the neighborhood range for each data point in the target data set. For example:

[0136] The neighborhood range of data point A (temperature is 60 °C, smoke concentration is 15 ppm) includes 5 target data points, and the neighborhood distances are all less than 0.5 meters;

[0137] The neighborhood range of data point B (temperature is 45 °C, smoke concentration is 5 ppm) only contains 2 target data points.

[0138] Data point A is determined to be a core data point because the number of target data points (5) within its neighborhood range is greater than or equal to the minimum number of points threshold (4);

[0139] Data point B is not determined to be a core data point because the number of target data points (2) within its neighborhood range is less than the minimum number of points threshold (4).

[0140] All data points (including itself) within the neighborhood range of data point A are classified into the initial cluster. If other data points within the neighborhood range (such as data point C) are also core data points, it will continue to expand and merge all data points within the neighborhood range of C into this cluster.

[0141] Finally, the processing module 200 identifies a certain area inside the energy storage cabinet as an abnormal area and marks it as the first target area for subsequent use by the warning module 300 and the execution module 400.

[0142] In this way, by analyzing the target data set through the density clustering method, the present invention can adaptively discover the abnormal areas in the energy storage cabinet, overcoming the problems of misjudgment and missed judgment in traditional single-point threshold monitoring. The density clustering method has high flexibility in parameter setting. For example, the neighborhood distance threshold can be adjusted according to the arrangement density of sensors and the physical perception range, and the minimum number of points threshold can be defined according to the distribution characteristics of the target data to determine the scale of the abnormal area.

[0143] In addition, the clustering analysis method of the present invention does not require presetting the number or shape of abnormal areas, has strong adaptability and high accuracy, provides reliable data support for subsequent early warning and fire protection processing, and significantly improves the efficiency and accuracy of the fire safety management of the energy storage cabinet.

[0144] As an optional implementation manner, the above density clustering method further includes:

[0145] Under the condition of meeting the preset spatial constraint conditions, incorporating the boundary data within the neighborhood range of the core data into the clustering;

[0146] For the newly incorporated boundary data, if it meets the core data conditions and conforms to the spatial constraints, continue to expand the target data within its neighborhood range;

[0147] Iteratively expand the clustering until no new target data is incorporated into the clustering range.

[0148] As an optional implementation manner, expanding the initial clustering range includes:

[0149] Based on the three-dimensional space model of the energy storage cabinet, determining the spatial coordinates of each target data point;

[0150] Based on the spatial coordinates of the target data points, determining the physical regions and components to which each target data point belongs;

[0151] Based on the physical structure information and electrical connection relationship information of the energy storage cabinet, determining the spatial constraint conditions;

[0152] Based on the spatial coordinates, the physical regions and components to which each target data point in the initial clustering range belongs, and the spatial constraint conditions, expanding the initial clustering range, including:

[0153] Judging whether the following conditions are simultaneously met for the target data points to be expanded that are not within the initial clustering range:

[0154] The physical region to which the target data point to be expanded belongs is directly adjacent in structure to the physical region to which at least one target data point within the current clustering range belongs, and there is no physical partition between the two;

[0155] The component to which the target data point to be expanded belongs is electrically directly connected to the component to which at least one target data point within the current clustering range belongs;

[0156] If the above conditions are all met, the target data point to be expanded is included in the clustering range.

[0157] Among them, in the complex physical environment of the energy storage cabinet, the determination of the abnormal area is not only affected by the distribution density of the target data points, but also needs to consider the physical space layout and component relevance. For example, due to the existence of physical structure constraints such as fire partitions and electrical isolation inside the energy storage cabinet, the neighborhood relationship between target data points may be restricted, and the traditional density clustering method is difficult to adapt to such a complex scenario. In addition, the relevance between components such as battery units and cables in the energy storage cabinet also plays an important role in determining whether target data points belong to the same area.

[0158] The present invention introduces spatial constraint conditions on the basis of the density clustering method, and precisely restricts the expansion process of the clustering range by combining the three-dimensional space model, physical structure information and electrical connection relationship information of the energy storage cabinet. Specifically, when the processing module 200 expands the neighborhood range of the core data points, it will make a judgment by combining the spatial coordinates, the physical area to which the target data points belong, and component information, ensuring that the clustering range is limited to the physically directly adjacent area without physical partitions. In addition, the processing module 200 iteratively analyzes whether each newly included target data point meets the core data conditions during the expansion process, so as to gradually expand the clustering range and finally accurately identify the abnormal area of the energy storage cabinet.

[0159] In a specific implementation, the processing module 200 uses the three-dimensional space model of the energy storage cabinet to determine the spatial coordinates of each target data point. For example, the spatial coordinates take the reference point of the energy storage cabinet as the origin, and the position of the target data point is represented by three-dimensional coordinates (x, y, z) (unit: meter).

[0160] Based on the spatial coordinates of the target data points, the processing module 200 further determines the physical area and components to which the target data points belong. For example, a target data point may be located in the battery unit A1 area and is directly associated with the cooling module component.

[0161] Among them, directly adjacent means that the physical area to which the target data point belongs must be spatially directly adjacent to the physical area to which the target data point within the current clustering range belongs. For example, the definition of directly adjacent is that the distance between the center points of the two areas is less than a preset maximum adjacent distance threshold (such as 1 meter).

[0162] No physical partition means that there is no physical barrier such as a fire partition or a barrier between the target data point and the target data point within the current clustering range.

[0163] Component relevance means that the component to which the target data point belongs must be directly electrically connected to the component to which the target data point belongs within the current clustering range, for example, confirmed through an electrical connection relationship database.

[0164] In a specific implementation, for the target data points within the neighborhood range of each core data point, the processing module 200 determines one by one whether they are boundary data. The determination basis for boundary data is: the target data point is within the neighborhood range, but the number of target data within its neighborhood range is less than the minimum point threshold (MinPts).

[0165] On the premise of meeting the spatial constraint conditions, the processing module 200 incorporates the boundary data into the clustering range.

[0166] In a specific implementation, for the newly incorporated boundary data points, the processing module 200 determines whether they meet the core data conditions (that is, the number of target data within the neighborhood range is greater than or equal to the minimum point threshold). If they meet the conditions, they are used as new core data points, and the target data within their neighborhood ranges are continued to be expanded.

[0167] The clustering range is iteratively expanded in a recursive or looped manner until no new target data points meet the conditions.

[0168] Exemplarily, during the actual operation of a certain energy storage cabinet, the target data set transmitted by the acquisition module 100 includes data of 30 monitoring points. The processing module 200 applies the density clustering method for clustering expansion.

[0169] The processing module 200 first generates an initial cluster, and the initial cluster includes the core data point A and the target data points within its neighborhood range.

[0170] The target data point B within the neighborhood range is determined to be boundary data because the number of target data within its neighborhood range is 3, which is less than MinPts (4). The spatial coordinates of data point B are (1.2, 2.5, 0.8) meters, and the distance from the spatial coordinates (1.0, 2.0, 0.8) meters of the core data point A is 0.6 meters, which is less than the maximum adjacent distance threshold (1 meter). There is no fire partition between data point B and the core data point A, and the components corresponding to the two are directly electrically connected.

[0171] Data point B meets the spatial constraint conditions and is incorporated into the clustering range.

[0172] The processing module 200 analyzes the neighborhood range of data point B and finds that the number of target data within its neighborhood range is 5, which is greater than or equal to MinPts (4), and upgrades it to a core data point.

[0173] Taking data point B as the new core data point, continue to expand its neighborhood range.

[0174] After multiple iterations and expansions, the processing module 200 finally identifies the abnormal area inside the energy storage cabinet and marks it as the first target area, which contains 200 target data points and covers a group of battery units and cooling components of the energy storage cabinet.

[0175] In this way, by adding spatial constraint conditions and an iterative expansion mechanism to the density-based clustering method, the present invention effectively improves the accuracy of locating abnormal areas in the energy storage cabinet. The spatial constraint conditions combine the physical layout of the energy storage cabinet and the component relevance, ensuring that the clustering range is limited to physically relevant areas and avoiding the risk of misclassifying target data points in irrelevant areas. In addition, the design of iterative expansion clustering can dynamically identify multi-point linked abnormalities, providing accurate input data for subsequent early warning and fire protection processing. This technical solution significantly improves the efficiency and reliability of the energy storage cabinet fire safety system and is applicable to the fire safety management of energy storage cabinets in complex physical environments.

[0176] In the application of the density-based clustering method, the neighborhood distance threshold (Eps) and the minimum number of points threshold (MinPts) are key parameters that directly affect the clustering effect of abnormal areas. However, the traditional fixed threshold method may not be able to adapt to the dynamic changes of target data points in the complex operating environment of the energy storage cabinet. For example, target data points in different areas may exhibit significantly different degrees of abnormality due to differences in environmental conditions, equipment types, or monitoring status. If a unified clustering parameter is fixed, some abnormal areas may be ignored or misjudged.

[0177] The present invention dynamically adjusts the neighborhood distance threshold and the minimum number of points threshold by introducing an abnormality degree index, enabling the clustering algorithm to adaptively adjust the clustering range according to the specific abnormality of target data points. The abnormality degree index combines the temperature overlimit measurement and the smoke concentration change gradient, and quantifies the abnormality of target data points with the help of an abnormality degree evaluation model. By adjusting the threshold, the system expands the clustering range when the abnormality is severe to ensure capturing the complete abnormal area; and shrinks the clustering range when the abnormality degree is small to avoid misjudgment or over-expansion.

[0178] As an optional implementation manner, the setting of the minimum number of points threshold and the neighborhood distance threshold includes:

[0179] Dynamically adjusting the minimum number of points threshold and the neighborhood distance threshold based on the abnormality degree index of the target data points;

[0180] Among them, the determination of the abnormality degree index includes:

[0181] Quantifying the difference between the temperature value of the target data point and the temperature threshold to obtain the temperature overlimit measurement;

[0182] Monitoring the change rate of the smoke concentration of the target data point to determine the smoke concentration change gradient of the target data point;

[0183] Input the temperature excess amount and the smoke concentration change gradient into a preset abnormal degree evaluation model, and output the corresponding abnormal degree index;

[0184] The dynamically adjusting the minimum point number threshold and the neighborhood distance threshold includes:

[0185] When the abnormal degree index is greater than or equal to a preset abnormal degree index threshold, increase the neighborhood distance threshold and decrease the minimum point number threshold to expand the clustering range;

[0186] When the abnormal degree index is less than the preset abnormal degree index threshold, decrease the neighborhood distance threshold and increase the minimum point number threshold to narrow the clustering range.

[0187] In a specific implementation, the processing module 200 quantifies the difference between the temperature value of the target data point and the temperature threshold :

[0188]

[0189] If , then the temperature of the target data point exceeds the threshold, and it is quantified as a positive value; if , then it is quantified as zero.

[0190] Monitor the change rate of the smoke concentration of the target data point over time, and calculate the smoke concentration change gradient :

[0191]

[0192] wherein, is the change amount of the smoke concentration within the unit time (unit: ppm / s).

[0193] Input the temperature excess amount and the smoke concentration change gradient into a preset abnormal degree evaluation model (such as a regression model or a rule model based on machine learning) to obtain the abnormal degree index . For example:

[0194]

[0195] wherein, and are the model weights; the abnormal degree index is a dimensionless index reflecting the abnormality of the target data point, and its value range is . Generally, The higher the value, the stronger the abnormality of the target data point. For the convenience of calculation and comparison, the abnormality degree index can also be normalized to the interval [0, 1].

[0196] Exemplarily, the weights of the abnormality evaluation model and can be set according to the operating characteristics of different areas inside the energy storage cabinet. For example, in the battery unit area, temperature exceeding the limit is the main abnormality feature, so it is preferably set ; in the cooling component area, the change in smoke concentration is the main abnormality feature, and it is preferably set . In addition, the weight values can be obtained by optimizing through statistical analysis of historical data and model verification.

[0197] Exemplarily, the threshold of the abnormality degree index can be set according to the operating environment of the energy storage cabinet and the statistical results of historical data. For example, in the battery unit area, due to the high fire risk, the threshold of the abnormality degree index is preferably set to 2.0; in the cooling component area, due to the slow development of abnormalities, the threshold is preferably set to 3.0.

[0198] Exemplarily, when the abnormality degree index is greater than or equal to the preset abnormality degree index threshold, the neighborhood distance threshold Eps can be amplified by a ratio of 10%-20%, and the minimum number of points threshold MinPts can be reduced by 1-2 data points; when the abnormality degree index is less than the preset abnormality degree index threshold, the neighborhood distance threshold and the minimum number of points threshold gradually return to the initial values.

[0199] It should be noted that the adjusted parameters need to be controlled within the set upper and lower limits.

[0200] In this way, the processing module 200 calculates the abnormality degree index in real time during the clustering process and dynamically adjusts the clustering parameters, so that the clustering range can flexibly adapt to the abnormality degree of the target data point.

[0201] Exemplarily, the present invention uses a linear regression model as the abnormality evaluation model. The input features of the model include the temperature exceeding limit measure and the smoke concentration change gradient of the target data point, and the output is the abnormality degree index. The training data set is constructed by the actual operation data of the energy storage cabinet, and the temperature values and smoke concentration change values of the historical target data points are used to generate labels for model training by annotating the known abnormal areas. The model uses the mean square error as the loss function for optimization and evaluates the model performance through the validation data set. The experimental results show that the model can accurately reflect the abnormality degree of the target data point.

[0202] The present invention effectively solves the problem that the fixed parameters in the traditional density clustering method are difficult to adapt to dynamic changes by dynamically adjusting the clustering parameters based on the anomaly degree index. The quantification of the anomaly degree index comprehensively considers the degree of temperature overrun and the change rate of smoke concentration, and can accurately reflect the anomaly situation of the target data points. By dynamically adjusting the neighborhood distance threshold and the minimum number of points threshold, the present invention expands the clustering range when the anomaly is severe to ensure the integrity of the anomaly area; when the anomaly is mild, it reduces the clustering range to avoid misjudgment and over-expansion. This method significantly improves the flexibility and accuracy of the energy storage cabinet fire safety management system.

[0203] As an alternative implementation manner, determining the first target area of the energy storage cabinet based on the clustering result includes: determining the spatial range of the first target area based on the core data and boundary data in the target data set;

[0204] Extracting target features from the first target area includes:

[0205] Extracting the highest temperature value of the target data;

[0206] Extracting the change rate of the smoke concentration of the target data;

[0207] Extracting the spatial distribution density of the target data;

[0208] Extracting the proportion of the number of anomaly points in the target data.

[0209] The processing module 200 uses the result of the density clustering method, combines the core data and boundary data in the target data set, determines the first target area of the energy storage cabinet, and extracts the key feature information related to the anomaly state therefrom to provide support for the subsequent warning module 300 and execution module 400.

[0210] Among them, the determination process of the first target area includes accurately delimiting the area of the energy storage cabinet where anomalies may exist based on the spatial distribution of the core data and boundary data, combined with the three-dimensional spatial model, physical structure information, and electrical connection relationship information of the energy storage cabinet.

[0211] In a specific implementation, the processing module 200 first extracts core data points and boundary data points from the density clustering results. A core data point refers to a target data point whose number of target data within the neighborhood range is greater than or equal to the minimum point threshold MinPts, while a boundary data point is a target data point whose number of target data within the neighborhood range is less than MinPts but belongs to the neighborhood range of a core data point. Combining the spatial coordinates of the core data and the boundary data, the processing module 200 determines the preliminary range of the first target area according to the three-dimensional space model of the energy storage cabinet. The preliminary range of the first target area can be expressed as the minimum bounding volume of the core data points and the boundary data points, and its spatial range is defined as the minimum three-dimensional space range that contains all relevant data points. For example, if the spatial coordinates of the core data points and the boundary data points are and , then the spatial range of the first target area is: .

[0212] In addition, in order to further improve the accuracy of area determination, the processing module 200 uses the physical structure information and electrical connection relationship information of the energy storage cabinet to correct the preliminary range.

[0213] In a specific implementation, the processing module 200 will analyze whether there are physical barriers between the target data points, such as fire partitions, electrical barriers, etc. If a certain target data point within the preliminary range is blocked outside other areas, then this target data point will be removed from the first target area. At the same time, the processing module 200 will combine the electrical connection relationship information to judge whether the component to which the target data point belongs has a direct electrical connection relationship with the components in the current area. If the component to which a certain target data point belongs has no direct electrical connection with the components in the current area, this target data point will also be excluded from the first target area. By combining the three-dimensional space model, physical structure information and electrical connection relationship information, the exact range of the first target area is finally determined.

[0214] Exemplarily, the physical structure information and electrical connection relationship information of the energy storage cabinet can be stored in a database and managed in the form of a graph data structure (Graph) for the spatial and electrical relationships between components. The processing module 200 can use the NetworkX library of Python to implement the judgment of electrical connection relationships, and analyze whether there are physical barriers in combination with the three-dimensional spatial coordinates of the target data points (such as excluding target data points separated by fire partitions through spatial geometric calculations);

[0215] After the first target area is determined, the processing module 200 further extracts target feature information from this area to comprehensively evaluate the state of the abnormal area and provide support for subsequent modules. These target features include the highest temperature value, the change rate of smoke concentration, the spatial distribution density, and the proportion of the number of abnormal points, etc.

[0216] Exemplarily, the maximum temperature value is determined by extracting the maximum value of the temperature values of all target data points within the first target area, which is used to reflect the degree of temperature abnormality in this area; the smoke concentration change rate is obtained by calculating the average value of the smoke concentration change rates of all target data points within the first target area, which is used to evaluate the smoke change trend in this area; the spatial distribution density is determined by calculating the ratio of the number of target data points within the first target area to the volume of this area, which is used to reflect the distribution of target data points within this area; the proportion of the number of abnormal points is determined by calculating the percentage of the number of abnormal points within the first target area in the total number of target data points, which is used to reflect the relative proportion of abnormal points.

[0217] Exemplarily, it is assumed that the three-dimensional space model of the energy storage cabinet includes areas such as battery units and cooling components, and the core data points and boundary data points in the target data set are respectively distributed in the battery unit A1 and the cooling component B1 areas. The processing module 200 first determines the preliminary range based on the density clustering result, and then excludes the target data points isolated by the fire partition combined with the physical structure information, and excludes the target data points that have no direct electrical connection with the current area combined with the electrical connection relationship information. Finally, the first target area determined by the processing module 200 covers the battery unit A1 and the cooling component B1. Subsequently, the processing module 200 extracts target features from this area: the maximum temperature value is 80 °C, the smoke concentration change rate is 0.35 ppm / s, the spatial distribution density is 15 points / m³, and the proportion of the number of abnormal points is 60%. These features can comprehensively reflect the state of the abnormal area and provide a basis for the warning module 300 to generate warning information.

[0218] In this way, by determining the first target area from the clustering result and extracting the target feature information, the present invention can not only accurately locate the abnormal area, but also comprehensively evaluate the area state, providing efficient and reliable technical support for the fire safety management of the energy storage cabinet. This design is particularly applicable to the scenarios of the complex physical layout and multi-component correlation of the energy storage cabinet, significantly improving the abnormal detection accuracy and response efficiency of the system.

[0219] As an optional implementation manner, matching the corresponding warning information for the target feature based on the preset warning mechanism includes:

[0220] Based on the target feature, classifying the first target area into different warning levels; wherein, the warning levels include: first-level warning, second-level warning, and third-level warning;

[0221] Based on the warning level, generating the warning information corresponding to this warning level.

[0222] Based on the warning information, performing the fire protection processing corresponding to the warning information in the first target area includes:

[0223] In response to the warning level being the first-level warning, trigger the cooling system in the energy storage cabinet to reduce the temperature of the first target area;

[0224] In response to the warning level being the second-level warning, trigger the local fire protection system of the energy storage cabinet to spray fire extinguishing medium towards the first target area;

[0225] In response to the warning level being the third-level warning, trigger the full-cabinet fire protection system of the energy storage cabinet, simultaneously spray fire extinguishing medium towards the first target area, and issue an emergency alarm signal to notify the external control center.

[0226] In specific implementation, based on a preset warning mechanism, classify the abnormal characteristics of the first target area and generate corresponding warning information to guide the fire protection treatment operations of the energy storage cabinet. Specifically, divide the first target area into different warning levels according to the target characteristics, and generate corresponding warning information through the warning module 300. The execution module 400 then takes corresponding fire protection treatment measures in the first target area according to the warning information to ensure a quick and accurate response to abnormal situations.

[0227] Among them, the warning module 300 stores a multi-level warning mechanism, which is based on target characteristics and includes key parameters such as the highest temperature value, the change rate of smoke concentration, the spatial distribution density, and the proportion of the number of abnormal points. The warning module 300 determines the severity of the abnormality in the first target area according to these target characteristics and classifies it into the first-level warning, the second-level warning, and the third-level warning. The first-level warning is used to indicate a slight abnormal situation, the second-level warning is used to indicate a moderate abnormal situation, and the third-level warning is used to indicate a serious abnormal situation or an emergency state.

[0228] In specific implementation, the division of the warning level is based on a preset threshold rule. For example:

[0229] 1. First-level warning: If the highest temperature value in the first target area is between and (such as ), and the change rate of smoke concentration is low (such as less than 0.3 ppm / s) and the spatial distribution density is normal, it is determined as the first-level warning;

[0230] 2. Second-level warning: If the highest temperature value exceeds but is lower than (such as ), or the change rate of smoke concentration is high (such as within 0.3 to 0.6 ppm / s), it is determined as the second-level warning;

[0231] 3. Third-level warning: If the highest temperature value exceeds , or the rate of change of the smoke concentration exceeds 0.6 ppm / s, or the proportion of the number of abnormal points exceeds 50%, then it is determined as a level-three early warning.

[0232] The early warning module 300 generates the above classification results into corresponding early warning information and sends it to the execution module 400. The early warning information includes: the location information of the abnormal area, the early warning level, the key target characteristic values, and the recommended fire-fighting treatment measures. For example, if the first target area of a certain energy storage cabinet is determined to be a level-three early warning, the early warning information will indicate the spatial range of this area, the highest temperature value (such as 95 °C), the rate of change of the smoke concentration (such as 0.7 ppm / s), and the recommended emergency fire-fighting measures.

[0233] The execution module 400 responds to the abnormal situation in the first target area according to the early warning information and takes fire-fighting treatment measures corresponding to the early warning level:

[0234] 1. Level-one early warning: When the early warning level is level one, the execution module 400 triggers the cooling system in the energy storage cabinet, such as starting the cooling fan or opening the liquid cooling cycle, to reduce the temperature of the first target area and prevent the temperature from rising further;

[0235] 2. Level-two early warning: When the early warning level is level two, the execution module 400 triggers the local fire-fighting system of the energy storage cabinet, such as spraying a fire-extinguishing medium (such as carbon dioxide or inert gas) into the first target area to quickly suppress the possible fire source;

[0236] 3. Level-three early warning: When the early warning level is level three, the execution module 400 triggers the full-cabinet fire-fighting system, sprays the fire-extinguishing medium into the first target area at the same time, and issues an emergency alarm signal to notify the external control center. For example, high-priority alarm information can be sent to the monitoring center through the remote communication module, and relevant data is recorded for subsequent analysis.

[0237] Exemplarily, in a certain energy storage station, the early warning module 300 detects that the target characteristic values in the first target area are: the highest temperature is 85 °C, the rate of change of the smoke concentration is 0.5 ppm / s, the spatial distribution density is 12 points / m³, and the proportion of the number of abnormal points is 40%. According to the preset rules, this area is determined to be a level-two early warning. After the early warning information is generated, the execution module 400 triggers the local fire-fighting system, sprays carbon dioxide fire-extinguishing medium into this area, and starts the cooling system to assist in cooling down, avoiding the risk of further expansion of the abnormality.

[0238] Please refer to Figures 3 to 5 , Figure 3 a three-dimensional structure schematic diagram of an energy storage cabinet provided by an embodiment of the present disclosure; Figure 4 a front structure schematic diagram inside the cabinet provided by an embodiment of the present disclosure; Figure 5A schematic diagram of the back structure of a cabinet provided in an embodiment of the present disclosure. For example, in a certain energy storage station, the energy storage cabinet is equipped with a cooling circulation system and a fire protection piping system for temperature control management and fire protection of the battery PACK box 7 in the energy storage cabinet and the surrounding environment. During system operation, the processing module 200 obtains the target data in the energy storage cabinet in real time through the acquisition module 100, including the temperature distribution of the battery PACK box 7, changes in smoke concentration, etc. The processing module 200 uses a clustering algorithm combined with physical layout analysis to identify abnormal areas (first target areas) in the energy storage cabinet, and evaluates the warning level of the area through the warning module 300 to generate corresponding warning information.

[0239] When the warning module 300 detects that the highest temperature value in the first target area is 75°C, the smoke concentration change rate is 0.2 ppm / s, and the spatial distribution density is within the normal range (10 points / m³), it is determined to be a first-level warning. At this time, the execution module 400 starts the cooling circulation system of the energy storage cabinet and activates the refrigeration pipeline for local cooling. The specific processing process is as follows: the low-temperature coolant in the refrigerant box 3 is pumped into the water inlet main pipe 4 by the water pump 1, diverted to the water inlet branch pipe 11, and then flows into the battery PACK box 7 through the water inlet branch pipe 10. After the coolant exchanges heat with the heat generated by the battery heating, the high-temperature coolant flows out of the battery PACK box 7, enters the return water branch pipe 8, flows into the return water branch pipe 9 from the return water branch pipe 8, and then flows into the return water main pipe 6 from the return water branch pipe 9, and flows back to the refrigerant box 3 through the refrigerant box inlet 5 to complete the cooling cycle. The system monitors the inlet and return water temperatures of the coolant in real time to ensure the cooling effect. As the temperature gradually drops, the temperature of the target data point returns to the normal range (below 60°C), and the system cancels the first-level warning.

[0240] When the warning module 300 detects that the maximum temperature of the first target area rises to 85°C, the smoke concentration change rate reaches 0.5 ppm / s, and the number of abnormal points accounts for 40%, it is determined to be a secondary warning. The execution module 400 triggers the local fire protection system of the energy storage cabinet, and quickly cools down and extinguishes the abnormal area through the fire protection pipeline. The specific processing process is as follows: After the external fire protection measures are activated, the high-pressure fire protection water enters the fire protection pipeline from the fire protection water inlet pipe 2, flows into the return water main pipe 6 through the fire protection anti-reverse valve 12, and then enters the battery PACK box 7 through the return water branch pipe 9 and the return water branch pipe 8, and directly contacts the high-temperature area in the box for cooling and extinguishing. Part of the fire protection water flows into the refrigerant box 3 through the return water main pipe 6, and the coolant further reduces the temperature and provides support for the internal cooling system of the energy storage cabinet. The system monitors the temperature and smoke concentration changes of the battery PACK box 7 in real time to confirm the effectiveness of the cooling and fire extinguishing measures.

[0241] When the warning module 300 detects that the highest temperature in the first target area rises above 95°C, the smoke concentration change rate exceeds 0.7 ppm / s, and the proportion of the number of abnormal points reaches 60%, it is determined as a level-3 warning. At this time, the execution module 400 activates the full-cabinet fire protection system of the energy storage cabinet and cools down and extinguishes the fire inside and outside the cabinet through the fire pipeline. The specific processing process is as follows: High-pressure fire water enters the fire pipeline from the fire inlet pipe 2, flows into the return water main pipe 6 through the anti-backflow valve 12 for fire prevention, and then is divided into three paths: The first and second paths flow into the battery PACK box 7 through the return water branch pipe 8 and the refrigerant box 3 to cool down and extinguish the fire for the internal high-temperature battery units; the third path flows into the fire sprinkler 14 at the top of the cabinet through the fire spray pipe 13 to cool down and extinguish the fire for the outside and surrounding areas of the cabinet.

[0242] The system simultaneously sends level-3 warning information to the external monitoring center, including the specific location of the abnormal area, the current temperature (such as 95°C), the smoke concentration change rate (such as 0.8 ppm / s), and the fire protection measures that have been taken. After receiving the information, the monitoring center can further intervene remotely.

[0243] In this way, by combining the cooling pipeline and the fire pipeline system of the energy storage cabinet, the present invention can achieve precise response to hierarchical warnings. During the level-1 warning, the local temperature reduction treatment of the cooling circulation system can timely control minor abnormalities; during the level-2 and level-3 warnings, the local or full-cabinet fire extinguishing measures of the fire pipeline system can quickly suppress the fire source and ensure the safe operation of the energy storage cabinet. In addition, the external alarm function of the level-3 warning further improves the overall safety and reliability of the system.

[0244] In this way, by combining a multi-level warning mechanism with flexible fire protection measures, the present invention can effectively respond to various abnormal situations in the energy storage cabinet. By analyzing and classifying the target characteristics of the first target area in detail, the present invention can accurately generate warning information and select the most suitable fire protection means according to the abnormal level, thereby significantly improving the system response efficiency while ensuring the safety of the energy storage cabinet and reducing the use cost of fire protection resources.

[0245] It should be understood that in various embodiments of the present application, the magnitudes of the serial numbers of the above processes do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0246] It should be understood that determining B according to A does not mean determining B only according to A, but also B can be determined according to A and / or other information.

[0247] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present invention can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0248] In the description of this specification, the description referring to terms such as "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0249] The preferred embodiments of the present invention disclosed above are only used to help explain the present application. The preferred embodiments do not describe all the details in detail, nor do they limit the present application to only the specific implementation manners. Obviously, according to the content of this specification, many modifications and changes can be made. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present application, so that those skilled in the art can understand and utilize the present application well. The present application is only limited by the claims and their full scope and equivalents.

Claims

1. An automated energy storage cabinet fire safety system, characterized in that, The system includes: A collection module, configured to collect in real time target data at preset monitoring points of an energy storage cabinet, and generate a target data set; A processing module, configured to perform data screening on the target data set based on a temperature threshold and / or a smoke threshold and a time threshold, and then perform clustering analysis on the target data set based on the density clustering method to determine a first target area of the energy storage cabinet, and extract target features from the first target area; Wherein, the density clustering method includes: expanding the initial clustering range based on the spatial coordinates, the physical area and components to which each target data point in the initial clustering range belongs, and spatial constraint conditions; and dynamically adjusting the minimum number of points threshold and the neighborhood distance threshold in the density clustering method based on the abnormality degree index of the target data point; An early warning module, configured to match corresponding early warning information for the target features based on a preset early warning mechanism; An execution module, configured to perform fire protection processing corresponding to the early warning information in the first target area based on the early warning information; The density clustering method includes: setting a minimum number of points threshold and a neighborhood distance threshold, wherein the minimum number of points threshold is used to limit the number of target data required to form a cluster; the neighborhood distance threshold is used to limit the maximum distance between target data points to determine a neighborhood range; the neighborhood range is an area centered on each target data and with a radius equal to the neighborhood distance threshold; Based on the neighborhood range, core data in the target data set is determined, and the core data is target data whose number of target data within its neighborhood range is greater than or equal to the minimum number of points threshold; Based on the neighborhood range of the core data, an initial cluster is determined, and all target data within the neighborhood range of the core data is classified into the initial cluster; Wherein, the target data set includes a plurality of target data points; The setting of the minimum number of points threshold and the neighborhood distance threshold includes: dynamically adjusting the minimum number of points threshold and the neighborhood distance threshold based on the abnormality degree index of the target data point; Wherein, the determination of the abnormality degree index includes: quantifying the difference between the temperature value of the target data point and the temperature threshold to obtain a temperature over-limit measure; Monitoring the change rate of the smoke concentration of the target data point to determine the smoke concentration change gradient of the target data point; Inputting the temperature over-limit measure and the smoke concentration change gradient into a preset abnormality degree evaluation model, and outputting the corresponding abnormality degree index; The dynamic adjustment of the minimum number of points threshold and the neighborhood distance threshold includes: when the abnormality degree index is greater than or equal to a preset abnormality degree index threshold, increasing the neighborhood distance threshold and decreasing the minimum number of points threshold to expand the clustering range; When the abnormality degree index is less than the preset abnormality degree index threshold, decreasing the neighborhood distance threshold and increasing the minimum number of points threshold to narrow the clustering range.

2. The system according to claim 1, wherein The collection module further includes: A sensor network, configured to collect in real time the target data at each preset monitoring point in the energy storage cabinet; wherein, the sensor network includes at least one sensor; A preprocessing unit for preprocessing the target data at each preset monitoring point in the energy storage cabinet to generate the target data set.

3. The system according to claim 2, wherein The density clustering method further includes: Under the condition of meeting the preset spatial constraint conditions, incorporating the boundary data within the neighborhood range of the core data into the clustering; For the newly incorporated boundary data, if it meets the core data conditions and conforms to the spatial constraints, continue to expand the target data within its neighborhood range; Iteratively expand the clustering until no new target data is incorporated into the clustering range.

4. The system according to claim 3, characterized in that, Data screening based on temperature threshold and / or smoke threshold and time threshold in the target data set includes: Setting a time threshold; Screening the target data set based on the time threshold, including: Determining whether the target data point is greater than the temperature threshold and / or smoke threshold and continuously exceeds the time threshold; In response to the target data point being greater than the temperature threshold and / or smoke threshold but not exceeding the time threshold, exclude it from the target data set.

5. The system according to claim 4, characterized in that, Determining the first target area of the energy storage cabinet based on the clustering result includes: determining the spatial range of the first target area based on the core data and boundary data in the target data set; Extracting target features from the first target area includes: Extracting the highest temperature value of the target data; Extracting the smoke concentration change rate of the target data; Extracting the spatial distribution density of the target data; Extracting the proportion of the number of abnormal points in the target data.

6. The system according to claim 5, characterized in that The density clustering method further includes: Based on the three-dimensional space model of the energy storage cabinet, determining the spatial coordinates of each target data point; Based on the spatial coordinates of the target data point, determining the physical area and components to which each target data point belongs; Based on the physical structure information and electrical connection relationship information of the energy storage cabinet, determining the spatial constraint conditions; The expansion of the initial clustering range based on the spatial coordinates, the physical area and components to which each target data point in the initial clustering range belongs, and the spatial constraint conditions includes: Judging whether the following conditions are simultaneously satisfied for the target data point to be expanded that is not within the initial clustering range: The physical area to which the target data point to be expanded belongs is directly adjacent in structure to the physical area to which at least one target data point within the current clustering range belongs, and there is no physical partition between them; The component to which the target data point to be expanded belongs is directly electrically connected to the component to which at least one target data point within the current clustering range belongs; If the above conditions are all satisfied, incorporate the target data point to be expanded into the clustering range.

7. The system according to claim 6, wherein Matching corresponding warning information for the target features based on the preset warning mechanism includes: Based on the target features, classifying the first target area into different warning levels; wherein, the warning levels include: first-level warning, second-level warning, and third-level warning; Based on the warning level, generating the warning information corresponding to this warning level; Performing fire protection processing corresponding to the warning information in the first target area based on the warning information includes: In response to the warning level being the first-level warning, triggering the cooling system in the energy storage cabinet to reduce the temperature of the first target area; In response to the warning level being the secondary warning, trigger the local fire protection system of the energy storage cabinet to spray the fire extinguishing medium into the first target area; In response to the warning level being the tertiary warning, trigger the full-cabinet fire protection system of the energy storage cabinet, simultaneously spray the fire extinguishing medium into the first target area, and issue an emergency alarm signal to notify the external control center.

Images