Energy storage container safety inspection method and system

By identifying faults with data acquisition and cluster detection algorithms of energy storage containers, generating inspection strategies, and optimizing inspection paths, the problem of low fault identification and inspection efficiency in the existing technology is solved, and more precise management and energy are achieved Utilization efficiency.

CN118552001BActive Publication Date: 2024-11-19CHINA SOUTHERN POWER GRID ENERGY STORAGE CO LTD INFORMATION & COMM BRANCH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410993069.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-24
Publication Date
2024-11-19
Estimated Expiration
2044-07-24

AI Technical Summary

Technical Problem

Existing energy storage container monitoring and maintenance technologies cannot accurately identify complex failure modes in real time, and rely on manual inspections to be inefficient and insufficient data analysis, resulting in high operation and maintenance costs, low system efficiency and reliability.

Method used

By conducting comprehensive data acquisition of energy storage containers, including voltage, current and circulation data, building energy storage performance maps, using cluster detection algorithms to identify faults, generate data inspection strategies, and using environmental data to optimize inspection paths to control inspections The inspection robot conducts safety inspection.

Benefits of technology

It improves the accuracy of fault detection, reduces maintenance costs and safety risks, optimizes inspection efficiency and safety, extends battery service life, and improves energy utilization efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118552001B_ABST
    Figure CN118552001B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of safety inspection technology, and discloses a safety inspection method and system for energy storage containers, the method comprising: collecting data on a target energy storage container to obtain a battery performance data set; constructing an energy storage performance map of the target energy storage container and performing fault identification to obtain a fault data set; collecting environmental data on the target energy storage container to obtain an environmental data set and generate a data inspection strategy; constructing an inspection path for an inspection robot to obtain a target inspection path and control the inspection robot to perform an environmental safety inspection on the target energy storage container and a data safety inspection on the target energy storage container. This solution accurately manages the energy storage container, thereby extending the service life of the battery and optimizing energy utilization efficiency. By considering the impact of environmental factors on battery performance and analyzing environmental data such as temperature and humidity, the inspection strategy can be adjusted in real time, further improving the adaptability and robustness during the inspection process.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of safety inspection, and in particular to a safety inspection method and system for energy storage containers. Background Art

[0002] In the current application of energy storage technology, energy storage containers are used as an efficient energy storage solution in the fields of renewable energy storage, grid regulation, emergency backup power supply, etc. Existing technologies mainly rely on traditional monitoring systems and manual inspection methods to maintain and monitor the performance and safety of energy storage containers. These systems usually include basic voltage, current and temperature monitoring, as well as regular manual inspections. In some advanced applications, simple data analysis tools may be integrated to predict equipment failure or performance degradation.

[0003] However, existing energy storage container monitoring and maintenance technologies have several obvious shortcomings. First, traditional monitoring systems are usually unable to accurately identify and predict complex failure modes in real time, which limits the ability to respond to potential problems in a timely manner. Second, manual inspections rely on manual operations, which is not only inefficient, but may also lead to unstable inspection quality due to human factors. In addition, existing data analysis methods are generally insufficient to process and interpret large amounts of monitoring data, and cannot provide sufficient analysis depth to optimize the operation and maintenance strategies of energy storage systems. These limitations increase operation and maintenance costs and reduce the overall efficiency and reliability of the system. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a method and system for safety inspection of energy storage containers, which are used to improve the efficiency and accuracy of safety inspection of energy storage containers.

[0005] The present invention provides a method for safety inspection of an energy storage container, comprising: collecting data on a target energy storage container to obtain a battery performance data set, wherein the battery performance data set includes: voltage data, battery data and circulating current data; constructing an energy storage performance map of the target energy storage container according to the battery performance data set; performing fault identification on the energy storage performance map by a clustering detection algorithm to obtain a fault data set; collecting environmental data on the target energy storage container to obtain an environmental data set; generating a data inspection strategy based on the fault data set, wherein the data inspection strategy includes a data inspection frequency and an inspection data type; constructing an inspection path for a preset inspection robot based on the environmental data set to obtain a target inspection path; controlling the inspection robot to perform environmental safety inspection on the target energy storage container through the target inspection path, and at the same time, performing data safety inspection on the target energy storage container through the data inspection strategy.

[0006] In the present invention, data collection is performed on the target energy storage container to obtain a battery performance data set, wherein the battery performance data set includes: voltage data, battery data and circulating current data, including: positioning and configuring the voltage sensor of the target energy storage container to obtain a voltage sensor layout plan; positioning and configuring the current sensor of the target energy storage container to obtain a current sensor layout plan;

[0007] A sensor network is constructed based on the voltage sensor layout scheme and the current sensor layout scheme; data is collected on the target energy storage container through the sensor network to obtain initial voltage data and initial current data; time synchronization is performed on the initial voltage data and the initial current data to obtain the voltage data and the battery data; circulating current detection is performed on multiple battery modules in the target energy storage container to obtain initial circulating current data; and timestamps the initial circulating current data to obtain the circulating current data.

[0008] In the present invention, the energy storage performance map of the target energy storage container is constructed according to the battery performance data set, including: performing a battery module-based performance data cluster analysis on the battery performance data set to obtain a plurality of groups of sub-performance data corresponding to the battery performance data set; performing a time series analysis on each group of sub-performance data to obtain an energy storage decay trend corresponding to the target energy storage container; based on the energy storage decay trend, performing feature extraction on each group of sub-performance data to obtain an energy storage load capacity and a circulation level; and constructing a performance map of the battery performance data set according to the energy storage load capacity and the circulation level to obtain the energy storage performance map.

[0009] In the present invention, the energy storage performance map is subjected to fault identification by a clustering detection algorithm to obtain a fault data set, including: identifying performance nodes on the energy storage performance map to obtain a plurality of performance nodes; matching the performance data of each performance node respectively, and performing circulation path analysis on the plurality of performance nodes to obtain a plurality of circulation paths; performing probability density estimation on the performance data of each performance node by a kernel density estimation algorithm to obtain a probability density estimation value corresponding to each performance node; based on a preset probability density threshold, performing fault node identification on the probability density estimation value corresponding to each performance node respectively to obtain at least one fault node; performing circulation data correlation analysis on each circulation path to obtain circulation correlation data between every two circulation paths; performing circulation data anomaly identification on each circulation path respectively through the circulation correlation data between every two circulation paths to obtain abnormal circulation data; constructing fault data based on the at least one fault node and the abnormal circulation data to obtain the fault data set.

[0010] In the present invention, the data patrol strategy is generated based on the fault data set, wherein the data patrol strategy includes a data patrol frequency and a patrol data type, including: performing data analysis on the fault data set to obtain a fault frequency, a fault duration and a fault degree; generating fault cycle data through the fault frequency and the fault duration; performing patrol frequency analysis based on the fault cycle data and the fault degree to obtain the data patrol frequency; performing fault type analysis on the fault cycle data to obtain a fault type; performing patrol data type analysis on the fault type to obtain the patrol data type, and generating the data patrol strategy according to the patrol data type and the data patrol frequency.

[0011] In the present invention, the inspection path of the preset inspection robot is constructed based on the environmental data set to obtain the target inspection path, including: extracting data from the environmental data set to obtain map data, terrain data, obstacle data and equipment distribution data corresponding to the target energy storage container;

[0012] A three-dimensional space coordinate system corresponding to the target energy storage container is generated according to the map data and the terrain data; based on the three-dimensional space coordinate system, the obstacle data and the equipment distribution data are mapped to the three-dimensional space coordinate system to obtain a coordinate system to be analyzed; temperature and humidity are collected for the target energy storage container to obtain temperature data and humidity data; based on the temperature data and the humidity data, the coordinate system to be analyzed is divided into dangerous areas to obtain at least one dangerous area; through at least one dangerous area, an inspection path is constructed for the target energy storage container in the coordinate system to be analyzed to obtain the target inspection path.

[0013] In the present invention, the inspection path of the target energy storage container in the coordinate system to be analyzed is constructed through at least one dangerous area to obtain the target inspection path, including: matching the danger level of at least one dangerous area to obtain the danger level corresponding to the at least one dangerous area; performing inspection priority analysis on the at least one dangerous area based on the danger level corresponding to the at least one dangerous area to obtain a priority list; and constructing the inspection path of the target energy storage container in the coordinate system to be analyzed through the priority list to obtain the target inspection path.

[0014] The present invention also provides a safety inspection system for energy storage containers, comprising:

[0015] A first acquisition module is used to collect data from a target energy storage container to obtain a battery performance data set, wherein the battery performance data set includes: voltage data, battery data, and circulating current data;

[0016] A first construction module is used to construct an energy storage performance map of the target energy storage container according to the battery performance data set;

[0017] An identification module, used to perform fault identification on the energy storage performance map by using a clustering detection algorithm to obtain a fault data set;

[0018] A second acquisition module is used to collect environmental data of the target energy storage container to obtain an environmental data set;

[0019] A generating module, configured to generate a data inspection strategy based on the fault data set, wherein the data inspection strategy includes a data inspection frequency and an inspection data type;

[0020] A second construction module is used to construct an inspection path for a preset inspection robot based on the environmental data set to obtain a target inspection path;

[0021] The inspection module is used to control the inspection robot to perform an environmental safety inspection on the target energy storage container through the target inspection path, and at the same time, to perform a data safety inspection on the target energy storage container through the data inspection strategy.

[0022] In the technical solution provided by the present invention, by collecting comprehensive data of the energy storage container, including voltage, current, circulating current and other data, the working state and environmental conditions of the battery are monitored in real time, which not only improves the comprehensiveness of data collection, but also ensures the reliability and accuracy of the data through precise monitoring. Secondly, by constructing an energy storage performance map and using a clustering detection algorithm for fault identification, potential faults and anomalies can be effectively identified from a large amount of performance data, which not only improves the accuracy of fault detection, but also greatly reduces the maintenance cost and potential safety risks caused by faults. In addition, the data inspection strategy generated based on the fault data set and the use of the environmental data set further optimizes the path planning of the inspection robot, which not only improves the inspection efficiency, but also ensures the safety and stability of the system during the inspection process. Through this inspection method, the energy storage container can be managed more accurately and scientifically, thereby extending the service life of the battery and optimizing the energy utilization efficiency. More importantly, the scheme also takes into account the impact of environmental factors on battery performance. By analyzing environmental data such as temperature and humidity, the inspection strategy can be adjusted in real time to further improve the adaptability and robustness during the inspection process. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 This is a flow chart of a method for safety inspection of an energy storage container in an embodiment of the present invention;

[0025] Figure 2 Schematic diagram of a safety inspection system for an energy storage container in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0028] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0029] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , Figure 1 is a flow chart of a method for safety inspection of an energy storage container according to an embodiment of the present invention. Figure 1 As shown, the following steps are included:

[0030] S101, collecting data from a target energy storage container to obtain a battery performance data set, wherein the battery performance data set includes: voltage data, battery data, and circulating current data;

[0031] S102, constructing an energy storage performance map of a target energy storage container according to a battery performance data set;

[0032] S103, performing fault identification on the energy storage performance map by using a clustering detection algorithm to obtain a fault data set;

[0033] S104, collecting environmental data of the target energy storage container to obtain an environmental data set;

[0034] S105, generating a data inspection strategy based on the fault data set, wherein the data inspection strategy includes a data inspection frequency and an inspection data type;

[0035] S106, constructing an inspection path for a preset inspection robot based on the environmental data set to obtain a target inspection path;

[0036] S107. Control the inspection robot to perform an environmental safety inspection on the target energy storage container through the target inspection path. At the same time, perform a data safety inspection on the target energy storage container through the data inspection strategy.

[0037] It should be noted that, for example, by deploying a variety of sensors in the container, the system can continuously monitor key indicators such as voltage, current and circulating current. These data are sent to the data processing center in real time through an efficient transmission network, ensuring the timeliness and accuracy of the information. In addition, the data collection of environmental sensors such as temperature and humidity sensors provides the necessary information for understanding the performance of batteries under different environmental conditions. Further, based on these integrated data, an energy storage performance map is constructed. The map uses data clustering algorithms, such as K-means or hierarchical clustering, to analyze the battery performance data set and classify the batteries into different performance levels. In this way, the system can identify groups of batteries with similar performance and continuously monitor their performance. For example, if the current data of a battery group shows abnormal fluctuations, the clustering algorithm can quickly identify this group and trigger further fault analysis processes. This approach not only improves the accuracy of fault detection, but also can identify potential anomalies in a timely manner, thereby avoiding possible safety risks and maintenance costs.

[0038] In addition, targeted data inspection strategies are generated based on the fault data set. For example, if a battery module frequently overheats, the system will automatically adjust the inspection frequency of the module to ensure that the problem can be discovered and resolved in a timely manner. This strategy is not only based on the fault history data, but also combined with the current environmental data set, such as temperature and humidity. By analyzing these environmental data, the system can make real-time adjustments to the inspection strategy to adapt to changing external conditions. For example, during hot weather, it may be necessary to increase the inspection frequency of all battery modules, especially those that have performed poorly in previous high-temperature environments. Finally, using these strategies and data, the path planning of the inspection robot is further optimized. Through the integration of precise map data, terrain data, obstacle data, and equipment distribution data, the robot can calculate the optimal inspection path. This not only improves the inspection efficiency, but also ensures the safety of the inspection process and the stability of the system. For example, if an area is identified as a high-risk area, the inspection robot will adjust its path to avoid the area, or take additional safety measures if necessary.

[0039] By executing the above steps, the energy storage container is comprehensively collected, including voltage, current, circulating current and other data, and the working status and environmental conditions of the battery are monitored in real time, which not only improves the comprehensiveness of data collection, but also ensures the reliability and accuracy of the data through precise monitoring. Secondly, the construction of energy storage performance maps and the use of clustering detection algorithms for fault identification can effectively identify potential faults and anomalies from a large amount of performance data, which not only improves the accuracy of fault detection, but also greatly reduces the maintenance costs and potential safety risks caused by faults. In addition, the data inspection strategy generated based on the fault data set and the use of the environmental data set further optimizes the path planning of the inspection robot, which not only improves the inspection efficiency, but also ensures the safety and stability of the system during the inspection process. Through this inspection method, the energy storage container can be managed more accurately and scientifically, thereby extending the service life of the battery and optimizing the energy utilization efficiency. More importantly, the scheme also takes into account the impact of environmental factors on battery performance. By analyzing environmental data such as temperature and humidity, the inspection strategy can be adjusted in real time to further improve the adaptability and robustness of the inspection process.

[0040] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0041] (1) Position and configure the voltage sensors of the target energy storage container to obtain a voltage sensor layout plan;

[0042] (2) Position and configure the current sensors of the target energy storage container to obtain a current sensor layout plan;

[0043] (3) Constructing a sensor network based on the voltage sensor layout scheme and the current sensor layout scheme;

[0044] (4) Collect data from the target energy storage container through the sensor network to obtain initial voltage data and initial current data;

[0045] (5) Time-synchronize the initial voltage data and the initial current data to obtain voltage data and battery data;

[0046] (6) Performing circulation detection on multiple battery modules in the target energy storage container to obtain initial circulation data;

[0047] (7) Timestamp the initial circulation data to obtain the circulation data.

[0048] For example, if the battery modules are configured in series, voltage sensors will be placed at each connection point to capture possible voltage differences. Such a configuration can promptly detect voltage imbalances caused by battery aging or failure. Next, the positioning and configuration of current sensors is equally important, mainly to monitor the flow and changes of current. In energy storage containers, current sensors are usually placed at the inlet and outlet of the main circuit and at key nodes connecting the main loads. Through such a layout scheme, not only can the overall flow of current be monitored in real time, but also the performance of current on a specific path can be understood in detail, thereby effectively predicting and diagnosing possible faults.

[0049] With the specific layout plan of voltage and current sensors, a comprehensive sensor network can be built. This network connects all sensors and transmits data back to the central processing unit in real time. In actual operation, the sensor network not only needs to collect data efficiently, but also needs to have a fault-tolerant mechanism to ensure that the integrity and accuracy of the data will not be greatly affected even if a sensor fails. Subsequently, the target energy storage container is collected through this sensor network to initially obtain the raw data of voltage and current. These data are collected in real time and can reflect the instantaneous state of the battery in actual operation. The collected initial voltage and current data then need to be time-synchronized to ensure the consistency and comparability of the data set during subsequent analysis. Time synchronization is usually achieved through a network time protocol (NTP) server to ensure that all data has a unified time tag to facilitate timing analysis and trend prediction.

[0050] In addition, circulation detection in energy storage containers is also an important means of monitoring battery health. Circulation usually refers to the circulating current generated in the unbalanced state of the battery module, which will increase the thermal load and aging rate of the battery. By setting up a circulation detection sensor in the battery module, initial circulation data can be obtained. This data also needs to be time-stamped to ensure the timeliness and accuracy of the analysis.

[0051] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0052] (1) Performing a battery module-based performance data cluster analysis on the battery performance data set to obtain multiple groups of sub-performance data corresponding to the battery performance data set;

[0053] (2) Perform time series analysis on each group of sub-performance data to obtain the energy storage decay trend corresponding to the target energy storage container;

[0054] (3) Based on the energy storage decline trend, feature extraction is performed on each group of sub-performance data to obtain the energy storage load capacity and circulation level;

[0055] (4) A performance map of the battery performance data set is constructed based on the energy storage load capacity and circulation level to obtain an energy storage performance map.

[0056] It should be noted that, for example, some battery modules may show high voltage stability but large current fluctuations, while others may perform poorly in low temperature environments. Such classification makes further analysis more targeted and efficient. Next, for each battery performance data set group, time series analysis is performed to identify and predict the performance degradation trend of each group of batteries. Time series analysis usually involves statistical methods and prediction models, such as autoregressive moving average (ARMA) models or seasonal decomposition time series prediction (STL). These models help understand the changes in battery performance over time, such as the gradual decrease in battery capacity or the decrease in charging efficiency. Through these analyses, the possible state of the battery at a certain point in the future can be predicted, providing data support for maintenance and replacement. After obtaining the trend of battery performance degradation, feature extraction is further performed on each group of data, mainly extracting those features that have the greatest impact on energy storage performance, such as energy storage load capacity and circulation level. The energy storage load capacity reflects the ability of the battery to continuously supply power under a specific load, while the circulation level is an important indicator for evaluating the imbalance state between battery modules. Feature extraction uses techniques such as principal component analysis (PCA) or linear discriminant analysis (LDA), which can identify the most informative features from large amounts of data.

[0057] Finally, these features are used to construct an energy storage performance map. The construction of the map is based on the features extracted above, using data visualization techniques such as heat maps or scatter plots to represent the performance status of different battery modules and the relationship between them. For example, the depth of color can intuitively show which battery modules have a load capacity higher than the average level and which ones have potential risks. In addition, the level of circulation will also be marked with different symbols or colors in the map, allowing maintenance personnel to quickly identify battery modules that need attention.

[0058] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0059] (1) Identify the performance nodes of the energy storage performance map and obtain multiple performance nodes;

[0060] (2) Match the performance data of each performance node respectively, and perform circulation path analysis on multiple performance nodes to obtain multiple circulation paths;

[0061] (3) Perform probability density estimation on the performance data of each performance node using the kernel density estimation algorithm to obtain the probability density estimation value corresponding to each performance node;

[0062] (4) Based on a preset probability density threshold, the probability density estimation value corresponding to each performance node is used to identify the faulty node, and at least one faulty node is obtained;

[0063] (5) Perform circulation data correlation analysis on each circulation path to obtain circulation correlation data between every two circulation paths;

[0064] (6) Using the circulation correlation data between every two circulation paths, the circulation data anomaly of each circulation path is identified to obtain abnormal circulation data;

[0065] (7) Construct fault data based on at least one faulty node and abnormal circulation data to obtain a fault data set.

[0066] Specifically, first, performance nodes are identified from the constructed energy storage performance map. This step involves representing the performance data of the energy storage system as multiple nodes in the map, each of which represents the performance status of the energy storage system under specific working conditions. For example, a performance node may represent the output performance of a battery module under high temperature and high load conditions. These performance nodes are matched in detail and the circulation path analysis is performed. Specifically, the data of each performance node, such as voltage, current, and temperature, will be used to analyze the circulation path between battery modules. Circulation path analysis refers to identifying and evaluating the path and intensity of current circulation between battery modules, which is crucial for discovering imbalances in battery packs. For example, if two adjacent battery modules show a significant current difference, this may indicate that the performance of one of the modules has degraded and further testing is required.

[0067] After completing the preliminary analysis of the circulation path, the kernel density estimation algorithm is applied to estimate the probability density of the data of each performance node. Kernel density estimation is a non-parametric method for estimating the probability density function of a random variable, which can help understand the distribution of each node in the entire performance map. Through this analysis, the probability density estimate value of each performance node can be obtained, and then the potential fault nodes can be identified based on the preset probability density threshold. For example, if the probability density of a node is significantly lower than that of other nodes, this may indicate that the battery module corresponding to the node is abnormal. Next, for each circulation path, the correlation analysis of the circulation data is performed. This analysis is to identify the data correlation between different circulation paths, such as two paths may show similar abnormal patterns because they are connected to a poorly performing battery module. In this way, abnormal circulation data can be further identified, which usually points to potential problem areas in the battery pack. Finally, a fault data set is constructed based on at least one identified faulty node and the related abnormal circulation data. This data set combines all identified problems and anomalies, providing a clear direction for subsequent maintenance and repair. For example, if faulty nodes and abnormal circulating current data are concentrated in a specific battery module, this indicates that the module may need to be replaced or further inspected.

[0068] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0069] (1) Perform data analysis on the fault data set to obtain the fault frequency, fault duration, and fault severity;

[0070] (2) Generate fault cycle data through fault frequency and fault duration;

[0071] (3) Perform inspection frequency analysis based on fault cycle data and fault severity to obtain data inspection frequency;

[0072] (4) Analyze the fault type of the fault cycle data to obtain the fault type;

[0073] (5) Analyze the inspection data type of the fault type to obtain the inspection data type, and generate a data inspection strategy based on the inspection data type and data inspection frequency.

[0074] Specifically, first of all, the process starts with data analysis of the fault data set to obtain the frequency, duration and severity of the fault. This analysis process uses statistical methods, such as frequency distribution and time series analysis, to evaluate the frequency and duration of faults at different times and under different conditions. For example, if the data shows that the failure frequency of battery modules increases significantly under high temperature conditions, this indicates that temperature is a key influencing factor. Further, using the frequency and duration of faults, fault cycle data can be generated. These data reflect the regularity of faults within a certain time period and help predict the possible occurrence time of future faults. For example, if the analysis results show that a certain type of fault occurs once every month, then this periodicity is very obvious, and future inspection and maintenance time points can be set accordingly.

[0075] Based on the fault cycle data and the degree of fault, the inspection frequency is further analyzed. This step is to determine the inspection frequency by evaluating the severity of the fault and the cycle of occurrence. For example, for those fault types with short cycles and serious impacts, the inspection frequency will be increased to ensure that these faults can be discovered and handled in a timely manner. Conversely, for those faults with less impact or less frequency of occurrence, the inspection frequency can be reduced. Next, the fault type analysis is performed on the fault cycle data to clarify the specific categories of different faults. This step is achieved by in-depth mining of fault data, such as using classification algorithms to distinguish different types of faults, such as circuit short circuits, battery overheating, or battery capacity reduction. After identifying the specific fault type, inspection plans and maintenance strategies can be formulated more targeted.

[0076] Finally, the inspection data type is analyzed based on the identified fault type. The most appropriate monitoring and detection method is selected according to the different fault types. For example, for battery overheating, the inspection data type will include temperature monitoring and thermal imaging detection; while for circuit short circuit, the inspection data may focus on abnormal monitoring of current and voltage. Combining the inspection data type and inspection frequency, a comprehensive data inspection strategy is finally formed. This strategy not only customizes the inspection content according to the characteristics of the fault, but also arranges the inspection plan according to the cycle of the fault occurrence to ensure that it is both effective and economical.

[0077] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0078] (1) Extract data from the environmental data set to obtain map data, terrain data, obstacle data, and equipment distribution data corresponding to the target energy storage container;

[0079] (2) Generate a three-dimensional spatial coordinate system corresponding to the target energy storage container based on map data and terrain data;

[0080] (3) Based on the three-dimensional space coordinate system, the obstacle data and equipment distribution data are mapped to the three-dimensional space coordinate system to obtain the coordinate system to be analyzed;

[0081] (4) Collect temperature and humidity data of the target energy storage container to obtain temperature and humidity data;

[0082] (5) Dividing the coordinate system to be analyzed into dangerous areas based on the temperature data and the humidity data to obtain at least one dangerous area;

[0083] (6) An inspection path is constructed for the target energy storage container in the coordinate system to be analyzed through at least one dangerous area to obtain a target inspection path.

[0084] Specifically, first, by performing a detailed data extraction of the environmental data set, the map data, terrain data, obstacle data, and equipment distribution data of the location of the energy storage container can be obtained. This step is achieved by using a combination of a high-precision geographic information system (GIS) and on-site field surveys. For example, map data can be obtained through satellite images and existing geographic information databases, while terrain data is recorded in detail through topographic surveying technology, which is essential for understanding the physical environment in which the energy storage container is located. After obtaining these basic data, a corresponding three-dimensional spatial coordinate system is constructed based on the map and terrain data. This three-dimensional model can accurately reflect the location of the energy storage container and the specific layout of the surrounding environment, including any terrain undulations and obstacle distribution that may affect the inspection path. For example, through three-dimensional modeling, it can be clear which areas are difficult to access due to complex terrain or obstacles, and thus need to be considered in the inspection plan.

[0085] Next, based on this three-dimensional spatial coordinate system, the obstacle data and equipment distribution data are mapped to the coordinate system. This process involves accurately calibrating the location information of each physical entity in the three-dimensional model to ensure that all spatial relationships are accurately reflected in the virtual environment. Such mapping not only facilitates visual analysis, but also provides the necessary data basis for the generation of automated inspection paths. In addition, real-time collection of temperature and humidity of the target energy storage container is also an indispensable part of this process. By installing temperature and humidity sensors inside and outside the container, real-time data on environmental conditions can be obtained, which has an important impact on the analysis of battery operating efficiency and safety. For example, abnormal fluctuations in temperature and humidity may affect the chemical reaction rate and safety of the battery, and thus affect the stability of the entire energy storage system.

[0086] Based on the collected temperature and humidity data, the data in the three-dimensional coordinate system is further analyzed to divide the dangerous areas. This division is based on preset safety parameters, such as temperature and humidity thresholds, to identify areas that may pose a threat to the energy storage container. For example, if the temperature in a certain area continues to exceed the maximum safe temperature for battery operation, then this area will be classified as a high-risk area and requires special attention during inspection. Finally, through at least one of the divided dangerous areas, the inspection path is constructed for the target energy storage container in the coordinate system to be analyzed. This path construction takes into account all environmental factors and safety risks to ensure that the inspection robot or personnel can complete the inspection task in the safest and most effective way. For example, if the inspection path planning system finds that a path passes through a marked high-risk area, the system will automatically re-plan the path to avoid these areas, or add safety precautions when necessary.

[0087] In a specific embodiment, the process of executing the step of constructing an inspection path for a target energy storage container in the coordinate system to be analyzed may specifically include the following steps:

[0088] (1) matching the danger level of at least one danger zone to obtain the danger level corresponding to at least one danger zone;

[0089] (2) performing inspection priority analysis on at least one hazardous area based on the degree of danger corresponding to the at least one hazardous area to obtain a priority list;

[0090] (3) The inspection path of the target energy storage container in the coordinate system to be analyzed is constructed through the priority list to obtain the target inspection path.

[0091] It should be noted that, first of all, the process of matching the danger level of dangerous areas involves evaluating the risk level of each area using pre-defined criteria. These criteria may include temperature, humidity, battery performance data sets, and historical fault data. For example, if the temperature of an area continuously exceeds the safety threshold, the area will be marked as a high danger level. Similarly, if battery performance degradation is frequently recorded in a certain area, this will also increase the risk level of the area. After determining at least one dangerous area and its corresponding danger level, the next step is to perform inspection priority analysis on the dangerous areas based on these danger levels. This analysis takes into account the risk level of each dangerous area and combines other factors such as the availability of inspection resources and historical inspection data to determine the inspection priority of each area. For example, an area with both high temperature records and battery performance problems will be given a higher priority because it indicates that the area may pose a greater threat to the safety and stability of the energy storage system. Based on the determined priority list, the next step is to construct the inspection path for the target energy storage container in the coordinate system to be analyzed. This process requires not only considering the priority of each area, but also the feasibility and efficiency of physical access. For example, even if an area has a high risk level, if it is located in a complex terrain or difficult to access location, the design of the inspection route must consider how to reach the area safely and efficiently. Using advanced routing algorithms, the inspection route can be optimized to ensure that each hazardous area is properly inspected while maximizing the overall efficiency of the inspection process. In addition, combining this method with the battery surface defect detection method based on image processing can further improve the accuracy and effectiveness of the inspection. For example, the use of image processing technology can identify and record cracks, leaks or other visual defects on the battery surface in real time during the inspection process. These image data can be analyzed in real time or uploaded to a central database for more in-depth analysis. This not only enables a rapid response to hazardous areas, but also provides detailed data support to improve future inspection activities and safety strategies.

[0092] The embodiment of the present invention also provides a safety inspection system for energy storage containers, such as Figure 2 As shown, the energy storage container safety inspection system specifically includes:

[0093] The first acquisition module 201 is used to collect data from the target energy storage container to obtain a battery performance data set, wherein the battery performance data set includes: voltage data, battery data and circulating current data;

[0094] A first construction module 202, configured to construct an energy storage performance map of the target energy storage container according to the battery performance data set;

[0095] An identification module 203 is used to perform fault identification on the energy storage performance map by using a clustering detection algorithm to obtain a fault data set;

[0096] The second acquisition module 204 is used to collect environmental data of the target energy storage container to obtain an environmental data set;

[0097] A generating module 205, configured to generate a data inspection strategy based on the fault data set, wherein the data inspection strategy includes a data inspection frequency and an inspection data type;

[0098] A second construction module 206 is used to construct an inspection path for a preset inspection robot based on the environmental data set to obtain a target inspection path;

[0099] The inspection module 207 is used to control the inspection robot to perform an environmental safety inspection on the target energy storage container through the target inspection path, and at the same time, perform a data safety inspection on the target energy storage container through the data inspection strategy.

[0100] Through the collaborative work of the above modules, the energy storage container is comprehensively collected, including voltage, current, circulating current and other data, and the working status and environmental conditions of the battery are monitored in real time, which not only improves the comprehensiveness of data collection, but also ensures the reliability and accuracy of the data through precise monitoring. Secondly, the construction of energy storage performance maps and the use of clustering detection algorithms for fault identification can effectively identify potential faults and anomalies from a large amount of performance data, which not only improves the accuracy of fault detection, but also greatly reduces the maintenance costs and potential safety risks caused by faults. In addition, the data inspection strategy generated based on the fault data set and the use of the environmental data set further optimizes the path planning of the inspection robot, which not only improves the inspection efficiency, but also ensures the safety and stability of the system during the inspection process. Through this inspection method, the energy storage container can be managed more accurately and scientifically, thereby extending the battery life and optimizing energy utilization efficiency. More importantly, the solution also takes into account the impact of environmental factors on battery performance. By analyzing environmental data such as temperature and humidity, the inspection strategy can be adjusted in real time to further improve the adaptability and robustness of the inspection process.

[0101] The above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the same. Although the present invention has been described in detail with reference to the embodiments, a person skilled in the art should understand that the specific implementation modes of the present invention can still be modified or replaced by equivalents, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A method for safety inspection of energy storage containers, characterized in that: include: The target energy storage container is subjected to data collection to obtain a battery performance data set, specifically comprising: positioning and configuring a voltage sensor of the target energy storage container to obtain a voltage sensor layout plan; positioning and configuring a current sensor of the target energy storage container to obtain a current sensor layout plan; constructing a sensor network based on the voltage sensor layout plan and the current sensor layout plan; performing data collection on the target energy storage container through the sensor network to obtain initial voltage data and initial current data; performing time synchronization on the initial voltage data and the initial current data to obtain voltage data and battery data; performing circulating current detection on multiple battery modules in the target energy storage container to obtain initial circulating current data; and timestamping the initial circulating current data to obtain circulating current data; Constructing the energy storage performance map of the target energy storage container according to the battery performance data set, specifically comprising: performing a battery module-based performance data clustering analysis on the battery performance data set to obtain a plurality of groups of sub-performance data corresponding to the battery performance data set; performing a time series analysis on each group of sub-performance data to obtain an energy storage decay trend corresponding to the target energy storage container; performing feature extraction on each group of sub-performance data based on the energy storage decay trend to obtain an energy storage load capacity and a circulation level; constructing a performance map of the battery performance data set according to the energy storage load capacity and the circulation level to obtain the energy storage performance map; Fault identification is performed on the energy storage performance map by a clustering detection algorithm to obtain a fault data set, which specifically includes: identifying performance nodes on the energy storage performance map to obtain multiple performance nodes; matching the performance data of each performance node respectively, and performing circulation path analysis on the multiple performance nodes to obtain multiple circulation paths; performing probability density estimation on the performance data of each performance node by a kernel density estimation algorithm to obtain a probability density estimation value corresponding to each performance node; based on a preset probability density threshold, performing fault node identification on the probability density estimation value corresponding to each performance node respectively to obtain at least one fault node; performing circulation data correlation analysis on each circulation path to obtain circulation correlation data between every two circulation paths; performing circulation data anomaly identification on each circulation path respectively through the circulation correlation data between every two circulation paths to obtain abnormal circulation data; constructing fault data based on the at least one fault node and the abnormal circulation data to obtain the fault data set; Collecting environmental data of the target energy storage container to obtain an environmental data set; Generate a data inspection strategy based on the fault data set, wherein the data inspection strategy includes a data inspection frequency and an inspection data type; Based on the environmental data set, an inspection path is constructed for a preset inspection robot to obtain a target inspection path, specifically comprising: extracting data from the environmental data set to obtain map data, terrain data, obstacle data, and equipment distribution data corresponding to the target energy storage container; generating a three-dimensional space coordinate system corresponding to the target energy storage container according to the map data and the terrain data; based on the three-dimensional space coordinate system, mapping the obstacle data and the equipment distribution data to the three-dimensional space coordinate system to obtain a coordinate system to be analyzed; collecting temperature and humidity of the target energy storage container to obtain temperature data and humidity data; dividing the coordinate system to be analyzed into dangerous areas based on the temperature data and the humidity data to obtain at least one dangerous area; constructing an inspection path for the target energy storage container in the coordinate system to be analyzed through at least one dangerous area to obtain the target inspection path; The inspection robot is controlled through the target inspection path to perform an environmental safety inspection on the target energy storage container, and at the same time, a data safety inspection is performed on the target energy storage container through the data inspection strategy.

2. The energy storage container safety inspection method according to claim 1 is characterized in that: The generating of a data inspection strategy based on the fault data set, wherein the data inspection strategy includes a data inspection frequency and an inspection data type, including: Performing data analysis on the fault data set to obtain fault frequency, fault duration, and fault severity; Generate fault cycle data by using the fault occurrence frequency and the fault duration; Perform inspection frequency analysis based on the fault cycle data and the fault degree to obtain the data inspection frequency; Performing fault type analysis on the fault cycle data to obtain the fault type; An inspection data type analysis is performed on the fault type to obtain the inspection data type, and the data inspection strategy is generated according to the inspection data type and the data inspection frequency.

3. The energy storage container safety inspection method according to claim 1 is characterized in that: The step of constructing an inspection path for the target energy storage container in the coordinate system to be analyzed through at least one dangerous area to obtain the target inspection path includes: Performing danger level matching on at least one danger zone to obtain a danger level corresponding to the at least one danger zone; Performing inspection priority analysis on the at least one dangerous area based on the degree of danger corresponding to the at least one dangerous area to obtain a priority list; An inspection path is constructed for the target energy storage container in the coordinate system to be analyzed using the priority list to obtain the target inspection path.

4. A safety inspection system for energy storage containers, used to execute the safety inspection method for energy storage containers according to any one of claims 1 to 3, characterized in that: include: The first acquisition module is used to collect data from the target energy storage container to obtain a battery performance data set, specifically including: positioning and configuring the voltage sensor of the target energy storage container to obtain a voltage sensor layout plan; positioning and configuring the current sensor of the target energy storage container to obtain a current sensor layout plan; building a sensor network based on the voltage sensor layout plan and the current sensor layout plan; collecting data from the target energy storage container through the sensor network to obtain initial voltage data and initial current data; performing time synchronization on the initial voltage data and the initial current data to obtain voltage data and battery data; performing circulating current detection on multiple battery modules in the target energy storage container to obtain initial circulating current data; and timestamping the initial circulating current data to obtain circulating current data; The first construction module is used to construct the energy storage performance map of the target energy storage container according to the battery performance data set, specifically including: performing a battery module-based performance data clustering analysis on the battery performance data set to obtain multiple groups of sub-performance data corresponding to the battery performance data set; performing a time series analysis on each group of sub-performance data to obtain an energy storage decay trend corresponding to the target energy storage container; based on the energy storage decay trend, performing feature extraction on each group of sub-performance data to obtain an energy storage load capacity and a circulation level; and constructing a performance map of the battery performance data set according to the energy storage load capacity and the circulation level to obtain the energy storage performance map; An identification module is used to perform fault identification on the energy storage performance map through a clustering detection algorithm to obtain a fault data set, specifically including: performing performance node identification on the energy storage performance map to obtain multiple performance nodes; matching the performance data of each performance node respectively, and performing circulation path analysis on the multiple performance nodes to obtain multiple circulation paths; performing probability density estimation on the performance data of each performance node through a kernel density estimation algorithm to obtain a probability density estimation value corresponding to each performance node; based on a preset probability density threshold, performing fault node identification on the probability density estimation value corresponding to each performance node respectively to obtain at least one fault node; performing circulation data correlation analysis on each circulation path to obtain circulation correlation data between every two circulation paths; performing circulation data anomaly identification on each circulation path respectively through the circulation correlation data between every two circulation paths to obtain abnormal circulation data; constructing fault data based on the at least one fault node and the abnormal circulation data to obtain the fault data set; A second acquisition module is used to collect environmental data of the target energy storage container to obtain an environmental data set; A generating module, configured to generate a data inspection strategy based on the fault data set, wherein the data inspection strategy includes a data inspection frequency and an inspection data type; The second construction module is used to construct an inspection path for a preset inspection robot based on the environmental data set to obtain a target inspection path, specifically comprising: extracting data from the environmental data set to obtain map data, terrain data, obstacle data, and equipment distribution data corresponding to the target energy storage container; generating a three-dimensional space coordinate system corresponding to the target energy storage container according to the map data and the terrain data; mapping the obstacle data and the equipment distribution data to the three-dimensional space coordinate system based on the three-dimensional space coordinate system to obtain a coordinate system to be analyzed; collecting temperature and humidity of the target energy storage container to obtain temperature data and humidity data; dividing the coordinate system to be analyzed into dangerous areas based on the temperature data and the humidity data to obtain at least one dangerous area; constructing an inspection path for the target energy storage container in the coordinate system to be analyzed through at least one dangerous area to obtain the target inspection path; The inspection module is used to control the inspection robot to perform an environmental safety inspection on the target energy storage container through the target inspection path, and at the same time, to perform a data safety inspection on the target energy storage container through the data inspection strategy.