Energy storage system status monitoring method based on multi-type energy storage sensors

Abstract

The present invention relates to the technical field of energy storage systems, and specifically to a method for monitoring the state of an energy storage system based on multiple types of energy storage sensors, comprising: collecting monitoring data of multiple types of energy storage sensors at the same sampling time point; inputting the monitoring data into a preset classification network, and determining abnormal data according to the judgment conditions in the classification network; determining the abnormal state level of the energy storage system according to the abnormal data and the abnormal level algorithm; wherein the judgment conditions in the classification network are set according to the historical data of multiple types of energy storage sensors. The present invention uses the original historical data of multiple types of energy storage sensors to set judgment conditions, which can fully consider the characteristics and data distribution of different types of sensors, making the judgment conditions more scientific and reasonable, thereby improving the accuracy of abnormal data judgment. After determining the abnormal data through the classification algorithm, the abnormal state level of the energy storage system is determined in combination with the abnormal level algorithm, so that the severity of the abnormality can be intuitively understood and corresponding decisions can be made.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage systems, and in particular to a method for monitoring the state of an energy storage system based on multiple types of energy storage sensors. Background Art

[0002] With the continuous development of the energy sector and the growing demand for energy storage systems, it has become crucial to ensure the safe and stable operation of energy storage systems.

[0003] In today's society, the storage and efficient use of energy have become key issues. Energy storage systems play an important role in the power sector. They can balance the supply and demand of the power grid and improve the stability and reliability of the power system. In the field of new energy, such as the development of renewable energy such as solar energy and wind energy, energy storage systems can solve the problems of intermittency and instability and achieve continuous and stable energy supply. However, due to the complexity of energy storage systems and the diversity of their operating environments, accurate monitoring of their status faces many challenges.

[0004] Traditional energy storage system status monitoring methods often rely on a single type of sensor, which has obvious limitations. A single type of sensor can only obtain specific information, making it difficult to fully and accurately reflect the overall status of the energy storage system, thereby increasing the risk of system abnormalities and being unable to know the abnormality level after an abnormality occurs. Summary of the invention

[0005] (I) Purpose of the invention

[0006] The purpose of the present invention is to provide a method for monitoring the state of an energy storage system based on multiple types of energy storage sensors, which can improve the accuracy of abnormal data judgment and reflect the state of the energy storage system at a specific moment.

[0007] (II) Technical solution

[0008] To solve the above problems, the present invention provides a method for monitoring the state of an energy storage system based on multiple types of energy storage sensors, comprising:

[0009] Collect monitoring data of multiple types of energy storage sensors at the same sampling time point;

[0010] Inputting the monitoring data into a preset classification network, and determining abnormal data according to the judgment conditions in the classification network;

[0011] Determine the abnormal state level of the energy storage system according to the abnormal data and the abnormal level algorithm;

[0012] Wherein, the judgment conditions in the classification network are set according to the historical data of multiple types of energy storage sensors.

[0013] In another aspect of the present invention, preferably,

[0014] The preset classification network includes a primary node, a connection path and a secondary node, the primary node and the secondary node are connected by the connection path, and the connection path represents the operation relationship between the data of a plurality of primary nodes and the data of the secondary nodes;

[0015] The first-level node stores historical data of various types of energy storage sensors;

[0016] The data of several first-level nodes are connected through path calculation to obtain the data of the second-level nodes.

[0017] In another aspect of the present invention, preferably,

[0018] The judgment conditions in the classification network are set according to the historical data of multiple types of energy storage sensors, including:

[0019] The primary node stores historical data corresponding to the energy storage sensor;

[0020] Determine the safety threshold of the primary node according to the historical data;

[0021] Using the historical data and connection paths, the original data of the secondary node is calculated;

[0022] Determining a safety threshold of the secondary node according to the original data;

[0023] When both the primary node and the secondary node meet the corresponding safety threshold, the output classification result is normal data;

[0024] When at least one of the primary node and the secondary node does not meet the corresponding safety threshold, the output classification result is abnormal data.

[0025] In another aspect of the present invention, preferably,

[0026] The energy storage sensor includes: a temperature sensor and a current sensor;

[0027] The temperature sensor and the current sensor are primary nodes;

[0028] The temperature sensor is used to monitor the temperature of the energy storage system, and the current sensor is used to monitor the current of the energy storage system;

[0029] The data of the temperature sensor and the current sensor are connected through a path operation to obtain thermal barrier data, which is a secondary node.

[0030] In another aspect of the present invention, preferably,

[0031] The operation of the connection path of the thermal barrier data includes:

[0032] N=m·c·T 温 +I 2 R

[0033] Where N represents the thermal barrier data, m represents the mass of the energy storage system, c represents the specific heat capacity of the energy storage system, and T 温 represents the monitoring data of the temperature sensor, R represents the internal resistance of the energy storage system, and I represents the monitoring data of the current sensor.

[0034] In another aspect of the present invention, preferably,

[0035] The energy storage sensor includes: a wind direction sensor, a wind speed sensor and a flow sensor;

[0036] The wind direction sensor, wind speed sensor and flow sensor are primary nodes;

[0037] The wind direction sensor is used to monitor the wind direction of the natural wind, the wind speed sensor is used to monitor the wind speed of the natural wind, and the flow sensor is used to monitor the gas flow at the air inlet of the energy storage system;

[0038] The data of the wind direction sensor, wind speed sensor and flow sensor are connected through path calculation to obtain the location data of the pollutants, and the location data of the pollutants is a secondary node.

[0039] In another aspect of the present invention, preferably,

[0040] The calculation of the connection path of the location data of the pollutants includes:

[0041]

[0042] Among them, F(t) represents the location data of the pollutant at time t, F0 represents the location information of the energy storage system, is the diffusion velocity vector caused by natural wind, is the diffusion velocity vector caused by the energy storage system.

[0043] In another aspect of the present invention, preferably,

[0044] The calculation of the connection path of the location data of the pollutants includes:

[0045]

[0046] in, is the diffusion velocity vector caused by the energy storage system, G1 is the monitoring data of the flow sensor, G is the historical data of the flow sensor, and v 预 is the preset diffusion velocity vector, that is, the diffusion velocity vector when the data of the flow sensor is G, is the diffusion velocity vector caused by natural wind, V1 represents the monitoring data of the wind speed sensor, and θ represents the monitoring data of the wind direction sensor, which is the angle measured clockwise from the north direction.

[0047] In another aspect of the present invention, preferably,

[0048] The abnormal level algorithm uses the following formula to calculate the abnormal status level of thermal fault:

[0049]

[0050] Among them, r 热 represents the abnormal level of thermal fault, N represents the thermal barrier data, N0 represents the original data of the thermal barrier data, γ represents the empirical parameter, B represents the surface area of ​​the energy storage system, k represents the thermal conductivity of the energy storage system, and h represents the convection heat transfer coefficient between the energy storage system and the surrounding objects.

[0051] In another aspect of the present invention, preferably,

[0052] The abnormal level algorithm uses the following formula to calculate the pollution abnormal state level:

[0053]

[0054] Among them, r 污 represents the abnormal pollution state level, F(t) represents the location of the pollutant at time t, F0 represents the location information of the energy storage system, and S0 represents the original data of the pollution area.

[0055] (III) Beneficial effects

[0056] The above technical solution of the present invention has the following beneficial technical effects:

[0057] The present invention uses the historical data of multiple types of energy storage sensors to set the judgment conditions, which can fully consider the characteristics and data distribution of different types of sensors, making the judgment conditions more scientific and reasonable, thereby improving the accuracy of abnormal data judgment. After determining the abnormal data through the classification network, the abnormal state level of the energy storage system is determined in combination with the abnormal level algorithm, which can intuitively understand the severity of the abnormality and make corresponding decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is an overall flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0060] Obviously, the described embodiments are only some embodiments of the present invention, but not all 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.

[0061] In the description of the present invention, it should be noted that the terms “first”, “second” and “third” are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0062] 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.

[0063] Embodiment 1

[0064] A method for monitoring the state of an energy storage system based on multiple types of energy storage sensors. Figure 1 FIG. 1 shows an overall flow chart of an embodiment of the present invention, as shown in FIG. Figure 1 As shown, including:

[0065] Collect monitoring data from multiple types of energy storage sensors at the same sampling time point; Collect monitoring data from multiple types of energy storage sensors at the same sampling time point. This ensures that the data from different types of sensors reflect the state of the energy storage system at the same time, avoiding inconsistent and inaccurate data due to time differences.

[0066] The monitoring data is input into a preset classification network, and abnormal data is determined according to the judgment conditions in the classification network. The specific content of the classification network is not limited here, and those skilled in the art can understand that as long as the monitoring data can be classified, the classification results include abnormal data and normal data.

[0067] In this embodiment, the preset classification network includes primary nodes, connection paths and secondary nodes, and the primary nodes, connection paths and secondary nodes together constitute a hierarchical architecture system. The primary nodes are at a relatively basic level, and they are like "containers" for data storage, each of which is responsible for storing historical data collected by various types of energy storage sensors. These energy storage sensors may cover a variety of different application scenarios and technical principles, such as lithium-ion battery sensors and flow battery sensors commonly used in power energy storage systems, or corresponding sensors in other related fields such as thermal energy storage and mechanical energy storage. The various parameter data recorded by them during the past operation process will be classified and placed in the corresponding primary nodes.

[0068] The primary nodes and the secondary nodes are connected via a connection path, and the connection path represents a computational relationship between data of a plurality of primary nodes and data of a secondary node;

[0069] The first-level node stores historical data of various types of energy storage sensors;

[0070] The data of several first-level nodes are connected through path calculation to obtain the data of the second-level nodes.

[0071] The connection path is not just a simple physical connection between the primary node and the secondary node. More importantly, it defines a specific operation relationship. The operation relationship clarifies how to integrate, process and convert the data stored in several primary nodes so as to obtain the data content required by the secondary node. For example, the operation relationship specified by the connection path may involve a variety of mathematical or logical processing methods such as weighted summation, proportional operation, logical judgment combination, etc. The purpose is to extract more comprehensive secondary node data that can better reflect a certain specific feature or state from a large number of basic primary node data based on different business needs and data association logic. The secondary nodes are located at a relatively high level, and the data they carry is the result of complex operations on the primary node data through the connection path. The data of these secondary nodes often have a higher level of meaning and can be used to describe, analyze and support decisions on the entire energy storage system or related energy storage phenomena at a more macro and abstract level. For example, it can represent the overall health status score of the energy storage system at a certain stage.

[0072] In this embodiment, the energy storage sensor includes: a temperature sensor and a current sensor;

[0073] The temperature sensor and the current sensor are primary nodes; the temperature sensor is used to monitor the temperature of the energy storage system, and the current sensor is used to monitor the current of the energy storage system;

[0074] In the energy storage system monitoring system of this embodiment, the temperature sensor and the current sensor play a basic data collection role as the first-level nodes. The temperature sensor monitors the temperature of the energy storage system in real time, and the temperature data obtained can intuitively reflect the current thermal fault state of the energy storage system. For example, in a lithium-ion battery energy storage system, excessively high temperatures may indicate problems such as intensified chemical reactions inside the battery and poor heat dissipation, and the temperature values ​​continuously recorded by the temperature sensor become the key basis for subsequent analysis. The current sensor is responsible for monitoring the current of the energy storage system, and the current data it collects is also indispensable for evaluating the working state of the energy storage system. At the same time, it is also used to evaluate the thermal fault state of the energy storage system.

[0075] The data of the temperature sensor and the current sensor are connected through a path operation to obtain thermal barrier data, which is a secondary node.

[0076] The operation of the connection path of the thermal barrier data includes:

[0077] N=m·c·T 温 +I 2 R

[0078] Where N represents the thermal barrier data, m represents the mass of the energy storage system, c represents the specific heat capacity of the energy storage system, and T 温 represents the monitoring data of the temperature sensor, R represents the internal resistance of the energy storage system, and I represents the monitoring data of the current sensor. The mass and specific heat capacity of the energy storage system are parameters related to the characteristics of the energy storage system itself. Multiplying them with the temperature data monitored by the temperature sensor reflects the thermal energy accumulation inside the energy storage system in the previous period of time. In the energy storage system, when current flows through a part with a certain internal resistance, heat will inevitably be generated, and future heat can be estimated. The two parts of heat are added together to generate thermal barrier data, making it more scientific and reasonable to judge whether the monitoring data is abnormal.

[0079] In this embodiment, further, the energy storage sensor includes: a wind direction sensor, a wind speed sensor and a flow sensor;

[0080] The wind direction sensor, wind speed sensor and flow sensor are primary nodes;

[0081] The wind direction sensor is used to monitor the direction of the natural wind, the wind speed sensor is used to monitor the speed of the natural wind, and the flow sensor is used to monitor the gas flow at the air inlet of the energy storage system; the wind direction sensor, wind speed sensor and flow sensor are used as first-level nodes, which respectively monitor the wind direction and wind speed of the natural wind and the gas flow at the air inlet of the energy storage system, and are the basis for the subsequent calculation of pollutant location data.

[0082] The data of the wind direction sensor, wind speed sensor and flow sensor are connected through the operation of the path to obtain the location data of the pollutant, which is a secondary node. The secondary node here represents the location data of the pollutant, which is obtained by the data of the primary node through the specific operation of the connection path.

[0083] The calculation of the connection path of the location data of the pollutants includes:

[0084]

[0085] Among them, F(t) represents the location data of the pollutant at time t, F0 represents the location information of the energy storage system, is the diffusion velocity vector caused by natural wind, It is the diffusion velocity vector caused by the energy storage system. The calculation process combines the diffusion velocity vector caused by the influence of natural wind and the operation of the energy storage system itself, so that the diffusion position of pollutants can be calculated more accurately.

[0086] The calculation of the connection path of the location data of the pollutants also includes:

[0087]

[0088] in, is the diffusion velocity vector caused by the energy storage system, G1 is the monitoring data of the flow sensor, G is the historical data of the flow sensor, and v 预 is the preset diffusion velocity vector, that is, the diffusion velocity vector when the data of the flow sensor is G, is the diffusion velocity vector caused by natural wind, V1 represents the monitoring data of the wind speed sensor, and θ represents the monitoring data of the wind direction sensor, which is the angle measured clockwise from the north direction. For the diffusion velocity vector caused by the energy storage system, the monitoring data of the flow sensor reflects the gas flow at the current air inlet of the energy storage system, while the historical data G provides historical flow information for comparison and trend analysis. The preset diffusion velocity vector is a baseline diffusion velocity when the flow sensor data is G. By comparing the relationship between the monitoring data G1 and the historical data G and the preset diffusion velocity vector, the diffusion velocity vector caused by the change in the current air intake state of the energy storage system can be accurately determined, thereby improving accuracy.

[0089] According to the abnormal data and the abnormal level algorithm, the abnormal state level of the energy storage system is determined; according to the abnormal data and the abnormal level algorithm, the abnormal state level of the energy storage system is determined. The abnormal level can intuitively understand the possible impact of the abnormal data, and divide the abnormal state of the energy storage system into different levels, such as mild abnormality, moderate abnormality, severe abnormality, etc. Different abnormal state levels correspond to different treatment measures and urgency.

[0090] Among them, the judgment conditions in the classification network are set according to the historical data of multiple types of energy storage sensors. Multiple types of energy storage sensors can monitor the energy storage system from different angles and aspects. For example, temperature sensors can monitor the temperature changes of the energy storage system, voltage sensors can monitor the voltage fluctuations of the system, and current sensors can detect the magnitude of the current. Historical data is a collection of data collected by multiple types of sensors in the normal operation and various abnormal conditions of the energy storage system over a period of time in the past. By using these historical data, the distribution characteristics, change patterns and mutual relationships of different types of sensor data can be analyzed. Based on this, the judgment conditions in the preset classification network can be set. The judgment condition can be a numerical range threshold determined based on statistical methods.

[0091] In this embodiment, the judgment conditions in the classification network are set according to the historical data of multiple types of energy storage sensors, including:

[0092] The primary node stores historical data corresponding to the energy storage sensor;

[0093] Determine the safety threshold of the primary node based on the historical data; take the current sensor as an example, through in-depth analysis of its historical data, such as statistically analyzing the maximum, minimum, average value of the current during normal operation and the fluctuation range under different working conditions, comprehensively consider the design specifications, safety standards and long-term operation stability requirements of the energy storage system, so as to set a suitable safety threshold. Assuming that the current of a certain energy storage system is usually between 10A and 50A during normal operation, combined with the system's ability to withstand current overloads and a certain safety margin, the safety threshold of the primary node of the current sensor may be set to 60A. In this way, when the current data monitored in real time exceeds 60A, it may indicate that there is an abnormal risk in the system.

[0094] Using the historical data and connection paths, the original data of the secondary node is calculated;

[0095] According to the original data, the safety threshold of the secondary node is determined; for example, the historical data of the temperature sensor and the current sensor are calculated according to the above calculation formula to obtain the secondary node original data reflecting the thermal barrier state. A reasonable safety threshold is set based on the original data obtained by calculating the historical data under the past safety state.

[0096] When both the primary node and the secondary node meet the corresponding safety threshold, the output classification result is normal data; when at least one of the primary node and the secondary node does not meet the corresponding safety threshold, the output classification result is abnormal data. In the real-time monitoring process, when both the primary node and the secondary node meet their corresponding safety thresholds, the system outputs the classification result as normal data, which indicates that the energy storage system is in a safe and stable normal operating range at the current moment, whether it is the local state reflected by each basic sensor or the overall performance state after integrated analysis. On the contrary, when at least one of the primary node and the secondary node does not meet the corresponding safety threshold, the output classification result is abnormal data.

[0097] In this embodiment, further, the abnormal level algorithm uses the following formula to calculate the abnormal state level of the thermal fault:

[0098]

[0099] Among them, r 热 Represents the abnormal level of thermal fault, N represents thermal barrier data, N0 represents the original data of thermal barrier data, γ represents the empirical parameter, B represents the surface area of ​​the energy storage system, k represents the thermal conductivity of the energy storage system, and h represents the convective heat transfer coefficient between the energy storage system and the surrounding objects. The thermal barrier data is obtained by connecting the data of the temperature sensor, current sensor and other data mentioned above through the connection path operation, which reflects the current thermal condition and potential thermal risk level of the energy storage system. The original data of the thermal barrier data is a benchmark value, which is used to compare the change range of the current thermal barrier data. This embodiment also comprehensively considers factors such as the material properties and structural characteristics of the energy storage system and the laws of thermal failures in similar systems in the past, and plays a role in correcting and adjusting the calculation of the abnormal level of thermal faults, so that the calculation results are more in line with the actual situation.

[0100] In this embodiment, further, the abnormal level algorithm uses the following formula to calculate the pollution abnormal state level:

[0101]

[0102] Among them, r 污 represents the level of abnormal pollution state, F(t) represents the location of the pollutant at time t, F0 represents the location information of the energy storage system, and S0 represents the raw data of the pollution area. S0 is the raw data of the pollution area, which can reflect the degree of pollution diffusion when compared with the current pollution area. For example, if the calculated abnormal pollution state level is high, it means that the location of the pollutant is far away from the energy storage system and the pollution area has increased significantly, which may affect the environment and personnel in a wider area. This requires timely measures to initiate pollution control plans to reduce pollution hazards.

[0103] The present invention uses the historical data of multiple types of energy storage sensors to set the judgment conditions, which can fully consider the characteristics and data distribution of different types of sensors, making the judgment conditions more scientific and reasonable, thereby improving the accuracy of abnormal data judgment. After determining the abnormal data through the classification network, the abnormal state level of the energy storage system is determined in combination with the abnormal level algorithm, which can intuitively understand the severity of the abnormality and make corresponding decisions.

[0104] It should be understood that the above specific embodiments of the present invention are only used to illustrate or explain the principles of the present invention, and do not constitute a limitation of the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all changes and modifications that fall within the scope and boundaries of the appended claims, or the equivalent forms of such scope and boundaries.

[0105] The present invention has been described above with reference to the embodiments of the present invention. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present invention. The scope of the present invention is defined by the appended claims and their equivalents. Without departing from the scope of the present invention, a person skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

[0106] Although the embodiments of the present invention have been described in detail, it should be understood that the various changes, substitutions, and alterations could be made hereto without departing from the spirit and scope of the invention.

[0107] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.

Claims

1. A method for monitoring the state of an energy storage system based on multiple types of energy storage sensors, characterized in that: include: Collect monitoring data of multiple types of energy storage sensors at the same sampling time point; Inputting the monitoring data into a preset classification network, and determining abnormal data according to the judgment conditions in the classification network; Determine the abnormal state level of the energy storage system according to the abnormal data and the abnormal level algorithm; Wherein, the judgment conditions in the classification network are set according to the historical data of multiple types of energy storage sensors.

2. The method for monitoring the state of an energy storage system based on multiple types of energy storage sensors according to claim 1, characterized in that: The preset classification network includes a primary node, a connection path and a secondary node, the primary node and the secondary node are connected by the connection path, and the connection path represents the operation relationship between the data of a plurality of primary nodes and the data of the secondary nodes; The first-level node stores historical data of various types of energy storage sensors; The data of several first-level nodes are connected through path calculation to obtain the data of the second-level nodes.

3. The method for monitoring the state of an energy storage system based on multiple types of energy storage sensors according to claim 2, characterized in that: The judgment conditions in the classification network are set according to the historical data of multiple types of energy storage sensors, including: The primary node stores historical data corresponding to the energy storage sensor; Determine the safety threshold of the primary node according to the historical data; Using the historical data and connection paths, the original data of the secondary node is calculated; Determining a safety threshold of the secondary node according to the original data; When both the primary node and the secondary node meet the corresponding safety threshold, the output classification result is normal data; When at least one of the primary node and the secondary node does not meet the corresponding safety threshold, the output classification result is abnormal data.

4. The method for monitoring the state of an energy storage system based on multiple types of energy storage sensors according to claim 3 is characterized in that: The energy storage sensor includes: a temperature sensor and a current sensor; The temperature sensor and the current sensor are primary nodes; The temperature sensor is used to monitor the temperature of the energy storage system, and the current sensor is used to monitor the current of the energy storage system; The data of the temperature sensor and the current sensor are connected through a path operation to obtain thermal barrier data, which is a secondary node.

5. The method for monitoring the state of an energy storage system based on multiple types of energy storage sensors according to claim 4, characterized in that: The operation of the connection path of the thermal barrier data includes: N=m·c·T 温 +I 2 R Where N represents the thermal barrier data, m represents the mass of the energy storage system, c represents the specific heat capacity of the energy storage system, and T 温 represents the monitoring data of the temperature sensor, R represents the internal resistance of the energy storage system, and I represents the monitoring data of the current sensor.

6. The method for monitoring the state of an energy storage system based on multiple types of energy storage sensors according to claim 3, characterized in that: The energy storage sensor includes: a wind direction sensor, a wind speed sensor and a flow sensor; The wind direction sensor, wind speed sensor and flow sensor are primary nodes; The wind direction sensor is used to monitor the wind direction of the natural wind, the wind speed sensor is used to monitor the wind speed of the natural wind, and the flow sensor is used to monitor the gas flow at the air inlet of the energy storage system; The data of the wind direction sensor, wind speed sensor and flow sensor are connected through path calculation to obtain the location data of the pollutants, and the location data of the pollutants is a secondary node.

7. The method for monitoring the state of an energy storage system based on multiple types of energy storage sensors according to claim 6, characterized in that: The calculation of the connection path of the location data of the pollutants includes: Among them, F(t) represents the location data of the pollutant at time t, F0 represents the location information of the energy storage system, is the diffusion velocity vector caused by natural wind, is the diffusion velocity vector caused by the energy storage system.

8. The method for monitoring the state of an energy storage system based on multiple types of energy storage sensors according to claim 7, characterized in that: The calculation of the connection path of the location data of the pollutants includes: in, is the diffusion velocity vector caused by the energy storage system, G1 is the monitoring data of the flow sensor, G is the historical data of the flow sensor, and v 预 is the preset diffusion velocity vector, that is, the diffusion velocity vector when the data of the flow sensor is G, is the diffusion velocity vector caused by natural wind, V1 represents the monitoring data of the wind speed sensor, and θ represents the monitoring data of the wind direction sensor, which is the angle measured clockwise from the north direction.

9. The method for monitoring the state of an energy storage system based on multiple types of energy storage sensors according to claim 5, characterized in that: The abnormal level algorithm uses the following formula to calculate the abnormal status level of thermal fault: Among them, r 热 represents the abnormal level of thermal fault, N represents the thermal barrier data, N0 represents the original data of the thermal barrier data, γ represents the empirical parameter, B represents the surface area of ​​the energy storage system, k represents the thermal conductivity of the energy storage system, and h represents the convection heat transfer coefficient between the energy storage system and the surrounding objects.

10. The method for monitoring the state of an energy storage system based on multiple types of energy storage sensors according to claim 7, characterized in that: The abnormal level algorithm uses the following formula to calculate the pollution abnormal state level: Among them, r 污 represents the abnormal pollution state level, F(t) represents the location of the pollutant at time t, F0 represents the location information of the energy storage system, and S0 represents the original data of the pollution area.

Images