Electrochemical energy storage system early warning method, safety control method, device and equipment

Abstract

The invention discloses an early warning method, a safety control method, a safety control device and equipment for an electrochemical energy storage system. The method comprises the following steps: acquiring the battery cell temperature and the battery cell voltage of each battery cell to be detected; according to the battery cell temperature and the battery cell voltage, obtaining a plurality of characteristic quantities of each to-be-measured battery cell; based on the thermal runaway boundary conditions, the multiple characteristic quantities are combined and judged, early warning information is obtained, and the early warning information is used for indicating the thermal runaway state of the electrochemical energy storage system. The multiple characteristic quantities and the thermal runaway boundary conditions are used for combined judgment, accurate early warning of thermal runaway can be conducted on the electrochemical energy storage system, and the safety and reliability of the system are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy storage systems, and specifically relates to an early warning method, a safety control method, a device and equipment for an electrochemical energy storage system. Background Art

[0002] Thermal runaway early warning and control of electrochemical energy storage systems are crucial to ensure system safety, reliability and long-term performance.

[0003] The existing technology usually monitors the temperature and voltage of the electrochemical energy storage system to warn and control thermal runaway. However, the existing technology relies too much on the static parameters of temperature and voltage, resulting in delayed warning and misjudgment. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide an electrochemical energy storage system early warning method, a safety control method, a device and equipment in view of the above-mentioned deficiencies in the prior art. The method can be used to accurately warn of thermal runaway of the electrochemical energy storage system, thereby improving the safety and reliability of the system.

[0005] In a first aspect, an embodiment of the present invention provides an electrochemical energy storage system early warning method, wherein the electrochemical energy storage system includes a plurality of cells to be tested, and the method includes:

[0006] Collecting the cell temperature and cell voltage of each of the cells to be tested;

[0007] Obtaining a plurality of characteristic quantities of each of the battery cells to be tested according to the battery cell temperature and the battery cell voltage;

[0008] Based on the thermal runaway boundary condition, the multiple characteristic quantities are combined and judged to obtain warning information, where the warning information is used to indicate the thermal runaway state of the electrochemical energy storage system.

[0009] Preferably, the plurality of characteristic quantities include temperature difference, temperature change rate and voltage change rate, maximum temperature, minimum temperature and minimum voltage, and the characteristic quantities are acquired in real time.

[0010] Among them, the temperature difference is the temperature difference of each battery cell to be tested per unit time, the temperature change rate is the speed at which the battery cell temperature changes with time per unit time for each battery cell to be tested, the voltage change rate is the speed at which the battery cell voltage changes with time per unit time for each battery cell to be tested, the maximum temperature is the highest temperature measured in all battery cells to be tested per unit time, the minimum temperature is the lowest temperature measured in all battery cells to be tested per unit time, and the minimum voltage is the lowest voltage measured in all battery cells to be tested per unit time.

[0011] Preferably, before performing combined determination on the multiple characteristic quantities based on the thermal runaway boundary condition to obtain the warning information, the method further comprises:

[0012] Determine a thermal runaway boundary condition, wherein the thermal runaway boundary condition is a set of predetermined fixed parameter thresholds in the electrochemical energy storage system, and the fixed parameter thresholds are used to indicate the risk level of thermal runaway of the electrochemical energy storage system.

[0013] Preferably, the determining of thermal runaway boundary conditions specifically includes:

[0014] Collecting thermal runaway data and normal operation data of battery cells in the electrochemical energy storage system, wherein the thermal runaway data and normal operation data include the multiple characteristic quantities of the battery cells to be tested;

[0015] Calculating, according to the thermal runaway data and the normal operating data, a Mahalanobis distance between each characteristic quantity in the thermal runaway data and the normal operating data;

[0016] According to the Mahalanobis distance between each characteristic quantity in the thermal runaway data and the normal operating data, a P value between each characteristic quantity in the thermal runaway data and the normal operating data is obtained, and the P value is used to characterize the degree of difference between the thermal runaway data and the normal operating data.

[0017] The thermal runaway boundary condition of the electrochemical energy storage system is determined according to the P value between each characteristic quantity in the thermal runaway data and the normal operating data.

[0018] Preferably, the combining and judging of the multiple characteristic quantities based on the thermal runaway boundary condition to obtain the early warning information includes:

[0019] dividing the plurality of feature quantities into a plurality of feature quantity groups;

[0020] For each feature quantity group, calculating a P value between each feature quantity in the feature quantity group and a corresponding feature quantity in the normal operation data;

[0021] Determining whether a P value between each characteristic quantity in the characteristic quantity group and a corresponding characteristic quantity in the normal operating data satisfies the thermal runaway boundary condition;

[0022] In the plurality of feature quantity groups, if the P value of any feature quantity group satisfies the thermal runaway boundary condition, then a warning message including the thermal runaway state of the electrochemical energy storage system is generated. Preferably, the plurality of feature quantities are divided into a plurality of feature quantity groups, including:

[0023] Divide the plurality of feature quantities into 7 feature quantity groups,

[0024] Among them, the seven characteristic quantity groups are voltage change rate and temperature change rate, maximum temperature and temperature change rate, minimum voltage and temperature change rate, temperature difference and temperature change rate, minimum voltage and maximum temperature, minimum voltage and temperature difference, temperature difference and maximum temperature.

[0025] In a second aspect, an embodiment of the present invention further provides an electrochemical energy storage system control method, the method comprising:

[0026] Performing a thermal runaway warning on the electrochemical energy storage system according to the electrochemical energy storage system early warning method of the first aspect to obtain the early warning information;

[0027] Safety control measures are performed on the electrochemical energy storage system according to the early warning information.

[0028] In a third aspect, an embodiment of the present invention further provides an electrochemical energy storage system early warning device, wherein the electrochemical energy storage system includes a plurality of cells to be tested, and the device includes:

[0029] A first collecting mechanism is used to collect the cell temperature and cell voltage of each of the cells to be tested;

[0030] A feature extraction module, connected to the first acquisition mechanism, and used to obtain a plurality of feature quantities of each of the battery cells to be tested according to the battery cell temperature and the battery cell voltage;

[0031] The early warning module is connected to the feature extraction module and is used to perform combined judgment on the multiple feature quantities based on the thermal runaway boundary conditions to obtain early warning information, wherein the early warning information is used to indicate the thermal runaway state of the electrochemical energy storage system.

[0032] In a fourth aspect, an embodiment of the present invention further provides an energy storage device, including:

[0033] An electrochemical energy storage system, comprising a plurality of cells to be tested;

[0034] The electrochemical energy storage system early warning device described in the third aspect above is used to provide thermal runaway early warning for the electrochemical energy storage system.

[0035] The electrochemical energy storage system early warning method of the present application comprehensively considers the static parameters and dynamic changes of temperature and voltage. Specifically, by respectively collecting and analyzing static and dynamic battery cell temperature and voltage data, multiple characteristic quantities of the battery cell to be tested are determined, and multiple characteristic quantities and thermal runaway boundary conditions are used for combined judgment. It can accurately warn the electrochemical energy storage system of thermal runaway, thereby improving the safety and reliability of the system. . BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 : A flow chart of an electrochemical energy storage system early warning method provided in an embodiment of the present application;

[0037] Figure 2 : A schematic diagram of a process flow of a thermal runaway warning and control method for an electrochemical energy storage system provided in an embodiment of the present application;

[0038] Figure 3 : A schematic diagram of the position of a fiber optic temperature sensor placed in a battery cell provided in an embodiment of the present application;

[0039] Figure 4 : A schematic diagram of a BMS and optical fiber temperature sensor acquisition module provided in an embodiment of the present application;

[0040] Figure 5 : A schematic diagram of a model result provided in an embodiment of the present application;

[0041] Figure 6 : A structural diagram of an electrochemical energy storage system early warning device provided in an embodiment of the present application;

[0042] Figure 7 : A structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention is further described in detail below with reference to the accompanying drawings and embodiments.

[0044] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0045] Electrochemical energy storage system is a system that stores and releases energy through the conversion between chemical energy and electrical energy. It usually uses electrochemical batteries or supercapacitors as the core energy storage unit, and its applications range from small portable devices to large grid energy storage systems. The basic principle of electrochemical energy storage is to use the charging and discharging process of batteries or capacitors, in which electricity drives chemical reactions to store energy during charging and generates current in an external circuit during discharge.

[0046] Thermal runaway warning and control of electrochemical energy storage systems are crucial to ensure system safety, reliability and long-term performance. Existing technologies usually monitor the two main parameters of temperature and voltage in electrochemical energy storage systems to perform thermal runaway warning and control. These methods rely on temperature sensors (such as negative temperature coefficient thermistors) and voltage measurement devices installed on the surface of the battery cells to detect abnormal signs. At the same time, the system may also use a combination of CO, H2, VOC, smoke and temperature detectors to identify thermal runaway events that have occurred so that corresponding safety control measures can be taken in a timely manner.

[0047] The inventors have found that the existing thermal runaway warning and control methods of electrochemical energy storage systems have the following defects:

[0048] Lack of comprehensiveness: Existing early warning methods often only use temperature and voltage data to warn the battery system, without considering the temperature change rate and voltage change rate, etc., resulting in delayed and misjudgment of thermal runaway judgment.

[0049] Lack of accuracy: The existing temperature collection is mainly carried out through NTC to collect the welding position of the battery pole, which cannot truly reflect the internal temperature of the battery cell, has poor accuracy, and has the phenomenon of delayed thermal runaway judgment. The existing thermal runaway warning boundary conditions lack the conditions for real test verification and big data learning, and there are problems of misjudgment and delay of thermal runaway warning.

[0050] Lack of intelligent operation and maintenance: Existing warnings mainly monitor thermal runaway through a random combination of CO, H2, VOC, smoke and temperature detectors in the battery pack. This method not only increases the cost of the product, but also can only detect abnormalities in the battery cell after the battery cell spray valve is turned on. In addition, the detector has a short lifespan and needs to be replaced after a few years, which will lead to difficulties in later operation and maintenance.

[0051] Embodiment 1:

[0052] Based on the above research, in order to solve the existing technical problems, such as Figure 1 As shown, this embodiment provides an electrochemical energy storage system early warning method, wherein the electrochemical energy storage system includes a plurality of battery cells to be tested, and specifically includes the following steps S101 to S105.

[0053] S101, collecting the cell temperature and cell voltage of each cell to be tested.

[0054] The battery cells to be tested may be multiple battery cells in an electrochemical energy storage system. These battery cells are objects that need to be monitored to prevent possible thermal runaway.

[0055] Specifically, the temperature of the battery cell can be measured in real time through sensing technology, such as using a temperature sensor (such as a thermocouple, thermistor or fiber optic temperature sensor). Use a voltage detection device (such as a voltage sensor or a voltage monitoring circuit) to measure the voltage of the battery cell. By collecting these two parameters (temperature and voltage), the system can perform basic monitoring of the operating status of the battery, which lays a data foundation for subsequent feature extraction and thermal runaway warning.

[0056] S102, obtaining a plurality of characteristic quantities of each battery cell to be tested according to the battery cell temperature and the battery cell voltage.

[0057] Specifically, for each cell to be tested in the electrochemical energy storage system, multiple feature quantities are extracted or calculated from the collected cell temperature and voltage data. These feature quantities reflect various status indicators of the cell and are key indicators for analyzing the health of the cell and predicting the risk of thermal runaway. This step can convert the raw data into more valuable numerical values ​​through data preprocessing, feature extraction algorithms, and statistical analysis, providing a basis for subsequent early warning judgments.

[0058] S103, based on the thermal runaway boundary condition, a combination of multiple characteristic quantities is determined to obtain early warning information, where the early warning information is used to indicate the thermal runaway state of the electrochemical energy storage system.

[0059] Specifically, based on the predefined thermal runaway boundary conditions, the multiple characteristic quantities obtained in step S102 are comprehensively analyzed and combined to obtain early warning information. This not only takes into account the comprehensive effect of multiple indicators, but also uses the preset boundary conditions as the judgment criteria, aiming to discover potential thermal runaway risks in advance.

[0060] The final output warning information directly indicates the thermal runaway state of the electrochemical energy storage system and can include different levels of warnings or specific risk assessment results.

[0061] In this embodiment, by collecting the temperature and voltage of the battery cell, extracting multiple feature quantities, and making a combined judgment based on the thermal runaway boundary conditions, an effective early warning of the thermal runaway state of the system is achieved. This method comprehensively utilizes multiple parameters and features, combined with preset boundary conditions, and can more accurately and comprehensively evaluate the system status, thereby improving the accuracy and reliability of the early warning. By timely discovering potential thermal runaway risks, this method helps prevent serious accidents, improves the safety performance of electrochemical energy storage systems, and provides important support for the stable operation and risk management of the system.

[0062] Optionally, the collecting of the cell temperature of each cell to be tested in S101 specifically includes the following steps:

[0063] The cell temperature of the cell to be tested is collected by an optical fiber temperature sensor, which is implanted at the center of the diaphragm inside the cell to be tested.

[0064] Fiber optic temperature sensor is a device that uses optical fiber to transmit light signals to measure temperature. It has the characteristics of high sensitivity, anti-electromagnetic interference, high voltage resistance and miniaturization, and is very suitable for accurate temperature measurement in complex or tiny environments.

[0065] Specifically, the optical fiber temperature sensor is implanted inside the battery cell to be tested, especially in the center of the diaphragm. The diaphragm is located in a key heat exchange position in the battery cell, and its temperature change can reflect the actual working state inside the battery cell. The center of the diaphragm is usually also a relatively uniform position of the temperature field inside the battery cell, which can more accurately represent the temperature state of the entire battery cell.

[0066] In one example, if Figure 3 As shown, the optical fiber temperature sensor can be implanted on the surface of the center position of the internal diaphragm of the battery cell to be tested.

[0067] In this embodiment, by placing the optical fiber temperature sensor inside the battery core, the core temperature of the battery core can be measured more timely and accurately, thereby improving the accuracy and reliability of temperature measurement.

[0068] Optionally, the above-mentioned multiple characteristic quantities include temperature difference, temperature change rate and voltage change rate, maximum temperature, minimum temperature, and minimum voltage, and the characteristic quantities are acquired in real time.

[0069] The temperature difference is the temperature difference of each battery cell to be tested per unit time, which can be used to identify the temperature fluctuation of the battery cell in a short period of time and help detect abnormal temperature changes.

[0070] The temperature change rate is the speed at which the cell temperature of each cell under test changes with time per unit time. It reflects the rate at which the cell temperature rises or falls and is a key indicator for determining whether the cell heats up rapidly.

[0071] The voltage change rate is the speed at which the cell voltage of each tested cell changes over time per unit time. It characterizes the stability and change trend of the cell voltage and helps determine the health status of the cell.

[0072] The maximum temperature is the highest temperature measured in all the cells to be tested within a unit time, and can be used to identify which cell in the system has the highest temperature.

[0073] The minimum temperature is the lowest temperature measured in all the cells to be tested within a unit time.

[0074] The minimum voltage is the lowest voltage measured in all the cells to be tested within a unit time.

[0075] Specifically, these characteristic quantities reflect the temperature and voltage changes of the battery cells, providing multi-dimensional data support for the thermal runaway warning of the system. By analyzing the changes in these characteristic quantities, possible abnormal conditions of the battery cells can be identified in a timely manner, and corresponding preventive measures can be taken.

[0076] Optionally, before the above S103, the following steps may also be included:

[0077] Determine thermal runaway boundary conditions, which are a set of predetermined fixed parameter thresholds in the electrochemical energy storage system. The fixed parameter thresholds are used to indicate the risk level of thermal runaway in the electrochemical energy storage system.

[0078] Specifically, thermal runaway boundary conditions play a key safety monitoring role in electrochemical energy storage systems. They consist of a set of predetermined fixed parameter thresholds that are used to assess the risk of thermal runaway in the system. By monitoring key parameters such as temperature, voltage, and current of the system, and then obtaining the dynamic characteristic parameters of the electrochemical energy storage system, and comparing them with the above fixed thresholds, operators can judge the safety status of the system in real time. When the parameters approach or exceed these thresholds, the system will be considered to be in a high-risk state, thereby triggering an early warning mechanism and taking necessary safety measures.

[0079] In this embodiment, the thermal runaway boundary condition provides a stable reference standard and can also support dynamic risk assessment, helping to prevent potential thermal runaway events and improving the overall safety and reliability of the system.

[0080] Optionally, before the above S103, the following steps may also be included:

[0081] Collect thermal runaway data and normal operation data of battery cells in the electrochemical energy storage system, where the thermal runaway data and normal operation data include multiple characteristic quantities of the battery cells to be tested;

[0082] According to the thermal runaway data and the normal operation data, the Mahalanobis distance between each characteristic quantity in the thermal runaway data and the normal operation data is calculated;

[0083] According to the Mahalanobis distance between each characteristic quantity in the thermal runaway data and the normal operation data, the P value between each characteristic quantity in the thermal runaway data and the normal operation data is obtained. The P value is used to characterize the degree of difference between the thermal runaway data and the normal operation data.

[0084] The thermal runaway boundary conditions of the electrochemical energy storage system are determined based on the P value between each characteristic quantity in the thermal runaway data and the normal operation data.

[0085] Among them, thermal runaway data is the characteristic quantity recorded when the battery cell experiences a thermal runaway event, and normal operation data is the characteristic quantity recorded when the battery cell is in normal working state. These data include multiple characteristic quantities of the battery cell to be tested, such as the temperature difference, temperature change rate, voltage change rate, etc. mentioned above.

[0086] Mahalanobis distance is a statistical measurement method that can measure the "distance" between multivariate data sets. It is a statistical method used to measure the difference between two sets of data. It takes into account the correlation between feature quantities and can better reflect the distribution characteristics of multidimensional data than Euclidean distance.

[0087] The P value is a probability value used in statistics for hypothesis testing. Here, the P value is used to indicate the degree of difference between thermal runaway data and normal operation data. The smaller the P value, the more significant the difference between the two sets of data.

[0088] Specifically, first, thermal runaway data and normal operating data are collected from the electrochemical energy storage system; then, the Mahalanobis distance between each feature quantity group in the thermal runaway data and the normal operating data is calculated; based on the calculated Mahalanobis distance, the P value between each feature quantity in the thermal runaway data and the normal operating data is obtained, and a smaller P value (generally when there is a statistically significant difference) means that there is a significant difference between the thermal runaway data and the normal operating data; the calculated P value is used to determine the boundary conditions of thermal runaway, for example, a threshold value of the P value can be set, and when the P value generated by the actually observed data is less than this threshold value, it is determined that the system may be in a thermal runaway state.

[0089] In this embodiment, by collecting thermal runaway and normal operation data, the Mahalanobis distance between the characteristic quantities in these two types of data is calculated, and then the P value is obtained to quantify the data difference. Finally, the boundary conditions of thermal runaway are determined based on these statistical analysis results. This method combines multidimensional data analysis and statistical principles to provide an objective and accurate framework to identify potential thermal runaway risks, thereby enhancing the safety monitoring and early warning capabilities of electrochemical energy storage systems.

[0090] In one example, multi-level boundary values ​​can also be set according to the P value between each characteristic quantity in the thermal runaway data and the normal operation data, so that potential problems can be identified earlier, more detailed thermal runaway warnings can be provided, and corresponding graded response measures can be taken. For example: Normal state: The P value is higher than a certain threshold, indicating that the system is operating normally. Level 1 thermal runaway: The P value is lower than the normal threshold but higher than the moderate abnormal threshold, and preventive maintenance may be required. Level 2 thermal runaway: The P value is further reduced, indicating that the system may be about to enter a thermal runaway state and intervention measures need to be taken. Level 3 thermal runaway: The P value is extremely low, indicating that the system is likely to be in the early stages of thermal runaway and emergency measures need to be taken immediately. Level 4 thermal runaway: The P value is lower than the danger threshold, indicating that the system has entered a thermal runaway state and needs to be shut down immediately and safety measures need to be taken.

[0091] Optionally, the above S103 may specifically include the following steps:

[0092] dividing the plurality of feature quantities into a plurality of feature quantity groups;

[0093] For each feature quantity group, calculating the P value between each feature quantity in the feature quantity group and the corresponding feature quantity in the normal operation data;

[0094] Determining whether a P value between each characteristic quantity in the characteristic quantity group and a corresponding characteristic quantity in the normal operating data satisfies the thermal runaway boundary condition;

[0095] In the plurality of characteristic quantity groups, if the P value of any characteristic quantity group satisfies the thermal runaway boundary condition, then early warning information including the thermal runaway state of the electrochemical energy storage system is generated.

[0096] Specifically, the characteristic quantities can be grouped based on their properties (such as temperature correlation, voltage correlation) or their mutual relationship in the system; for each characteristic quantity in each characteristic quantity group, the P value between it and the corresponding characteristic quantity in the normal operating data is calculated, and a smaller P value indicates that the current observation value is significantly different from the normal state, which may indicate an abnormal situation; the P value of each characteristic quantity is compared with a pre-set thermal runaway boundary condition, and the boundary condition is the thermal runaway boundary condition determined according to the P value between each characteristic quantity in the thermal runaway data and the normal operating data as mentioned above; finally, if the P value of any characteristic group in multiple characteristic groups meets the thermal runaway boundary condition, a thermal runaway warning is triggered, that is, as long as one group shows an abnormality, it is considered that the system may be in a thermal runaway state.

[0097] In this embodiment, by dividing multiple characteristic quantities into different groups and calculating the P value for each group and comparing it with the preset thermal runaway boundary conditions, a comprehensive assessment of the thermal runaway risk of the electrochemical energy storage system is achieved. If any characteristic group meets the boundary conditions, an early warning is triggered, thereby providing an early warning mechanism with high sensitivity and low false alarm rate.

[0098] Optionally, the plurality of feature quantities are divided into a plurality of feature quantity groups, including:

[0099] The multiple feature quantities are divided into 7 feature quantity groups.

[0100] Among them, the seven characteristic quantity groups are voltage change rate and temperature change rate, maximum temperature and temperature change rate, minimum voltage and temperature change rate, temperature difference and temperature change rate, minimum voltage and maximum temperature, minimum voltage and temperature difference, temperature difference and maximum temperature.

[0101] Specifically, the multiple feature quantities can be divided into the following 7 feature quantity groups:

[0102] (1) Voltage change rate and temperature change rate: reflect the dynamic change characteristics of the battery. The voltage change rate may indicate the battery's charge and discharge status or the speed of the internal chemical reaction, and the temperature change rate may reflect the speed of heat generation or dissipation. The combination of the two can reveal the relationship between battery performance and thermal management conditions.

[0103] (2) Maximum temperature and temperature change rate: Maximum temperature is a key indicator of battery safety. Too high a temperature may lead to thermal runaway. Maximum temperature combined with temperature change rate can predict whether the temperature will continue to rise to a dangerous level, which helps to detect local overheating problems in a timely manner.

[0104] (3) Minimum voltage and temperature change rate: The minimum voltage may indicate that the battery is over-discharged or that certain battery cells are degraded. The minimum voltage combined with the temperature change rate can detect whether the battery is still heating up at low voltage. This helps identify abnormal discharge behavior that may cause safety issues.

[0105] (4) Temperature difference and temperature change rate: The temperature difference reflects the uniformity of temperature distribution inside the battery cell. Combined with the temperature change rate, it can be observed whether the temperature non-uniformity is increasing. It helps to find hot spots or cold spots, as well as the efficiency problems of the thermal management system.

[0106] (5) Minimum voltage and maximum temperature: The combination of these two features can detect whether the battery is in a low voltage and high temperature condition at the same time. This helps to identify specific battery cells that may be in a dangerous state and reveals the potential correlation between voltage and temperature.

[0107] (6) Minimum voltage and temperature difference: It can detect whether the battery cell with the lowest voltage also has a significant temperature difference. It helps to identify battery cells with degraded performance or potential problems. It reveals the relationship between voltage imbalance and uneven temperature distribution.

[0108] (7) Temperature difference and maximum temperature: This combination can evaluate whether the maximum temperature is a local or global phenomenon. It helps determine whether the thermal management system is operating effectively. It can detect whether there are serious hot spot problems.

[0109] In this embodiment, by grouping multiple characteristic quantities for early warning analysis, the system can monitor the state of the electrochemical energy storage system more comprehensively and accurately, and effectively improve the accuracy and timeliness of thermal runaway early warning.

[0110] Embodiment 2:

[0111] This embodiment provides a safety control method for an electrochemical energy storage system, wherein the electrochemical energy storage system includes a plurality of cells to be tested, specifically including the following:

[0112] Performing a thermal runaway warning on the electrochemical energy storage system according to the electrochemical energy storage system warning method of any of the above embodiments to obtain warning information;

[0113] Implement safety control measures on the electrochemical energy storage system based on early warning information.

[0114] Specifically, the electrochemical energy storage system is monitored in real time using the warning method described previously. For example, when an abnormality is detected, warning information is generated and output. The warning information may include the location of the battery cell that may have problems, the type and severity of the abnormality, etc. Based on the warning information, appropriate safety control measures are taken to prevent accidents.

[0115] Optionally, the security control measures implemented above may include:

[0116] Isolate the affected cells or modules to prevent thermal runaway from spreading;

[0117] Adjust system temperature and pressure, such as increasing cooling or activating ventilation systems;

[0118] Adjust current or power output to reduce heat load;

[0119] Notify operators and issue real-time notifications through alarm systems to facilitate human intervention;

[0120] Shutdown operation: When necessary, power down part or all of the energy storage system to prevent further thermal runaway.

[0121] In this embodiment, the above-mentioned electrochemical energy storage system early warning method and intelligent control strategy are combined to provide a comprehensive safety control solution for the electrochemical energy storage system. First, thermal runaway warning is performed through steps such as characteristic quantity grouping and P value calculation, and then the corresponding safety control measures are automatically executed based on the early warning information. It has the advantages of active prevention, automation, precise control and flexibility, can identify safety hazards in a timely manner and take appropriate measures, significantly improve the safety and reliability of the system, and can be applied to various scenarios such as electric vehicles and large-scale energy storage facilities.

[0122] In one example, the warning information includes the thermal runaway risk level of the electrochemical energy storage system. After determining the thermal runaway risk level of the electrochemical energy storage system, the specific control method is as follows:

[0123] (1) If the alarm level 1 is reached, the energy storage system is prohibited from charging or discharging, and the liquid cooling unit is requested to cool at maximum power.

[0124] (2) If the alarm reaches level 2, the fire control system is activated and the fire extinguisher is activated to suppress thermal runaway of the energy storage system.

[0125] (3) If neither the Level 1 nor the Level 2 alarm is reached, it indicates that the thermal runaway warning state is a non-warning state and the energy storage system does not take any action.

[0126] In order to facilitate the understanding of the electrochemical energy storage system early warning method provided in this embodiment, a practical application description of the above electrochemical energy storage system early warning method is provided here. Figure 2 For details, see the following example:

[0127] S110: Collecting the temperature and voltage data of the battery cells to be evaluated (ie, collecting the battery cell temperature and battery cell voltage of each battery cell to be tested).

[0128] The temperature inside the battery cell to be evaluated is detected by implanting an optical fiber temperature sensor inside the battery cell, and the voltage of the battery cell is detected through the wires on the collection harness in the battery module. Then, the battery management system collects and records the temperature and voltage data of the battery cell to be evaluated, and determines whether the collected data is valid. The details are as follows:

[0129] S111: Select the cell to be determined, implant the optical fiber temperature sensor on the surface of the center of its internal diaphragm, and lead out the interface on the cell cover, such as Figure 3 shown.

[0130] S112: Integrate all interfaces on the cover plate of the battery cell to be determined on the module's acquisition harness board, integrate them with the wires for detecting voltage on the acquisition harness, and connect them to the battery management system, such as Figure 4 shown.

[0131] S113: Record the temperature and voltage data of the battery cell to be evaluated through the battery management system, and determine whether the collected data is valid, and remove invalid values.

[0132] S120: Build an algorithm model and use the collected data to obtain feature quantities.

[0133] The characteristic quantities of the collected data are obtained (i.e., multiple characteristic quantities of each battery cell to be tested are obtained according to the battery cell temperature and battery cell voltage). From the collected battery cell temperature and voltage data, the algorithm model is used to obtain the lowest voltage of all batteries to be determined in the energy storage system in different time periods, the highest temperature of all batteries to be determined, the lowest temperature of all batteries to be determined, the difference between the highest and lowest temperatures of all batteries to be determined, the rate of change of the temperature of the batteries to be determined over time, the rate of change of the voltage of the batteries to be determined, and the communication status and other related parameters.

[0134] The specific steps are as follows:

[0135] S121: Calculate the minimum voltage, maximum temperature, minimum temperature, temperature difference, temperature change rate, voltage change rate and other related parameters of all cells to be determined in the system according to the voltages and temperatures of all cells in the energy storage system under different working conditions and different time periods collected by the BMS (i.e.

[0136] S122: The feature quantity calculation formula in the algorithm model is as follows: Formula (1) to (3),

[0137] Temperature difference △T=T max -T min (1)

[0138] Temperature change rate dT / dt = (T2-T1) / (t2-t1) (2)

[0139] Voltage change rate dU / dt = (U2-U1) / (t2-t1) (3)

[0140] in:

[0141] Tmin is the lowest temperature of all cells to be determined in the energy storage system at a certain moment in the energy storage system, °C;

[0142] Tmax is the maximum temperature of all cells to be determined in the energy storage system at a certain moment in the energy storage system, °C;

[0143] t1 is the time of the first collection, s;

[0144] t2 is the time of the second collection, s;

[0145] The time interval between t1 and t2 is one unit time;

[0146] T2 is the temperature of the battery cell to be determined at time t2 in the energy storage system, °C;

[0147] T1 is the temperature of the battery cell to be determined at time t1 in the energy storage system, °C;

[0148] U2 is the cell voltage to be determined at time t2 in the energy storage system, V;

[0149] U1 is the cell voltage to be determined at time t1 in the energy storage system, V.

[0150] S130: Compare the characteristic quantity with the thermal runaway warning boundary condition to determine the thermal runaway warning state of the battery cell.

[0151] The acquired characteristic quantities are used to confirm the thermal runaway warning status (i.e., based on the thermal runaway boundary conditions, multiple characteristic quantities are combined and judged to obtain warning information). First, the thermal runaway warning boundary conditions are confirmed by selecting the data of the same type of electrochemical energy storage power station for learning, and combining with the actual battery cell thermal runaway test data; then, the characteristic quantities of the battery cell to be judged are compared with the thermal runaway warning boundary conditions to confirm the thermal runaway warning status of the battery cell to be judged. The details are as follows:

[0152] S131: According to the calculated characteristic quantity, the combined thermal runaway boundary conditions are set as follows:

[0153] Condition a) Voltage change rate: the rate of change of the voltage of the battery cell to be determined in the energy storage system;

[0154] Condition b) Temperature change rate: the rate of increase of the temperature of the battery cell to be determined in the energy storage system over time;

[0155] Condition c) Maximum temperature: the maximum temperature of all cells to be determined in the energy storage system;

[0156] Condition d) Minimum voltage: the lowest voltage of all cells to be determined in the energy storage system;

[0157] Condition e) Temperature difference: the difference between the highest and lowest temperatures of all cells to be determined.

[0158] When any combination of the conditions {(a&b)||(c&b)||(d&b)||(e&b)||(d&c)||(d&e)||(e&c)} is met, the thermal runaway warning is triggered.

[0159] S132: Triggering thermal runaway of the battery cell by heating, puncture or overcharging, etc., obtaining actual thermal runaway test data of the battery cell as the abnormal label data set D1 (i.e. the thermal runaway data mentioned above), and obtaining data during normal battery cell charging and discharging as the normal data set D2 (i.e. the normal operating data mentioned above);

[0160] S133: Combine the feature data sets F1, F2, F7 in the data sets D1 and D2 that meet the combination of S131, where F represents the thermal runaway warning combination, and calculate the Mahalanobis distance d of each data point in each feature data set (i.e., calculate the Mahalanobis distance between each feature quantity in the thermal runaway data and the normal operation data based on the thermal runaway data and the normal operation data). The calculation formula is as follows:

[0161] d 2 =(X-μ)T Σ -1 (X-μ) (4)

[0162] Wherein, X is the observed value (such as the multiple characteristic quantities of each battery cell to be tested obtained as described above), T is the transpose, μ is the mean vector, which can be calculated based on the characteristic quantity data in the normal operation data, and Σ is the covariance matrix.

[0163] S134: Set control limits: Calculate the P value of the Mahalanobis distance (i.e., obtain the P value between each feature quantity in the thermal runaway data and the normal operation data according to the Mahalanobis distance between each feature quantity in the thermal runaway data and the normal operation data), and set a suitable significance level to ensure a suitable accuracy rate and false alarm rate. This significance level is the thermal runaway boundary threshold that satisfies this data set. The schematic diagram of the model results is shown in the figure below. Figure 5 shown.

[0164] Specifically, the P value of the Mahalanobis distance of each feature data set is calculated, including the following steps:

[0165] p value = 1-F (chi-square value, degrees of freedom), the square of the Mahalanobis distance is taken as the chi-square value, and the degrees of freedom are 2. F is the cumulative distribution function of the chi-square distribution, and it is necessary to perform a corresponding table lookup or calculation based on the degrees of freedom and significance level. Setting a suitable significance level also requires ensuring a suitable accuracy rate and false alarm rate. This significance level is the thermal runaway boundary threshold that meets this data set.

[0166] A total of 2 levels of thermal runaway warning functions are set up, and the characteristic quantities of the judgment conditions (voltage change rate, temperature change rate, maximum temperature, minimum voltage and temperature difference) are the same, but the thresholds of the characteristic quantities are different.

[0167] Specifically, the threshold setting method is as follows:

[0168] According to the method 6.7.4.3 in GB / T 36276-2023, multiple groups of experiments were conducted to obtain the actual battery cell thermal runaway test data as the abnormal label data set D1. The data during the normal battery cell charging and discharging process was taken as the normal data set D2. The D1 and D2 data sets were combined to meet the feature data sets F1, F2,,, ​​F7, and the Mahalanobis distance of each data point in each feature data set was calculated. The P value of the Mahalanobis distance of each feature data set was then calculated based on the Mahalanobis distance, and an appropriate significance level was set to ensure the appropriate accuracy and false alarm rate. This significance level is the thermal runaway boundary threshold that meets this data set. The experimental data was analyzed to obtain the battery cell thermal runaway boundary conditions.

[0169] (2) When the battery explosion-proof valve is open, it is a level 1 thermal runaway warning boundary condition; when the battery is in thermal runaway (emitting thick smoke), it is a level 2 thermal runaway warning boundary condition.

[0170] S134: Then, the characteristic quantity of the battery cell to be determined is compared with the thermal runaway warning boundary condition to confirm the thermal runaway warning state of the battery cell to be determined.

[0171] S140: Determine a thermal runaway control method for the battery cell according to the thermal runaway warning state of the battery cell.

[0172] According to the thermal runaway warning status of the battery cell, determine the thermal runaway control method of the battery cell. If the level 1 alarm action is reached, the energy storage system is prohibited from charging and discharging, and the liquid cooling unit is requested to cool at maximum power; if the level 2 alarm action is reached, the fire control system is started and the fire extinguisher is started to suppress the thermal runaway of the energy storage system. If neither the level 1 nor the level 2 alarm action is reached, it indicates that the thermal runaway warning status is no warning state, which is in a controllable state, and the energy storage system does not take any action. The details are as follows:

[0173] S141, the system does not take any action and continues to run

[0174] If neither level 1 nor level 2 alarm action is reached, it indicates that the thermal runaway warning state is a non-warning state and the energy storage system does not take any action.

[0175] S142, the system starts fire control to suppress thermal runaway

[0176] If the alarm level 1 is reached, the energy storage system is prohibited from charging or discharging, and the liquid cooling unit is requested to cool at maximum power.

[0177] If the alarm reaches level 2, the fire control system will be activated and the fire extinguisher will be started to suppress thermal runaway of the energy storage system.

[0178] In this embodiment, it is possible to obtain more accurate temperature data through optical fiber temperature sensor monitoring and to issue early warning of thermal runaway of the battery cells in the electrochemical energy storage system through software, which greatly reduces costs and improves the convenience of product operation and maintenance. It provides an important solution for the safety protection and operation and maintenance convenience of electrochemical energy storage systems. This method has the advantages of higher accuracy and robustness of thermal runaway early warning, and more advanced early warning time, which can reduce the accident rate and reduce the direct or indirect economic losses caused by thermal runaway of the energy storage system.

[0179] Embodiment 3:

[0180] like Figure 6 As shown, this embodiment provides an electrochemical energy storage system early warning device 600, the electrochemical energy storage system includes a plurality of cells to be tested,

[0181] The device includes:

[0182] The first collecting mechanism 601 is used to collect the cell temperature and cell voltage of each cell to be tested;

[0183] The feature extraction module 602 is connected to the first acquisition mechanism 601 and is used to obtain multiple feature quantities of each battery cell to be tested according to the battery cell temperature and the battery cell voltage;

[0184] The early warning module 603 is connected to the feature extraction module 602 and is used to make a combined judgment on multiple feature quantities based on the thermal runaway boundary conditions to obtain early warning information, which is used to indicate the thermal runaway state of the electrochemical energy storage system.

[0185] In this embodiment, by collecting and analyzing the temperature and voltage data of the battery cell, multiple characteristic quantities of the battery cell to be tested are determined, and a combined judgment is made using the multiple characteristic quantities and thermal runaway boundary conditions, so that an accurate early warning of thermal runaway of the electrochemical energy storage system can be provided, thereby improving the safety and reliability of the system.

[0186] Optionally, the first collection mechanism 601 includes:

[0187] Fiber optic temperature and voltage sensors,

[0188] The optical fiber temperature sensor is implanted in the center of the diaphragm inside the battery cell to be tested and connected to the feature extraction module to collect the battery cell temperature of the battery cell to be tested and send the collected battery cell temperature value to the feature extraction module 602. Optionally, the above device also includes: a determination module, used to determine the thermal runaway boundary condition;

[0189] The modules are determined to include:

[0190] A second collection mechanism is used to collect thermal runaway data and normal operation data of battery cells in the electrochemical energy storage system, wherein the thermal runaway data and normal operation data include multiple characteristic quantities of the battery cells to be tested;

[0191] A first calculation unit is connected to the second acquisition mechanism and is used to calculate the Mahalanobis distance between each characteristic quantity in the thermal runaway data and the normal operation data according to the thermal runaway data and the normal operation data;

[0192] The second calculation unit is connected to the first calculation unit and is used to obtain a P value between each characteristic quantity in the thermal runaway data and the normal operation data according to the Mahalanobis distance between each characteristic quantity in the thermal runaway data and the normal operation data, wherein the P value is used to characterize the degree of difference between the thermal runaway data and the normal operation data.

[0193] The determination unit is connected to the second calculation unit and is used to determine the thermal runaway boundary condition of the electrochemical energy storage system according to the P value between each characteristic quantity in the thermal runaway data and the normal operation data.

[0194] Optionally, the warning module 603 may include:

[0195] A division unit, used for dividing a plurality of feature quantities into a plurality of feature quantity groups;

[0196] a calculation unit, for calculating, for each feature quantity group, a P value between each feature quantity in the feature quantity group and a corresponding feature quantity in the normal operation data;

[0197] a comparison unit, for comparing a P value between each characteristic quantity in the characteristic quantity group and a corresponding characteristic quantity in the normal operating data with a thermal runaway boundary condition;

[0198] The determination unit is used to determine that the early warning information is that the electrochemical energy storage system has thermal runaway if the P value of any feature group in the multiple feature groups meets the thermal runaway boundary condition.

[0199] Optionally, the division unit is specifically used to divide the multiple feature quantities into 7 feature quantity groups,

[0200] Among them, the seven characteristic quantity groups are voltage change rate and temperature change rate, maximum temperature and temperature change rate, minimum voltage and temperature change rate, temperature difference and temperature change rate, minimum voltage and maximum temperature, minimum voltage and temperature difference, temperature difference and maximum temperature.

[0201] Embodiment 4:

[0202] This embodiment provides an energy storage device, including:

[0203] An electrochemical energy storage system, comprising a plurality of cells to be tested;

[0204] The electrochemical energy storage system early warning device provided in any of the above embodiments is used to provide a thermal runaway early warning for the electrochemical energy storage system.

[0205] Specifically, by integrating the electrochemical energy storage system and the thermal runaway early warning device, multiple cells to be tested are used to achieve efficient energy storage. At the same time, the early warning device monitors key parameters in real time to identify potential thermal runaway risks. When the parameters approach or exceed the preset safety threshold, the system will issue an early warning to prompt the necessary safety measures to be taken. This not only improves the safety and reliability of the equipment, but is also suitable for applications that require high safety standards, such as grid energy storage and electric vehicles, providing important support for the safe application of energy storage technology.

[0206] Figure 7 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0207] The electronic device may include a processor 701 and a memory 702 storing computer program instructions.

[0208] Specifically, the processor 701 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0209] The memory 702 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 702 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 702 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 702 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 702 is a non-volatile solid-state memory.

[0210] The memory may include a read-only memory (ROM), a random access memory (RAM), a disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of the present disclosure (the above-mentioned electrochemical energy storage system early warning method).

[0211] The processor 701 implements any one of the scheduling methods in the above embodiments by reading and executing computer program instructions stored in the memory 702 .

[0212] In one example, the electronic device may further include a communication interface 703 and a bus 710. Figure 7 As shown, the processor 701, the memory 702, and the communication interface 703 are connected via a bus 710 and communicate with each other.

[0213] The communication interface 703 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0214] Bus 710 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 710 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0215] In addition, in combination with the scheduling method in the above embodiment, the embodiment of the present application can provide a computer storage medium to implement. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the electrochemical energy storage system early warning methods in the above embodiment is implemented.

[0216] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0217] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0218] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0219] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable scheduling device to produce a machine so that these instructions executed by the processor of the computer or other programmable scheduling device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0220] The above are only specific implementation methods of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. An electrochemical energy storage system early warning method, characterized in that: The electrochemical energy storage system includes a plurality of cells to be tested, and the method includes: Collecting the cell temperature and cell voltage of each of the cells to be tested; Obtaining a plurality of characteristic quantities of each of the battery cells to be tested according to the battery cell temperature and the battery cell voltage; Based on the thermal runaway boundary condition, the multiple characteristic quantities are combined and judged to obtain warning information, where the warning information is used to indicate the thermal runaway state of the electrochemical energy storage system.

2. The method according to claim 1, characterized in that The collecting of the cell temperature of each of the cells to be tested comprises: The cell temperature of the cell to be tested is collected by an optical fiber temperature sensor, and the optical fiber temperature sensor is implanted in the center of the diaphragm inside the cell to be tested.

3. The method according to claim 1, characterized in that The multiple characteristic quantities include: temperature difference, temperature change rate and voltage change rate, maximum temperature, minimum temperature, and minimum voltage. The characteristic quantities are acquired in real time. Among them, the temperature difference is the temperature difference of each battery cell to be tested per unit time, the temperature change rate is the speed at which the battery cell temperature of each battery cell to be tested changes with time per unit time, the voltage change rate is the speed at which the battery cell voltage of each battery cell to be tested changes with time per unit time, the maximum temperature is the highest temperature measured in all battery cells to be tested per unit time, the minimum temperature is the lowest temperature measured in all battery cells to be tested per unit time, and the minimum voltage is the lowest voltage measured in all battery cells to be tested per unit time.

4. The method according to any one of claims 2 to 3, characterized in that: Before combining and determining the plurality of characteristic quantities based on the thermal runaway boundary condition to obtain the warning information, the method further includes: Determine a thermal runaway boundary condition, wherein the thermal runaway boundary condition is a set of predetermined fixed parameter thresholds in the electrochemical energy storage system, and the fixed parameter thresholds are used to indicate the risk level of thermal runaway of the electrochemical energy storage system.

5. The method according to any one of claims 2 to 3, characterized in that: Determining the thermal runaway boundary condition specifically includes: Collecting thermal runaway data and normal operation data of battery cells in the electrochemical energy storage system, wherein the thermal runaway data and normal operation data include the multiple characteristic quantities of the battery cells to be tested; Calculating, according to the thermal runaway data and the normal operating data, a Mahalanobis distance between each characteristic quantity in the thermal runaway data and the normal operating data; According to the Mahalanobis distance between each characteristic quantity in the thermal runaway data and the normal operating data, a P value between each characteristic quantity in the thermal runaway data and the normal operating data is obtained, and the P value is used to characterize the degree of difference between the thermal runaway data and the normal operating data. The thermal runaway boundary condition of the electrochemical energy storage system is determined according to the P value between each characteristic quantity in the thermal runaway data and the normal operating data.

6. The method according to claim 5, characterized in that The combining and judging the multiple characteristic quantities based on the thermal runaway boundary condition to obtain the early warning information includes: dividing the plurality of feature quantities into a plurality of feature quantity groups; For each feature quantity group, calculating a P value between each feature quantity in the feature quantity group and a corresponding feature quantity in the normal operation data; Determining whether a P value between each characteristic quantity in the characteristic quantity group and a corresponding characteristic quantity in the normal operating data satisfies the thermal runaway boundary condition; If the P value of any one of the plurality of characteristic quantity groups satisfies the thermal runaway boundary condition, then early warning information including the thermal runaway state of the electrochemical energy storage system is generated.

7. The method according to claim 6, characterized in that The dividing the plurality of feature quantities into a plurality of feature quantity groups comprises: The plurality of feature quantities are divided into 7 feature quantity groups, Among them, the seven characteristic quantity groups are voltage change rate and temperature change rate, maximum temperature and temperature change rate, minimum voltage and temperature change rate, temperature difference and temperature change rate, minimum voltage and maximum temperature, minimum voltage and temperature difference, temperature difference and maximum temperature.

8. A safety control method for an electrochemical energy storage system, characterized in that: The electrochemical energy storage system includes a plurality of cells to be tested, and the method includes: According to the electrochemical energy storage system early warning method according to any one of claims 1 to 7, a thermal runaway early warning is performed on the electrochemical energy storage system to obtain the early warning information; Safety control measures are performed on the electrochemical energy storage system according to the early warning information.

9. An electrochemical energy storage system early warning device, characterized in that: The electrochemical energy storage system includes a plurality of cells to be tested, and the device includes: A first collecting mechanism is used to collect the cell temperature and cell voltage of each of the cells to be tested; A feature extraction module, connected to the first acquisition mechanism, and used to obtain a plurality of feature quantities of each of the battery cells to be tested according to the battery cell temperature and the battery cell voltage; The early warning module is connected to the feature extraction module and is used to perform combined judgment on the multiple feature quantities based on the thermal runaway boundary conditions to obtain early warning information, wherein the early warning information is used to indicate the thermal runaway state of the electrochemical energy storage system.

10. The device according to claim 9, characterized in that The first acquisition mechanism includes: an optical fiber temperature sensor and a voltage sensor, The optical fiber temperature sensor is implanted in the center of the diaphragm inside the battery cell to be tested and connected to the feature extraction module to collect the battery cell temperature of the battery cell to be tested and send the collected battery cell temperature value to the feature extraction module.

11. The device according to claim 9, characterized in that The device also includes a determination module for determining thermal runaway boundary conditions; The determination module comprises: A second collecting mechanism is used to collect thermal runaway data and normal operating data of battery cells in the electrochemical energy storage system, wherein the thermal runaway data and normal operating data include the multiple characteristic quantities of the battery cells to be tested; a first calculation unit, connected to the second acquisition mechanism, and configured to calculate, based on the thermal runaway data and the normal operation data, a Mahalanobis distance between each characteristic quantity in the thermal runaway data and the normal operation data; A second calculation unit is connected to the first calculation unit, and is used to obtain a P value between each characteristic quantity in the thermal runaway data and the normal operation data according to the Mahalanobis distance between each characteristic quantity in the thermal runaway data and the normal operation data, wherein the P value is used to characterize the degree of difference between the thermal runaway data and the normal operation data. A determination unit is connected to the second calculation unit and is used to determine the thermal runaway boundary condition of the electrochemical energy storage system according to a P value between each characteristic quantity in the thermal runaway data and the normal operation data.

12. An energy storage device comprising: An electrochemical energy storage system, comprising a plurality of cells to be tested; The electrochemical energy storage system early warning device according to any one of claims 9 to 11 is used to provide a thermal runaway early warning for the electrochemical energy storage system.

Images