Early warning method and device for thermal runaway of energy storage battery

Abstract

The invention provides an early warning method and device for thermal runaway of an energy storage battery, and the method comprises the steps: installing a hydrogen and carbon monoxide gas sensor in a gas collection device, collecting the concentration data of hydrogen and carbon monoxide gas released by the side reaction of the battery, and respectively taking the data as a first early warning factor and a second early warning factor; gas concentration mutation rates of hydrogen and carbon monoxide are calculated in real time and serve as a third early warning factor and a fourth early warning factor respectively; 5 optical fiber temperature sensors are pre-embedded in the battery cell, the internal temperature of the single battery cell is detected, and the temperature average value of the 5 temperature sensors is taken as a fifth early warning factor; the temperature rise rates of the five temperature sensors are calculated, and the maximum value is taken as a sixth early warning factor; and carrying out weighted calculation on the six early warning factors to form a quantitative early warning value, and carrying out early warning by the BMS according to a calculation result. The technical problem that the reliability and the service life of the energy storage system are restricted due to the fact that the thermal runaway risk is difficult to find and process in time is solved.

Description

Technical Field

[0001] The present invention relates to the field of lithium battery energy storage control, and in particular to an early warning method and device for thermal runaway of an energy storage battery. Background Art

[0002] In the field of large-scale energy storage applications, smoke, fire, and explosion accidents caused by lithium-ion batteries pose a great threat to the safety of public life and property. In the early stage of thermal runaway of lithium-ion batteries, the characteristic identification parameters such as battery temperature, discharge voltage, and discharge current change very slowly. The battery management system (BMS) cannot detect battery failure early, and at this time, the electrochemical reaction inside the battery will produce a large amount of gas substances.

[0003] The existing invention patent application document with publication number CN118539051A is "A method, system and device for monitoring and processing thermal runaway of lithium battery storage". The existing method includes: building a sensor network model to obtain all data inside and outside the lithium battery; building a training early warning signal analysis model to obtain the early warning signal data of the battery sensor network model under working conditions, training the early warning signal analysis model according to the temperature data and voltage data, and obtaining the early warning signal analysis model, building a cooling system, and high-precision monitoring: through a variety of sensor networks, the real-time status of the battery can be more accurately monitored, including the temperature of every corner of the battery: through the early warning signal analysis system, the thermal runaway risk of the battery is monitored and predicted in real time, and heat dissipation operations are performed: the intelligent cooling system starts immediately at the moment when the possible thermal runaway risk begins to heat up, preventing the temperature from rising.

[0004] The above-mentioned prior art builds a method for handling thermal runaway by training early warning analysis models based on traditional perception systems. Model training requires more data to ensure the effectiveness of the model, and the signal characteristics of each thermal runaway are not completely consistent, especially for early warning, which is not very operable.

[0005] The existing invention patent application document "A method and system for predicting thermal runaway of energy storage batteries based on electrochemical mechanisms" with publication number CN117783885A, the existing method includes: collecting data samples of ambient temperature and output voltage of CO electrochemical sensor when abnormal conditions occur in energy storage batteries; performing data outlier test on the data samples; calculating the weighted average of the test data; obtaining the ambient temperature compensation coefficient; obtaining the electrode kinetics Butler-Volmer equation to obtain the output current density of the CO electrochemical sensor; obtaining the CO reaction rate of the CO electrochemical sensor; substituting the CO reaction rate into the logistic regression model to obtain the probability of thermal runaway.

[0006] The above-mentioned prior art collects the ambient temperature and the output voltage of the CO sensor, and predicts the probability of thermal runaway after data analysis and calculation. This is a method for calculating the probability of occurrence, and it is unable to clearly define the specific risks and specific operations to be taken under different probabilities.

[0007] The existing invention patent application document "Power battery thermal runaway advance warning method and system based on multi-source information fusion" with publication number CN116796285A, the existing method includes: the power battery thermal runaway advance warning method based on multi-source information fusion includes obtaining historical time series information of several evaluation indicators of the power battery; using multiple deep neural networks to process the historical time series information of each evaluation indicator respectively, and obtain the preliminary warning time of each evaluation indicator respectively; quantitatively assigning weight coefficients of the preliminary warning time of each evaluation indicator, and weighted summing them to obtain the comprehensive warning time to achieve thermal runaway advance warning.

[0008] The aforementioned prior art is applied to power batteries. By collecting time information of historical thermal runaway events and calculating the comprehensive warning time, the time series of historical events is applied to the warning process, which can only solve the problem of how long in advance the warning should be given.

[0009] The existing invention patent application document "Research on Very Early Warning Method and Technology for Thermal Runaway of Lithium-ion Batteries" proposes a method for constructing a warning indicator system based on thermal runaway data of large-capacity ternary lithium-ion power batteries. This paper combines the gas production and heat production mechanism of thermal runaway with experimental data to construct a warning indicator system integrating multi-point temperature, hydrogen, carbon monoxide, and hydrocarbon gas in the cell body; through thermal induced runaway experiments under three states of charge (SOC) of 100%, 60%, and 30%, the time series of the peak values ​​of each key indicator are characterized, and a dynamic warning indicator system integrating heat production and gas production category indicators is established, and the reliability of the warning indicators is analyzed; then the classification rules of the warning level and the input and output characteristics of the warning model are deeply analyzed, the redundant information of the warning indicator system is eliminated, the spatiotemporal characteristic indicator system composed of heat production and gas production is optimized, and the total data set of the thermal runaway warning model of the trinity of training, testing, and verification is created.

[0010] The above-mentioned existing literature proposes a method for constructing an early warning indicator system for ternary lithium power batteries, attempting to extract signal characteristics of different development stages of thermal runaway and establish a total data set of a thermal runaway early warning model, so as to simplify the early warning and response operations for thermal runaway of energy storage batteries.

[0011] In summary, the existing technology has the technical problem that the risk of thermal runaway is difficult to detect and deal with in a timely manner, which restricts the reliability and service life of the energy storage system. Summary of the invention

[0012] The technical problem to be solved by the present invention is: how to solve the technical problem in the prior art that the risk of thermal runaway is difficult to detect and handle in a timely manner, which restricts the reliability and service life of the energy storage system.

[0013] The present invention adopts the following technical solutions to solve the above technical problems: The early warning method for thermal runaway of energy storage batteries includes:

[0014] S1. Obtain the graded alarm threshold, process it to obtain the current warning judgment result, and process it to obtain the timing judgment criterion according to the graded alarm threshold and the current warning judgment result;

[0015] S2. Perform temperature acquisition and delay operations according to the timing criteria to obtain the temperature value;

[0016] S3. Calculate the average temperature, the internal temperature of the battery cell, and the sudden change rate of the internal temperature of the battery cell according to the temperature value;

[0017] S4. Using a hydrogen and carbon monoxide gas collection system, collect gas concentration values, and process the gas concentration value mutation rate to obtain the gas concentration value mutation rate, wherein the gas concentration value mutation rate includes: hydrogen concentration mutation rate and carbon monoxide concentration mutation rate;

[0018] S5, updating the sampled gas according to a preset update strategy through the sampled gas update valve;

[0019] S6. The gas concentration value, the gas concentration value mutation rate, the internal temperature of the battery cell and the internal temperature mutation rate of the battery cell are used as warning factors, and the warning factors are weighted to generate quantitative warning values. The BMS performs warning operations according to the quantitative warning values ​​to control the charging and discharging operations.

[0020] The present invention aims at the characteristic of lithium-ion battery, which is a completely closed system, that the surface temperature and internal temperature differ greatly. By monitoring the internal temperature of the battery, the identification parameters required for state estimation are improved, and the risk of thermal runaway of the battery is more accurately assessed. It is also of great value in the early warning of thermal runaway of lithium-ion batteries. The present invention solves the problem of early warning of thermal runaway of lithium-ion batteries. The present invention can detect the risk of thermal runaway early, deal with the risk in time, ensure the reliability of the energy storage system, extend the service life of lithium batteries, improve the safety of lithium-ion batteries, and protect the lives and property of the people.

[0021] In a more specific technical solution, S1 includes:

[0022] S11, perform system initialization operation and read the graded alarm threshold;

[0023] S12, according to the graded alarm threshold and delay data, processing to obtain the current warning judgment result;

[0024] S13, summarizing and calculating the graded alarm threshold, delay data and current warning judgment result to obtain the timing judgment criterion.

[0025] In a more specific technical solution, S2 includes:

[0026] S21, determining whether the preset time in the timing criterion has been reached;

[0027] S22, if not, then perform a delay operation;

[0028] S23: If yes, use the preset internal data collection system of the battery cell to collect the temperature value.

[0029] In a more specific technical solution, in S23, the internal temperature collection system of the battery cell includes: no less than 2 optical fiber temperature sensors and a BMS; the optical fiber temperature sensors are evenly arranged at preset temperature collection positions in the battery cell.

[0030] In more specific technical solutions, S3 includes:

[0031] S31, using the BMS to collect and calculate the average value of each temperature value as the internal temperature value of the battery cell;

[0032] S32, using the BMS to calculate the temperature mutation rate of each optical fiber temperature sensor according to the temperature value;

[0033] S33. From each temperature mutation rate, take the maximum value as the internal temperature mutation rate of the battery cell.

[0034] The present invention detects the early signal characteristics of the temperature change inside the battery cell and the release of flammable gases such as hydrogen and carbon monoxide in the early stage of thermal runaway of the lithium-ion battery, so as to detect the risk of thermal runaway at an early stage.

[0035] In a more specific technical solution, in S4, the hydrogen and carbon monoxide gas collection system includes: a hydrogen sensor, a carbon monoxide sensor, a collection device and a sampling gas update valve, and the hydrogen sensor and the carbon monoxide sensor are installed in the collection device.

[0036] The present invention adopts a method of directly collecting and calculating the internal temperature and temperature mutation rate of the battery cell using a built-in sensor, and combined with the over-temperature gas release situation, it can judge that the temperature rise is too fast early and reduce the occurrence of the final thermal runaway situation.

[0037] In a more specific technical solution, S4 includes:

[0038] S41, collecting hydrogen concentration values ​​using a hydrogen sensor; collecting carbon monoxide concentration values ​​using a carbon monoxide sensor;

[0039] S42, using BMS to read the hydrogen concentration value and the carbon monoxide concentration value;

[0040] S43. Calculate the hydrogen concentration mutation rate based on the hydrogen concentration value; calculate the carbon monoxide concentration mutation rate based on the carbon monoxide concentration value.

[0041] In a more specific technical solution, in S43, the hydrogen concentration mutation rate and the carbon monoxide concentration mutation rate are calculated using the following logic:

[0042] Mutation rate = (current value - last minute value) / last minute value * 100%.

[0043] In a more specific technical solution, S6 includes:

[0044] S61. When the warning operation is determined to be a third-level warning, the warning information is sent to an upper level;

[0045] S62, when it is determined that the warning operation is a second-level alarm, sending alarm information to prohibit charging and discharging operations;

[0046] S63: When it is determined that the warning operation is a first-level alarm, the alarm information is sent to the upper part, the charging and discharging operations are prohibited, the preset delay time is set, and the battery circuit is disconnected.

[0047] The effective range of the calculated value of the alarm signal of the present invention is large, and the size of the alarm threshold at each level can be adjusted according to the actual operating conditions to improve the warning effect. The application object of the present invention is the energy storage battery, and a specific warning level is given by calculation, and finally specific actions such as prohibiting charging and discharging, disconnecting the battery circuit, etc. are taken. This application is an early warning method for thermal runaway of energy storage batteries, and different operations are performed for different warning levels to ensure the functional safety of the energy storage system.

[0048] While collecting the internal temperature, hydrogen concentration and carbon monoxide concentration of the battery cell, the present invention calculates the mutation rate of related quantities, assigns different weights to the collected values ​​and mutation rate values ​​in combination with the characteristics of the energy storage battery, performs real-time warnings based on the calculation results, and performs different operations for different warning levels.

[0049] In a more specific technical solution, the energy storage battery thermal runaway early warning device includes:

[0050] A timing criterion acquisition module is used to obtain the graded alarm threshold value, and process it to obtain the current early warning judgment result. According to the graded alarm threshold value and the current early warning judgment result, the timing criterion is processed;

[0051] The temperature data acquisition module is used to perform temperature acquisition operation and delay operation according to the timing criterion to obtain the temperature value. The temperature data acquisition module is connected to the timing criterion acquisition module;

[0052] A temperature factor calculation module is used to calculate the temperature average value, the internal temperature of the battery cell and the internal temperature mutation rate of the battery cell according to the temperature value. The temperature factor calculation module is connected to the temperature data acquisition module;

[0053] The concentration factor calculation module is used to collect gas concentration values ​​using hydrogen and carbon monoxide gas collection systems, and process the gas concentration value mutation rate accordingly, wherein the gas concentration value mutation rate includes: hydrogen concentration mutation rate and carbon monoxide concentration mutation rate;

[0054] A gas updating module, used for updating the sampled gas according to a preset updating strategy through a sampled gas updating valve, the gas updating module being connected to the concentration factor calculation module;

[0055] The weighted calculation and early warning module is used to take the gas concentration value, the gas concentration value mutation rate, the internal temperature of the battery cell and the internal temperature mutation rate of the battery cell as early warning factors, and perform weighted calculation on the early warning factors to generate quantitative early warning values. The BMS performs early warning operations according to the quantitative early warning values ​​to control the charging and discharging operations. The weighted calculation and early warning module is connected to the concentration factor calculation module and the temperature factor calculation module.

[0056] Compared with the prior art, the present invention has the following advantages:

[0057] The present invention aims at the characteristic of lithium-ion battery, which is a completely closed system, that the surface temperature and internal temperature are quite different. By monitoring the internal temperature of the battery, the identification parameters required for state estimation are improved, and the risk of thermal runaway of the battery is more accurately assessed. This is also of great value in the early warning of thermal runaway of lithium-ion batteries. The present invention solves the problem of early warning of thermal runaway of lithium-ion batteries. The present invention can detect the risk of thermal runaway early, deal with the risk in time, ensure the reliability of the energy storage system, extend the service life of lithium batteries, improve the safety of lithium-ion batteries, and protect the lives and property of the people.

[0058] The present invention detects the early signal characteristics of the temperature change inside the battery cell and the release of flammable gases such as hydrogen and carbon monoxide in the early stage of thermal runaway of the lithium-ion battery, so as to detect the risk of thermal runaway at an early stage.

[0059] The effective range of the calculated value of the alarm signal of the present invention is large, and the size of the alarm thresholds at each level can be adjusted according to the actual operating conditions to improve the early warning effect.

[0060] The present invention solves the technical problem in the prior art that the risk of thermal runaway is difficult to detect and handle in a timely manner, which restricts the reliability and service life of the energy storage system. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 This is a schematic diagram of the basic steps of the energy storage battery thermal runaway early warning method according to Example 1 of the present invention;

[0062] Figure 2 This is a schematic diagram of the distribution of the optical fiber temperature sensor in Example 1 of the present invention inside the battery core;

[0063] Figure 3 This is a schematic diagram of a hydrogen and carbon monoxide gas collection device according to Example 1 of the present invention. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in combination with the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] Example 1

[0066] like Figure 1 As shown, the energy storage battery thermal runaway early warning method provided by the present invention includes the following basic steps:

[0067] S1, system initialization;

[0068] S2, read the alarm threshold;

[0069] In this embodiment, the third-level alarm threshold can be set to, for example, 4500; the second-level alarm threshold can be set to, for example, 5500; the first-level alarm threshold can be set to, for example, 6000;

[0070] S3, summarizing the alarm threshold, delay data and current warning judgment results to obtain the timing judgment criteria;

[0071] S4, determining whether the preset time has been reached;

[0072] In this embodiment, the preset time can be set to, for example, 1 minute.

[0073] S5. If not, it is determined to perform a delay operation;

[0074] S6. If yes, collect the temperature values ​​of 5 temperature sensors;

[0075] The battery cell internal temperature acquisition system used in this embodiment includes but is not limited to: 5 optical fiber temperature sensors and BMS;

[0076] like Figure 3 As shown, in this embodiment, the aforementioned five optical fiber temperature sensors are arranged inside the battery core, and the optical fiber temperature sensors are evenly distributed inside the battery core. The BMS collects and calculates the average temperature of the five temperature sensors as the internal temperature value of the battery core. The BMS collects and calculates the temperature mutation rate of the five temperature sensors, and takes the maximum value as the internal temperature mutation rate of the battery core.

[0077] S7, calculating the average temperature and mutation rate;

[0078] S8, read the concentration value of the hydrogen sensor;

[0079] S9, calculating the mutation rate of hydrogen concentration;

[0080] S10, reading the concentration value of the carbon monoxide sensor;

[0081] In this embodiment, a hydrogen and carbon monoxide gas collection system is set up, and hydrogen and carbon monoxide gas sensors are installed in the collection device to collect the gas concentrations of the two gases. The BMS reads the collection results, and after the collection is completed, the sampled gas is updated through the update valve;

[0082] like Figure 2 As shown, in this embodiment, the hydrogen and carbon monoxide gas collection system further includes: a gas collection hood 1 and a sampled gas update valve 2. Specifically, the gas update valve updates the sampled gas once a minute according to the collection calculation rhythm.

[0083] The components of the hydrogen and carbon monoxide concentration collection system used in this embodiment include but are not limited to: a gas collection hood 1, a sampling gas update valve 2, a hydrogen detector 3, a carbon monoxide detector 4 and a BMS gas collection system; in this embodiment, the hydrogen detector 3 and the carbon monoxide detector 4 are arranged in the connecting pipe between the gas collection hood 1 and the sampling gas update valve 2.

[0084] S11, calculating the mutation rate of carbon monoxide concentration;

[0085] In this embodiment, the calculation formulas for the concentration of hydrogen, carbon monoxide, and the sudden change rate of the internal temperature of the battery cell are as follows:

[0086] Mutation rate = (current value - last minute value) / last minute value * 100%

[0087] In this embodiment, the average temperature values ​​of 5 optical fiber temperature sensors and the gas concentration values ​​of hydrogen and carbon monoxide gas sensors are read every minute, and the temperature mutation rate, hydrogen concentration mutation rate and carbon monoxide gas concentration mutation rate are calculated respectively;

[0088] S12, updating the sampling gas;

[0089] In this embodiment, the control strategy of the sampling gas update valve 2 is to update once the gas concentration detection is completed and update once every minute;

[0090] S13, weighted calculation of quantitative warning values;

[0091] In this embodiment, the warning factors are weighted and calculated to form a quantitative warning value, and the BMS issues a warning according to the calculation result; in this embodiment, the warning factors include but are not limited to: hydrogen concentration, carbon monoxide concentration, hydrogen concentration mutation rate, carbon monoxide concentration mutation rate, battery cell internal temperature, and battery cell internal temperature mutation rate;

[0092] In this embodiment, the logic that may be used for weighted calculation includes but is not limited to:

[0093] Calculated value = (hydrogen concentration - 50) * 200 + (carbon monoxide concentration - 50) * 200 + hydrogen concentration mutation rate * 200 + carbon monoxide concentration mutation rate * 200 + (cell internal temperature - 30) * 100 + cell internal temperature mutation rate * 100

[0094] In order to improve the warning effect, the calculation weights are set at a comparable level according to the contribution of the collected values ​​and mutation rates to the calculation results.

[0095] The calculation range of hydrogen and carbon monoxide concentration includes but is not limited to: 50-1000ppm, and the mutation rate is in percentage. When the collected values ​​of hydrogen and carbon monoxide concentration are below 50ppm, 50ppm is taken, and the mutation rate is 0. When the collected value of the internal temperature of the battery cell is below 30℃, 30℃ is taken, and the mutation rate is 0.

[0096] S14: Early warning judgment and processing.

[0097] The warning method adopted in this embodiment can be, for example: the third-level alarm sends alarm information; specifically, the second-level alarm prohibits charging and discharging in addition to sending alarm information; the first-level alarm, in addition to sending alarm information and prohibiting charging and discharging, delays 1.5 seconds to disconnect the battery circuit.

[0098] The present invention aims at the characteristic of lithium-ion battery, which is a completely closed system, that the surface temperature and internal temperature are quite different. By monitoring the internal temperature of the battery, the identification parameters required for state estimation are improved, and the risk of thermal runaway of the battery is more accurately assessed. This is also of great value in the early warning of thermal runaway of lithium-ion batteries. The present invention solves the problem of early warning of thermal runaway of lithium-ion batteries. The present invention can detect the risk of thermal runaway early, deal with the risk in time, ensure the reliability of the energy storage system, extend the service life of lithium batteries, improve the safety of lithium-ion batteries, and protect the lives and property of the people.

[0099] The present invention detects the early signal characteristics of the temperature change inside the battery cell and the release of flammable gases such as hydrogen and carbon monoxide in the early stage of thermal runaway of the lithium-ion battery, so as to detect the risk of thermal runaway at an early stage.

[0100] The effective range of the calculated value of the alarm signal of the present invention is large, and the size of the alarm thresholds at each level can be adjusted according to the actual operating conditions to improve the early warning effect.

[0101] The present invention solves the technical problem in the prior art that the risk of thermal runaway is difficult to detect and handle in a timely manner, which restricts the reliability and service life of the energy storage system.

[0102] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An early warning method for thermal runaway of energy storage batteries, characterized in that: The method comprises: S1. Obtaining a graded alarm threshold, processing the threshold to obtain a current warning determination result, and processing the graded alarm threshold and the current warning determination result to obtain a timing determination criterion; S2. Perform temperature acquisition and delay operations according to the timing criterion to obtain a temperature value; S3. Calculate the temperature average value, the internal temperature of the battery cell, and the internal temperature mutation rate of the battery cell according to the temperature value; S4. Using a hydrogen and carbon monoxide gas collection system, collect gas concentration values, and process the gas concentration value mutation rate to obtain the gas concentration value mutation rate, wherein the gas concentration value mutation rate includes: hydrogen concentration mutation rate and carbon monoxide concentration mutation rate; S5, updating the sampled gas according to a preset update strategy through the sampled gas update valve; S6. The gas concentration value, the gas concentration value mutation rate, the internal temperature of the battery cell and the internal temperature mutation rate of the battery cell are used as warning factors, and the warning factors are weightedly calculated to generate a quantitative warning value. The BMS performs a warning operation according to the quantitative warning value to control the charging and discharging operation.

2. The method for early warning of thermal runaway of energy storage batteries according to claim 1, characterized in that: The S1 includes: S11, performing system initialization operation and reading the graded alarm threshold; S12, processing to obtain the current warning determination result according to the graded alarm threshold and delay data; S13, summarizing and calculating the graded alarm threshold, the delay data and the current warning determination result to obtain the timing criterion.

3. The method for early warning of thermal runaway of energy storage batteries according to claim 1, characterized in that: The S2 includes: S21, determining whether the preset time in the timing criterion has been reached; S22, if not, then perform the delay operation; S23: If yes, use the preset internal data collection system of the battery cell to collect the temperature value.

4. The method for early warning of thermal runaway of energy storage batteries according to claim 3, characterized in that: In S23, the battery cell internal temperature collection system includes: no less than 2 optical fiber temperature sensors and a BMS; the optical fiber temperature sensors are evenly arranged at preset temperature collection positions in the battery cell.

5. The method for early warning of thermal runaway of energy storage batteries according to claim 1, characterized in that: The S3 includes: S31, using the BMS to collect and calculate the average value of each temperature value as the internal temperature value of the battery cell; S32, using the BMS to calculate the temperature mutation rate of each of the optical fiber temperature sensors according to the temperature value; S33. From the temperature mutation rates, take the maximum value as the temperature mutation rate inside the battery cell.

6. The method for early warning of thermal runaway of energy storage batteries according to claim 1, characterized in that: In S4, the hydrogen and carbon monoxide gas collection system includes: a hydrogen sensor, a carbon monoxide sensor, a collection device and a sampling gas update valve, and the hydrogen sensor and the carbon monoxide sensor are installed in the collection device.

7. The method for early warning of thermal runaway of energy storage batteries according to claim 1, characterized in that: The S4 includes: S41, collecting hydrogen concentration values ​​using a hydrogen sensor; collecting carbon monoxide concentration values ​​using a carbon monoxide sensor; S42, using BMS to read the hydrogen concentration value and the carbon monoxide concentration value; S43. Calculate the hydrogen concentration mutation rate according to the hydrogen concentration value; calculate the carbon monoxide concentration mutation rate according to the carbon monoxide concentration value.

8. The method for early warning of thermal runaway of energy storage batteries according to claim 7, characterized in that: In S43, the hydrogen concentration mutation rate and the carbon monoxide concentration mutation rate are calculated using the following logic: Mutation rate = (current value - last minute value) / last minute value * 100%.

9. The method for early warning of thermal runaway of energy storage batteries according to claim 1, characterized in that: The S6 includes: S61, when it is determined that the warning operation is a third-level alarm, sending alarm information; S62, when it is determined that the warning operation is a second-level alarm, sending the alarm information to prohibit charging and discharging operations; S63: When it is determined that the warning operation is a first-level alarm, the alarm information is sent to an upper layer, the charging and discharging operation is prohibited, the delay is set to a preset time, and the battery circuit is disconnected.

10. An early warning device for thermal runaway of energy storage batteries, characterized in that: The device comprises: A timing criterion acquisition module is used to obtain a graded alarm threshold value, and process it to obtain a current early warning determination result, and process it to obtain a timing criterion according to the graded alarm threshold value and the current early warning determination result; A temperature data acquisition module, used to perform temperature acquisition operation and delay operation according to the timing criterion to obtain a temperature value, the temperature data acquisition module is connected to the timing criterion acquisition module; A temperature factor calculation module, used to calculate the temperature average value, the internal temperature of the battery cell and the internal temperature mutation rate of the battery cell according to the temperature value, and the temperature factor calculation module is connected to the temperature data acquisition module; A concentration factor calculation module is used to collect gas concentration values ​​using hydrogen and carbon monoxide gas collection systems, and process the collected gas concentration values ​​to obtain gas concentration value mutation rates, wherein the gas concentration value mutation rates include: hydrogen concentration mutation rate and carbon monoxide concentration mutation rate; A gas updating module, used for updating the sampled gas according to a preset updating strategy through a sampled gas updating valve, the gas updating module being connected to the concentration factor calculating module; The weighted calculation and early warning module is used to use the gas concentration value, the gas concentration value mutation rate, the internal temperature of the battery cell and the internal temperature mutation rate of the battery cell as early warning factors, and perform weighted calculation on the early warning factors to generate a quantitative early warning value. The BMS performs early warning operations according to the quantitative early warning value to control the charging and discharging operations. The weighted calculation and early warning module is connected to the concentration factor calculation module and the temperature factor calculation module.

Images