Energy storage device safety protection early warning system applied to industrial park

Abstract

The application belongs to the technical field of safety protection, and specifically relates to an energy storage equipment safety protection early warning system applied to an industrial park. The system adopts a three-level architecture of'module-cluster-cabin' to realize real-time monitoring and dynamic evaluation of thermal runaway risks. The architecture integrates multiple sources of data. When the risk exceeds a preset threshold, the system will automatically start a graded fire extinguishing measure and a fire linkage mechanism. Meanwhile, the cloud platform is relied on to perform secondary analysis on the early warning result to optimize the model parameters, so as to ensure the accuracy and efficiency of the system. The system constructs an integrated monitoring, response and self-correction prevention and control process. The energy storage equipment safety protection system effectively overcomes the problems of early warning delay, high false alarm rate, single protection means and data island in the prior art through multi-parameter fusion early warning, accurate identification, graded fire extinguishing and intelligent linkage mechanism, and provides solid protection for fire safety in a high-density energy storage environment.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of safety protection, and particularly relates to a prewarning system, and particularly discloses a safety protection prewarning system for energy storage equipment applied to an industrial park. BACKGROUND

[0002] With the promotion of the "double carbon" strategy, electrochemical energy storage systems represented by lithium ion batteries are rapidly popularized in industrial parks. However, safety accidents such as fires and explosions caused by thermal runaway of energy storage equipment have become a core bottleneck restricting the large-scale development of the industry.

[0003] At present, most industrial parks adopt a traditional safety protection system, which relies on a BMS (battery management system) to monitor single-dimensional parameters such as voltage and temperature of a battery pack through threshold monitoring, and a fire detection network is formed by configuring a smoke detector (photoelectric / ion type) and a temperature sensor (NTC thermistor). The trigger threshold of the fire detection network is generally set to be above 150 DEG C. When visible smoke or high temperature is detected, a full-flooding gas fire extinguishing device is started in linkage. The fire extinguishing system started after the alarm is mostly full-flooding. Although this scheme can achieve effective fire extinguishing in the flaming stage, it has four core defects:

[0004] 1. It cannot identify risks in the early stage of thermal runaway, such as the hydrogen evolution stage of the battery;

[0005] 2. A single sensor is easily disturbed by the environment, such as dust and humidity, leading to misjudgment;

[0006] 3. It cannot accurately suppress local thermal runaway, causing secondary damage to the equipment;

[0007] 4. There is a lack of data linkage between the battery management system, the environmental monitoring system and the fire extinguishing system, making it difficult to achieve active protection.

[0008] Therefore, it is necessary to provide an energy storage equipment safety protection system with multi-parameter fusion prewarning, accurate identification, hierarchical fire extinguishing and intelligent linkage. SUMMARY

[0009] Therefore, the application provides an energy storage equipment safety protection prewarning system for an industrial park. A "module-cluster-cabin" three-level architecture is adopted to realize real-time monitoring and dynamic evaluation of thermal runaway risks. The architecture integrates multiple data sources. When the risk exceeds a preset threshold, the system will automatically start hierarchical fire extinguishing measures and fire linkage mechanisms. At the same time, the effectiveness of the protection measures is verified through a safety feedback module. The system builds an integrated monitoring, response and self-correction prevention and control process, solving the problems of prewarning lag, high false alarm rate, single protection means and data island in the prior art.

[0010] The application can be realized by the following technical scheme: an energy storage equipment safety protection prewarning system applied to an industrial park, comprising:

[0011] The park architecture planning module: based on the data location characteristics, the park map information is imported into the cloud, the location area is constructed, and is respectively recorded as a battery module area, a cluster level area and a cabin level area;

[0012] The detection data set acquisition module: for data acquisition in the battery module area, the cluster level area and the cabin level area, respectively obtaining a primary data text, a secondary data text and a tertiary data text;

[0013] The text data preprocessing module: for data integration of the primary data text, the secondary data text and the tertiary data text, obtaining a primary integrated data text, a secondary integrated data text and a tertiary integrated data text;

[0014] The integrated data analysis module: for importing the primary integrated data text, the secondary integrated data text and the tertiary integrated data text into the risk control data calculation model, obtaining a thermal runaway risk index R;

[0015] The early warning signal generation module: for analyzing the thermal runaway risk index R, and generating an early warning signal to the cloud;

[0016] The database secondary construction module: for secondary analysis after receiving the early warning signal, generating a hierarchical early warning signal to the cloud;

[0017] The safety protection module: for starting a hierarchical fire extinguishing device according to the hierarchical early warning signal;

[0018] The fire linkage module: for taking different measures according to the hierarchical early warning signal;

[0019] The safety feedback module: for feedback on the safety protection and fire linkage results, judging whether the safety protection and fire linkage are successful;

[0020] The safety evaluation module: for analyzing the safety evaluation coefficient of each specified detection area and processing.

[0021] In combination with all the technical solutions described above, the present application has the following positive effects:

[0022] 1. The present application realizes the effect of early warning, specifically: breaking through the limitation of single physical quantity monitoring, realizing effective intervention before the irreversible stage of thermal runaway through electric-thermal-gas multi-modal data fusion;

[0023] 2. The present application realizes the effect of accurate judgment, specifically: adopting a multi-source data anti-interference checking mechanism to eliminate abnormal values and perform safety evaluation to eliminate the risk of misoperation caused by environmental interference;

[0024] 3. The application realizes the role of precise treatment, specifically: based on the heat runaway propagation path (module -> cluster -> cabin), a differentiated fire extinguishing strategy is designed, taking into account the suppression efficiency and equipment protection;

[0025] 4. The application realizes the role of fast coordination, specifically: a cross-system data real-time interaction channel is constructed to realize millisecond-level linkage scheduling of BMS, environmental monitoring and fire resources. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of these drawings.

[0027] ATTACHMENT Figure 1 is the workflow diagram of the present application.

[0028] ATTACHMENT Figure 2 is the device connection diagram of the present application.

[0029] ATTACHMENT Figure 3 is the data acquisition step diagram of the present application. DETAILED DESCRIPTION

[0030] The technical solutions of the present application will be described in detail below in conjunction with the embodiments. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0031] Referring to Figure 1 and Figure 2 , the present application proposes an energy storage equipment safety protection early warning system applied to an industrial park, characterized in that it comprises a park architecture planning module, a detection data set acquisition module, a text data preprocessing module, an integrated data analysis module, a database secondary construction module, a safety protection module, a fire linkage module, a safety feedback module and a safety evaluation module.

[0032] In a more specific application of the present application, the park architecture planning module imports park map information into the cloud based on data location characteristics, constructs location areas, and is respectively marked as battery module area, cluster level area and cabin level area.

[0033] Among them, the module level area installs aerosol fire extinguishing device in the battery module, covering a single battery cell heat runaway; the module level database stores the temperature, voltage and current data corresponding to a single battery module, and the data acquisition interval is second.

[0034] Cluster level region Deploy perfluorocyclohexone directional spray device on top of battery cluster cabinet; Cluster level database Store gas concentration distribution matrix and thermal imaging data of battery cluster level, data collection interval seconds.

[0035] Cabin level region Configure heptafluoropropane full-flooding system in container; Cabin level database Store cabin structure stress monitoring data and pressure fluctuation curve, data collection interval minutes.

[0036] The detection data set acquisition module is used for data collection in the battery module region, the cluster level region and the cabin level region, to obtain first data text, second data text and third data text, respectively, and the data collection steps are as shown in Figure 3 , and specifically are:

[0037] A1, respectively, in the battery module region, the cluster level region and the cabin level region Set up a collection end;

[0038] A2, collect the data of the collection end to obtain the total sum of temperature data, combustible gas data, smoke data and current / voltage data;

[0039] A3, based on the total sum of data, data construction is carried out to obtain the module level database, the cluster level database and the cabin level database;

[0040] A4, wherein the data in the module level database, the cluster level database and the cabin level database are respectively recorded as first data text, second data text and third data text.

[0041] Among them, multiple source sensors are installed on the collection end, and the multiple source sensors include temperature sensors, hot spot sensors, combustible gas sensors, smoke sensors and current / voltage sensors.

[0042] The text data preprocessing module is used for data integration of the first data text, the second data text and the third data text, and the first data text, the second data text and the third data text are integrated before being processed, and the processing steps are as follows:

[0043] Data cleaning is performed to eliminate outliers, i.e. data points exceeding 3 times the standard deviation range;

[0044] Format standardization is performed to convert multiple source heterogeneous data into JSON format with unified timestamp;

[0045] Feature enhancement, adding gradient change label to temperature data, The time mark is a red warning section.

[0046] The processed data text is a primary integrated data text, a secondary integrated data text and a tertiary integrated data text, and the integration process of the primary integrated data text is specifically introducing the primary data text into a primary calculation model, wherein the primary calculation model comprises a temperature model, a combustible gas model, a smoke model and a voltage / current parameter model.

[0047] It should be noted that the temperature model comprises a battery module surface temperature change rate coefficient, denoted as , an in-cabin environment temperature coefficient, denoted as , and an intra-battery cluster temperature difference coefficient, denoted as .

[0048] The battery module surface temperature change rate coefficient is specifically:

[0049] ;

[0050] Since is an industry standard high-risk threshold, exceeding this value indicates that thermal runaway is accelerating, is an extreme limit, so the range is divided into , and for segmented design.

[0051] Wherein is the temperature change of the battery module surface, , , and M is a specific value between 5 and 8, and N is a specific value between 15 and 18. The main value is set based on the condition of ensuring the thermal safety of the battery module. The main purpose of the embodiment is to limit the range that the industry standard high-risk threshold may set in actual conditions. Therefore, the specific values of M and N are not limited.

[0052] In a low-risk scenario:

[0053] ;

[0054] At this time is a slow spontaneous heating stage, is the contribution value of the temperature change rate in the low-risk scenario, and the value is between 0.15 and 0.25. The specific value is determined according to the actual situation.

[0055] In a high-risk scenario:

[0056] ;

[0057] At this time , the risk increases with the temperature increase in a power-law manner, and the internal short circuit triggers a chain heat release reaction, which is non-linear acceleration, The contribution value of the temperature change rate of the battery module is 0.25-0.35, and the specific value is determined according to the actual situation, and the value of b is set to be 1.2-1.5.

[0058] For example, when the surface temperature change =10 , take =0.2, =0.3, T=15, t=5, b=1.5,

[0059] ;

[0060] That is, when the surface temperature change =10 , the contribution value of the temperature change rate of the battery module is 0.3.

[0061] In an extreme scenario:

[0062] ;

[0063] At this time , it is an extreme event such as explosion, so the saturation limit is made, that is, the maximum contribution of the temperature change rate is 0.5, accounting for 50% of the total weight of the temperature parameter.

[0064] The cabin environment temperature coefficient is specifically: when F℃,

[0065] ;

[0066] Since the upper limit of the working temperature of most energy storage systems is F-G℃, exceeding this range may lead to performance degradation or thermal runaway, F℃ is selected as the threshold to give an early warning, and the higher the temperature, the greater the risk of pyrolysis of materials in the cabin, failure of equipment heat dissipation or self-ignition of combustible materials, so an exponential function is introduced to strengthen the high-temperature risk.

[0067] Wherein is the real-time environment temperature in the cabin, and the threshold temperature is F℃, which is the critical value of triggering temperature risk, and when the temperature is lower than the threshold temperature, .

[0068] The higher the temperature, the greater the risk of pyrolysis of materials in the cabin, failure of equipment heat dissipation or self-ignition of combustible materials, wherein the range of F is 35-45, and the range of G is 45-55, and the main value is set to limit the upper limit of the working temperature of the energy storage system in the actual situation, therefore, the specific values of F and G are not limited.

[0069] The coefficient raises the temperature rise amount (T-T0) by an exponential function ) is mapped to a risk contribution value, ranging from where a reflects the contribution of the real-time ambient temperature in the cabin to the temperature model, and the value is any data between 0.35 and 0.45, and the specific value is determined according to the actual situation.

[0070] where the coefficient is used to control the exponential growth rate of temperature risk accumulation, and when the ambient temperature increases by q °C, the exponential term increases by 1.

[0071] For example, the coefficient is used to control the exponential growth rate of temperature risk accumulation, and when the coefficient is 0.1, the ambient temperature increases by 10 °C, the exponential term increases by 1, and the increase of the formula is This growth rate is consistent with the change trend of the activation energy in the Arrhenius equation of the lithium battery electrolyte decomposition reaction; when (i.e., more than the threshold of 10 °C), the coefficient 0.1 makes the risk value reach about 63% of the maximum value , which is consistent with the experimentally measured inflection point of the thermal runaway trigger probability.

[0072] The temperature difference coefficient in the battery cluster is specifically:

[0073] ;

[0074] where is the highest temperature in the cluster, is the lowest temperature in the cluster, is the average temperature in the cluster,

[0075] ;

[0076] n is the total number of temperature measurements, is the temperature of any one measurement.

[0077] It should be noted that the flammable gas model is specifically a flammable gas concentration rising coefficient, denoted as ;

[0078] The flammable gas concentration rising coefficient is specifically:

[0079] ;

[0080] where represents the real-time concentration of flammable gas in the cabin, measured in lower explosive limit percentage (%LEL), and 1%LEL is 1% of the lower explosive limit, i.e., one hundredth of the minimum flammable concentration, and in the formula For normalization operation, the actual concentration is converted into a multiple of 1% LEL, which is convenient for unified calculation (eliminate dimension).

[0081] wherein the concentration term reflects the linear relationship between the current concentration and the reference value (1% LEL), and the coefficient control sensitivity, the value of which is any data between 0.1 and 0.2, and the specific value is determined according to the actual situation.

[0082] wherein the temperature linkage term introduces a temperature change coefficient, such as a temperature difference correction factor, to reflect the influence of temperature on gas diffusion and reaction rate, and when the temperature change rate increases, the gas risk weight is automatically increased, the value of which is any data between 0 and 0.1, and the specific value is determined according to the actual situation.

[0083] wherein the upper limit constraint , the value of m is 0.3, indicating that the maximum contribution of the combustible gas concentration increase rate is 0.3, to avoid excessive amplification of the risk value in extreme scenarios.

[0084] It should be noted that the smoke model is specifically a smoke particle concentration coefficient, denoted as :

[0085] The smoke particle concentration coefficient is specifically:

[0086] ;

[0087] wherein is the real-time smoke particle concentration, is the reference smoke particle concentration, is the upper limit of the sensor range;

[0088] It should be noted that the voltage / current parameter model is unified and integrated into an electrical imbalance coefficient, denoted as :

[0089] The electrical imbalance coefficient is specifically:

[0090] ;

[0091] wherein is the actual measured voltage, is the nominal voltage of the battery, is the actual measured current, is the rated current of the battery, and 0.5 is the weight proportion of the current and voltage parameters, each accounting for half.

[0092] The voltage abnormality term quantifies the degree of voltage deviation from the nominal value, reflecting the risk of over-discharge;

[0093] When The normal state, at this time the molecule is 0, the voltage term contributes 0;

[0094] When The over-discharge state, at this time the molecule is positive, the voltage abnormal value increases;

[0095] When the voltage is lower than the nominal value by 20%, the over-discharge protection threshold is triggered.

[0096] The current abnormality term quantifies the proportion of current exceeding the rated value, reflecting the risk of short circuit or overcurrent;

[0097] When The normal state, at this time the molecule is 0, the current term contributes 0;

[0098] When The overcurrent state, at this time the molecule is positive, the current abnormal value increases;

[0099] If the current reaches 150% of the rated value, it represents overcurrent.

[0100] The integrated data analysis module is used to import the primary integrated data text, the secondary integrated data text and the tertiary integrated data text into the risk control data calculation model to obtain the thermal runaway risk index R.

[0101] Based on the integrated data text aggregation result output by the primary model, the thermal runaway risk index R is dynamically calculated through the weight coefficient iteration of the risk control model, and the formula is as follows:

[0102] ;

[0103] Among them , , and represent the weight factor, and the weight distribution formula design principle is: the temperature parameter reflects the direct correlation between thermal runaway and system explosion risk, the flammable gas system number reflects the sudden change of gas concentration indicating extreme events, the smoke coefficient reflects the positive correlation between the concentration of combustion products and the size of the fire, and the electrical parameter abnormality reflects the overcharge / overdischarge induced chain reaction.

[0104] The dynamic adjustment range is: ;

[0105] The dynamic weight adjustment mechanism is:

[0106] In a high temperature environment (cabin temperature > X), the temperature parameter weight , other parameters are compressed in proportion, where the conventional value of X is 40-50℃, which is not limited in the embodiment;

[0107] CO concentration detected At that time, the weight of the smoke coefficient Combustible gas weight The typical value of Y is between 50 and 60. This embodiment does not impose specific limitations on the specific context;

[0108] Voltage abnormality ( ), electrical parameter weights Temperature weighting The typical value of Z is between 20 and 30. This embodiment does not impose specific limitations on the terms.

[0109] The early warning signal generation module is used to analyze the thermal runaway risk index R and generate early warning signals to the cloud. The working mechanism of the early warning signal generation module is as follows:

[0110] When the comprehensive risk index R reaches or exceeds the low-risk threshold r, the system will immediately trigger an early warning mechanism to ensure that timely measures are taken to prevent potential safety accidents. Here, the value of r is between 0.4 and 0.5.

[0111] Conversely, when the comprehensive risk index R is lower than r, the system will execute the regular monitoring mode. In the regular monitoring mode, the system will automatically generate a health report of the energy storage equipment every hour to continuously track the operating status of the equipment and ensure that it is in good working condition.

[0112] The database secondary construction module is used to perform secondary analysis after receiving the early warning signal, generate graded early warning signals to the cloud platform, and trigger graded early warning signals based on the thermal runaway risk index R after the fire is confirmed.

[0113] when When a Level 1 warning is triggered, A level 2 warning is triggered at time 1. A level three warning is triggered at any time, among which The threshold for medium risk is between 0.6 and 0.7; among which... The high-risk threshold is between 0.8 and 0.9.

[0114] The safety protection module is used to activate the graded fire suppression system based on graded early warning signals.

[0115] Level 1 Warning: Activate the cell-grade compressed air foam extinguishing device, spraying foam containing [unspecified substance] within 3 seconds. The aerosol fire extinguishing agent can rapidly suppress thermal runaway of a single battery cell and control the scope of damage.

[0116] Secondary warning: Start the perfluorocyclohexanone pre-piped network fire extinguishing device, achieve 0.3 m³ / min precise coverage of the extinguishing agent through a double-fluid nozzle, and avoid waste of the extinguishing agent;

[0117] Tertiary warning: Link the heptafluoropropane full-flooding system, complete the release of the extinguishing agent within 10 seconds and maintain the fire extinguishing concentration for ≥30 minutes, meet the complete blocking requirement of the UL 9540A standard for thermal runaway diffusion, and prevent the spread of fire.

[0118] The fire-fighting linkage module is used to take different measures according to the graded warning signals:

[0119] ‌Primary warning: Start the exhaust system and push the operation and maintenance alarm;

[0120] ‌Secondary warning: Link the power supply of the equipment and prepare for fire extinguishing;

[0121] ‌Tertiary action: Automatically release the fire extinguishing medium and trigger the emergency broadcast.

[0122] The safety feedback module is used to feedback the results of safety protection and fire-fighting linkage, judge whether the safety protection and fire-fighting linkage are successful, and the judgment logic is as follows:

[0123] (1) If the following indicators are not reached within 60 seconds after the fire extinguishing is started, it is determined to be invalid:

[0124] temperature drop rate , smoke concentration drop , flammable gas concentration , trigger the secondary injection of the standby extinguishing agent tank, and activate the emergency exhaust fan, wherein the value of x is between 4 and 6 , the value of y is between 60 and 70 , and the value of z is between 5 and 7 , which is not limited in this embodiment.

[0125] (2) False alarm filtering mechanism:

[0126] When the R value fluctuates and the duration is seconds, the Kalman filter is enabled for noise reduction;

[0127] When the voltage / current parameters are abnormal, the BMS data is forced to be called for cross verification.

[0128] The safety evaluation module is used to analyze and process the safety evaluation coefficient of each specified detection area and evaluate the prediction accuracy.

[0129] The formula for calculating the safety evaluation coefficient is:

[0130] ;

[0131] Where j represents the number of false alarms, represents the total number of alarms, p represents the actual fire scene recognition rate.

[0132] When Q < w, the model parameter calibration program is automatically triggered, where u and v represent weights, u has a value of 0.6-0.7, and v has a value of 0.3-0.4, and the specific values are determined according to the actual situation.

[0133] w x 100% represents the prediction accuracy, w ranges from 0.8 to 1, and the specific value is selected according to the needs of the industrial park.

Claims

1. A safety protection and early warning system for energy storage equipment applied to an industrial park, characterized in that, Comprise: Park architecture planning module: based on data location characteristics, the park map information is imported into the cloud, and the location area is constructed, respectively marked as battery module area, cluster level area and cabin level area; Probe data set acquisition module: used for data acquisition in battery module area, cluster level area and cabin level area, respectively obtaining primary data text, secondary data text and tertiary data text; Text data preprocessing module: used for data integration of primary data text, secondary data text and tertiary data text, obtaining primary integrated data text, secondary integrated data text and tertiary integrated data text; Integrated data analysis module: used for importing primary integrated data text, secondary integrated data text and tertiary integrated data text into risk control data calculation model to obtain thermal runaway risk index R; The integration process of the primary integrated data text is specifically to import the primary data text into a primary calculation model, and the primary calculation model comprises temperature model, combustible gas model, smoke model and voltage / current parameter model; The temperature model includes a battery module surface temperature rate of change coefficient, denoted as ; an in-cabin ambient temperature coefficient, denoted as ; and a temperature difference within a battery cluster coefficient, denoted as ; The battery module surface temperature change rate coefficient is specifically: ； wherein is the temperature change of the surface of the battery module, , is the contribution value of the temperature change rate, and the maximum contribution of the temperature change rate is 0.5; t is the high-risk threshold of the industry standard, and b is the acceleration coefficient; The cabin environment temperature coefficient is specifically: when ℃, ； wherein T is the real-time ambient temperature in the cabin, and the threshold temperature is F °C, which is the critical value of triggering the temperature risk. By mapping the temperature rise amount ( ) to a risk contribution value, ranging from ; wherein the coefficient increases by 1 for each increase of q °C in the ambient temperature. the value of the exponential term increases by 1 for each increase of q °C in the ambient temperature. The battery cluster internal temperature difference coefficient is specifically: ； wherein is the highest temperature within the cluster, is the lowest temperature within the cluster, is the average temperature within the cluster, ； n is the total number of temperature measurements, T is the temperature of any one temperature measurement; Early warning signal generation module: used for analyzing thermal runaway risk index R and generating early warning signal to the cloud; The formula of the thermal runaway risk index R is as follows: ； wherein , , and represent a weight factor; is a flammable gas concentration rise coefficient, is a smoke particle concentration coefficient, is an electrical imbalance coefficient; Database secondary construction module: used for secondary analysis after receiving the early warning signal, and generating hierarchical early warning signal to the cloud; Safety protection module: used for starting hierarchical fire extinguishing device according to hierarchical early warning signal; Firefighting linkage module: used for taking different measures according to hierarchical early warning signal; Safety feedback module: used for feeding back the results of safety protection and firefighting linkage to judge whether the safety protection and firefighting linkage are successful; Safety evaluation module: used for analyzing safety evaluation coefficient of each specified detection area and processing; The formula of the safety evaluation coefficient is as follows: ； where j represents the number of false alarms, where Q represents the total number of alarms, p represents the actual fire scene recognition rate, w represents the threshold, u and v represent weights, and w x 100% represents the prediction accuracy.

2. The energy storage device safety protection and early warning system applied to an industrial park of claim 1, wherein: The acquisition steps of the probe data set acquisition module are as follows: A1, respectively set acquisition end in battery module area, cluster level area and cabin level area; A2, collect acquisition end data to obtain temperature data, combustible gas data, smoke data and current / voltage data; A3, based on data sum, data construction is carried out to obtain module level database, cluster level database and cabin level database; A4, wherein the data in the module level database, cluster level database and cabin level database are respectively marked as primary data text, secondary data text and tertiary data text.

3. The energy storage device safety protection and early warning system applied to an industrial park of claim 1, wherein: The combustible gas model is specifically a combustible gas concentration rise coefficient, denoted as ; The combustible gas concentration rising coefficient is specifically: ； wherein represents the real-time concentration of flammable gas in the cabin, is a coefficient for controlling sensitivity, is a coefficient for controlling sensitivity, is a temperature difference correction factor.

4. The energy storage device safety protection and early warning system applied to an industrial park of claim 1, wherein: The smoke model is in particular a smoke particle concentration coefficient, denoted : The smoke particle concentration coefficient is specifically: ； wherein is the real-time smoke particle concentration, is the reference smoke particle concentration, The electric imbalance coefficient is specifically: sensor upper range limit.

5. The energy storage device safety protection and early warning system applied to an industrial park of claim 1, wherein: The voltage / current parameter model is unified into an electrical imbalance coefficient, denoted as : ​ ； wherein is the actual measured voltage, is the battery nominal voltage, is the actual measured current, is the battery rated current; quantifies the degree to which the voltage deviates from the nominal value; The proportion of the quantized current exceeding the rated value is the current outlier.

Images