Battery management system for protecting energy storage battery packs fire protection system

Abstract

The present application belongs to the technical field of battery safety protection, and particularly relates to a protection energy storage battery pack fire protection system based on a battery management system. The system aims to solve the problems of low heat runaway sensing sensitivity and inaccurate fire extinguishing. The system comprises a multi-dimensional parameter sensing unit for collecting battery electricity, heat and environmental parameters; a core processing unit for determining the risk level according to the internal resistance change rate and gas time gradient; a fire protection linkage control unit responsible for loop cutting and linkage; and a directional fire extinguishing execution unit for realizing precise spraying through electromagnetic valves and branch selection valves. The present application realizes all-round sensing from electricity, heat to chemical signals, can effectively capture the initial abnormality of heat runaway and realize directional fire extinguishing, and significantly improves the early warning lead time and intrinsic safety of the energy storage power station.

Description

Technical Field

[0001] This invention belongs to the field of battery safety protection technology, specifically relating to a fire protection system for energy storage battery packs based on a battery management system. Background Technology

[0002] With the continuous increase in the proportion of renewable energy globally, energy storage systems, as a core infrastructure for regulating energy supply and demand balance and maintaining stable grid operation, are experiencing explosive growth in application scale. Against this backdrop, the safe operation of energy storage battery packs, especially fire safety, has become a key factor restricting the large-scale commercial application of this industry, directly impacting the smooth transformation of the energy structure and public safety.

[0003] To address the potential fire risks of energy storage systems, existing technologies typically rely on battery management systems (BMS) to monitor physical parameters such as voltage, current, and temperature in real time, in conjunction with physical fire suppression systems for safety protection. BMS, by integrating sensor arrays, constructs a microscopic sensing network for the operating status of battery modules. Its basic principle is to trigger early warning signals by capturing early signs of thermal runaway, thereby achieving closed-loop management of the overall operating environment of the energy storage system.

[0004] However, existing protection systems exhibit severe response lag in actual operation. This is primarily due to the logical decoupling between the sensing and execution layers. This decoupling prevents the battery management system's monitoring data from being efficiently and in real-time converted into preventative fire intervention actions. When a battery cell exhibits weak signs of thermal runaway due to chemical reactions, the complex decision-making logic and transmission losses between communication nodes in traditional systems prevent the detected abnormal signals from triggering the fire suppression system within the extremely short warning window. This leads to the rapid spread of thermal runaway within the battery pack in a chain reaction. Given this severe mismatch between sensing depth and execution speed, fire intervention often lags significantly behind the onset of thermal runaway. Consequently, existing fire suppression systems are inefficient in protecting high-energy-density battery packs, becoming a fundamental bottleneck restricting the safety and protection effectiveness of energy storage systems. Summary of the Invention

[0005] This invention provides a fire protection system for energy storage battery packs based on a battery management system, aiming to solve the problems of insufficient sensitivity in detecting the initial stage of battery thermal runaway, simple early warning logic, and secondary damage caused by the lack of accuracy in the delivery of fire extinguishing media in existing energy storage systems.

[0006] This invention provides a fire protection system for energy storage battery packs based on a battery management system, comprising: The multi-dimensional parameter sensing unit is used to collect in real time the voltage data, current data, surface temperature data of each individual cell in the energy storage battery pack, as well as the environmental characteristic parameters inside the battery box, including hydrogen concentration, carbon monoxide concentration and electrolyte vapor concentration. The core processing unit of the battery management system is connected to the multi-dimensional parameter sensing unit. It is used to calculate the rate of change of internal resistance of a single cell based on the received voltage data and current data, and to perform multi-criteria fusion analysis by combining the rate of change of surface temperature data and the time-series gradient of environmental characteristic parameters to determine the thermal runaway risk level of a single cell, and to generate corresponding fire control instructions based on the thermal runaway risk level. The fire protection linkage control unit is connected to the core processing unit of the battery management system. It is used to receive the fire control command and, according to the risk level corresponding to the fire control command, selectively execute electrical circuit disconnection and / or send drive signals to the directional fire extinguishing execution unit. The directional fire extinguishing execution unit includes a fire extinguishing medium storage container, a main solenoid valve, and a branch selection valve corresponding to each of the battery boxes. The fire protection linkage control unit controls the opening of the main solenoid valve and the branch selection valve corresponding to the target battery box to achieve quantitative and precise spraying of fire extinguishing medium to the specific battery box that has malfunctioned.

[0007] As one embodiment of the present invention, the multi-dimensional parameter sensing unit includes a composite gas sensor disposed at the top of the battery box and a thin-film temperature sensor attached to the terminal of a single battery cell; the composite gas sensor monitors the volume fraction changes of multiple characteristic gases simultaneously through a built-in microelectromechanical system chip; the thin-film temperature sensor monitors the terminal temperature through a high-precision thermistor and converts the temperature signal into a frequency signal and transmits it to the core processing unit of the battery management system.

[0008] As one embodiment of the present invention, the core processing unit of the battery management system has a built-in early thermal runaway feature extraction model. This model extracts voltage noise spectral density features by sampling the terminal voltage of a single cell at high frequency. When an abnormal change in voltage noise spectral density is detected in a specific frequency band and accompanied by an increase in the internal resistance of the single cell exceeding 15%, the single cell is determined to have entered the gas evolution warning stage.

[0009] As one embodiment of the present invention, the core processing unit of the battery management system executes the following logic when determining the thermal runaway risk level: when the rate of increase of the surface temperature data exceeds 3 degrees Celsius per minute and the hydrogen concentration in the environmental characteristic parameter reaches 50 parts per million, it is determined to be a level 1 risk; when the rate of increase of the surface temperature data exceeds 10 degrees Celsius per minute or the carbon monoxide concentration continues to rise, it is determined to be a level 2 risk; when the voltage of a single cell drops by more than 0.5V within 1 second and the rate of change of hydrogen concentration or carbon monoxide concentration within 1 second exceeds 50%, it is determined to be a level 3 risk.

[0010] As one embodiment of the present invention, the fire protection linkage control unit includes a logic control module and a drive circuit module; when the logic control module receives a first-level risk signal, it controls the heat dissipation system of the energy storage system to switch to full-power operation mode; when it receives a second-level risk signal, it controls the contactor to disconnect to shut off the charging and discharging circuit; when it receives a third-level risk signal, it immediately triggers the directional fire extinguishing execution unit.

[0011] In one embodiment of the present invention, the extinguishing medium storage container of the directional fire extinguishing execution unit is filled with perfluorohexanone extinguishing agent, and the container is maintained at a nitrogen driving pressure of 2.5 MPa to 4.2 MPa; the branch selection valve is controlled by pulse width modulation signal to adjust the spray intensity according to the fire load evaluated by the core processing unit of the battery management system.

[0012] As one embodiment of the present invention, the fire protection system for the energy storage battery pack based on the battery management system also includes a data storage and remote communication module, which is used to upload the real-time data collected by the multi-dimensional parameter sensing unit and the action record of the fire control command to the cloud monitoring platform to realize the digital safety operation and maintenance of the energy storage site.

[0013] In one embodiment of the present invention, the branch pipelines in the directional fire extinguishing execution unit are distributed in a ring inside the battery box, and multiple atomizing nozzles are provided on the branch pipelines. The arrangement of the atomizing nozzles corresponds to the arrangement gaps of the battery modules, ensuring that the fire extinguishing medium can cover the gaps between the individual batteries.

[0014] As one embodiment of the present invention, the core processing unit of the battery management system also includes a self-diagnostic algorithm for periodically detecting the online status of the sensors of the multi-dimensional parameter sensing unit and the loop integrity of the fire protection linkage control unit. If the sensor data is found to be constant or the loop resistance is abnormal, a system fault alarm is triggered.

[0015] As one embodiment of the present invention, after determining that a single cell has entered the gas evolution warning stage, the core processing unit of the battery management system will start a local circulation fan to guide the gas in the battery box to flow through the composite gas sensor, so as to eliminate the monitoring lag caused by gas stratification in the box and improve the response speed.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are as follows: This invention, through deep integration of a battery management system and a fire protection system, achieves comprehensive sensing of electrical, thermal, and chemical signals, fundamentally solving the problems of missed and false alarms caused by relying solely on temperature or smoke detection. Utilizing the high-frequency sampling capability of the battery management system, the system can capture minute voltage fluctuations and internal resistance anomalies in the early stages of thermal runaway in individual batteries, advancing the warning time to 5 to 10 minutes before open flames occur. Through the coordinated operation of the directional fire suppression execution unit and the branch selection valve, precise delivery of the fire extinguishing medium is achieved, avoiding indiscriminate spraying of batteries in non-faulty areas and significantly reducing insulation damage and subsequent cleanup costs during fire suppression. This system constructs a three-pronged protection system of prevention, blocking, and extinguishing, significantly improving the safe operation level and inherent safety of large-capacity energy storage power stations. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the overall architecture of the fire protection system for energy storage battery packs based on the battery management system of the present invention; Figure 2 This is a schematic diagram of the core principle framework of multidimensional parameter fusion and early warning of thermal runaway in this invention; Figure 3 This is a logical flowchart of the linkage between thermal runaway risk level determination and fire protection in this invention; Figure 4 This is a schematic diagram of the multi-level interaction relationship and data flow between the directional fire extinguishing execution unit and the battery box in this invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] In the accompanying drawings, the size of constituent elements, the thickness of layers, or areas may sometimes be exaggerated for clarity. Therefore, any implementation of this disclosure is not necessarily limited to the dimensions shown in the drawings, and the shapes and sizes of the components in the drawings do not reflect true proportions. Furthermore, the drawings schematically illustrate ideal examples, and any implementation of this disclosure is not limited to the shapes or values ​​shown in the drawings.

[0020] Reference Figure 1 , Figure 1 This is a schematic diagram of the overall technical solution architecture of the fire protection system for energy storage battery packs based on a battery management system proposed in this invention. Figure 1 As shown, the system includes: a multi-dimensional parameter sensing unit 10, a battery management system core processing unit 20, a fire protection linkage control unit 30, and a directional fire extinguishing execution unit 40.

[0021] During the safety monitoring of the energy storage site, the front-end multi-dimensional parameter sensing unit 10 collects in real time the voltage, current, and surface temperature data of each individual cell in the energy storage battery pack, as well as environmental characteristic parameters inside the battery box. These environmental characteristic parameters specifically include hydrogen concentration, carbon monoxide concentration, and electrolyte vapor concentration. The multi-dimensional parameter sensing unit 10 converts the collected multi-source physical quantities into digital signals and sends them to the core processing unit 20 of the battery management system via a high-speed communication bus.

[0022] In this embodiment, through integrated layout, the multi-dimensional parameter sensing unit 10 achieves microscopic monitoring of the physical state of individual battery cells. After receiving voltage and current data, the core processing unit 20 of the battery management system obtains the rate of change of internal resistance of the individual battery cells in real time through internal synchronous calculation logic, and combines this with the rate of change of surface temperature data (…). Multi-criteria fusion analysis is performed on the time-series gradients of characteristic gas concentrations and environmental feature parameters to determine the thermal runaway risk level of a single battery cell and generate corresponding fire control commands. The time-series gradient refers to the rate of change or trend of change of characteristic gas concentrations over time.

[0023] The fire protection linkage control unit 30 receives the fire control command and, based on the risk level corresponding to the fire control command, selectively executes electrical circuit disconnection and / or sends a drive signal to the directional fire extinguishing execution unit 40. The directional fire extinguishing execution unit 40 controls the opening of the main solenoid valve and the branch selection valve corresponding to the target battery box to achieve precise quantitative spraying of the extinguishing medium to the specific battery box experiencing an anomaly. This invention, through the deep integration of the sampling accuracy of the battery management system (BMS) and the spatial targeting of the fire extinguishing execution end, eliminates the shortcomings of traditional fire protection systems such as monitoring lag and indiscriminate spraying.

[0024] In one embodiment, the present invention provides a fire protection system for a protected energy storage battery pack based on a battery management system, the construction details of which are as follows: Figure 2 As shown. The multidimensional parameter sensing unit 10 includes a composite gas sensor disposed at the top of the battery box and a thin-film temperature sensor attached to the terminal of a single battery cell.

[0025] The composite gas sensor simultaneously monitors the volume fraction changes of multiple characteristic gases through a built-in microelectromechanical system (MEMS) chip. In the initial stage of gas evolution caused by side reactions in a single cell, the sensing array of the MEMS chip can capture the diffusion distribution of hydrogen, carbon monoxide, and electrolyte vapor molecules. The thin-film temperature sensor monitors the electrode temperature using a high-precision thermistor. Since the electrode is the physical channel for heat conduction inside the battery, its temperature change precedes the surface temperature. The thin-film temperature sensor converts the resistance fluctuations caused by temperature changes into frequency signals, which are transmitted to the core processing unit 20 of the battery management system, effectively avoiding analog signal attenuation during long-distance transmission.

[0026] In one implementation, such as Figure 2 As shown, the core processing unit 20 of the battery management system has a built-in early thermal runaway feature extraction model. This model serves as the algorithmic core for risk assessment, by performing high-frequency sampling of the terminal voltage of individual cells (sampling frequency...). ), extract voltage noise spectral density features.

[0027] In this embodiment, the system monitors minute ripples in the terminal voltage in real time. When an abnormal abrupt change in the voltage noise spectral density is detected in a specific frequency band (e.g., 10Hz-100Hz), accompanied by an increase in the internal resistance of a single cell exceeding 15%, the system logic determines that the single cell has entered the gas evolution warning stage caused by internal separator damage. At this time, the core processing unit 20 of the battery management system immediately starts a local circulation fan to guide the gas in the battery box to undergo forced convection and flow through the composite gas sensor. This eliminates the local concentration detection lag caused by gas stratification within the box, ensuring that the sensor can obtain the true volume fraction of characteristic gases in real time.

[0028] This embodiment provides a specific quantitative calculation model for the multi-criteria fusion analysis performed by the core processing unit of the battery management system. It aims to solve the problem that single threshold judgment is easily affected by environmental noise, which can lead to false alarms, and to achieve accurate risk level classification.

[0029] Specifically, the fusion analysis model built into the core processing unit adopts a computing architecture of "normalized mapping + dynamic weighted fusion".

[0030] 1. Normalization construction of risk factors: Because parameters such as voltage, internal resistance, temperature, and gas concentration have different dimensions and physical meanings, direct numerical calculations cannot reflect the true risk weights. The system first normalizes the raw data for each dimension, transforming it into... Risk membership degree within the interval: Internal resistance change rate factor ( Internal resistance is the most sensitive parameter reflecting the internal chemical activity state of a battery. The rate of change of internal resistance is set. .when When it is less than 5%, it is considered normal aging or measurement error, and the risk factor is 0; when When the percentage exceeds 20%, the diaphragm is considered severely damaged, and the risk factor saturates to 1. Linear interpolation is used for the intermediate range, calculated using the following formula: .

[0031] Temperature rise rate factor ( ): Set the temperature rise rate Considering that the temperature rise under normal operating conditions is usually less than... The risk factor is set to 0 at this point; when the temperature rises to... When this typical characteristic value of thermal runaway is reached, the risk factor is set to 1. The formula for calculating the intermediate interval is: .

[0032] Gas concentration characteristic factor ( ): Combined hydrogen ( ) and carbon monoxide ( For concentration, the strategy of taking the maximum value is adopted: These correspond to the electrolyte decomposition in the early stage of thermal runaway and the combustion characteristics of organic matter in the later stage, respectively.

[0033] 2. Weighting strategy: This invention introduces variable weight theory to solve the problem of delayed response under extreme conditions when the weight is fixed.

[0034] The base weights are set as follows: ,in , , This setting focuses on gas monitoring because gas evolution is usually the earliest macroscopic sign of thermal runaway.

[0035] Dynamic weight adjustment: Introducing an incentive-based state-variable weight vector The calculation formula is as follows: ,in, The adjustment coefficient has a range of values. ; The excitation threshold is set to [value]. ; For the first The normalized values ​​of each risk factor.

[0036] The adjusted dynamic weight is calculated using the following formula. :

[0037] In the formula, and All of these are index numbers of the risk factors. Indicates the number of terms to be calculated. The basic weight values ​​of each risk factor; Symbol for summing denominators The first traversal of the middle The base weight values ​​for each risk factor. The denominator represents the sum of the weighted adjustment values ​​for all three risk factors, used to normalize the weights and ensure that all dynamic weights are finalized. The sum is 1.

[0038] This formula ensures that when a certain characteristic parameter (such as the rate of temperature rise) is... A sudden surge exceeding the threshold At that time, the weight of that dimension The weights will increase exponentially, while the weights of other normal parameters will be automatically suppressed, thereby ensuring that the system can respond quickly to sudden thermal shocks and avoid missed risk detection due to the lag of gas sensors.

[0039] 3. Comprehensive Risk Index and Quantitative Boundaries: Based on the dynamic weights calculated above and normalized risk factors The system calculates the comprehensive risk index. :

[0040] according to The system sets clear quantification boundaries within a given numerical range to determine the risk level of thermal runaway: Normal state (risk-free stage): when At that time, it is determined to be a risk-free or normal state.

[0041] Level 1 Risk (Early Warning Stage): At this point, the battery is in a sub-healthy state, and may experience slight gas evolution or temperature rise, triggering the system's heat dissipation enhancement logic.

[0042] Level 2 Risk (Alarm Stage): At this point, signs of thermal runaway became apparent, and the system shut down the electrical circuits to prevent further injection of external energy.

[0043] Level 3 Risk (Critical Phase): At this point, all parameters exceed their limits, indicating that thermal runaway is unavoidable or has already occurred, and the directional fire suppression unit is immediately triggered.

[0044] Through the specific calculation model and quantization boundary setting described above, this invention realizes the transformation from "single threshold jump judgment" to "multi-dimensional coupled continuous situational awareness", effectively improving the robustness and accuracy of risk judgment.

[0045] In one embodiment, the system provided by the present invention strictly executes graded linkage control logic when determining the thermal runaway risk level; see the specific process below. Figure 3 The core processing unit 20 of the battery management system executes the following decision logic based on the real-time data stream: 1. Level 1 Risk Assessment: When the surface temperature rise rate exceeds 3 degrees Celsius per minute and the hydrogen concentration in the environmental characteristic parameters reaches 50 parts per million (ppm), it is assessed as a Level 1 risk. At this time, the fire protection linkage control unit 30 controls the auxiliary heat dissipation system of the energy storage system to switch to full-power operation mode, using forced air cooling or liquid cooling systems to quickly dissipate the accumulated heat.

[0046] 2. Level 2 Risk Assessment: When the surface temperature rises at a rate exceeding 10 degrees Celsius per minute, or when the carbon monoxide (CO) concentration shows a clear and sustained upward trend over time, it is assessed as a Level 2 risk. At this time, the drive circuit module in the fire protection linkage control unit 30 immediately activates, controlling the main circuit contactor to disconnect and shut off the charging and discharging circuit, physically isolating the damaged battery and preventing the spread of thermal runaway.

[0047] 3. Level 3 Risk Assessment: When the voltage of a single battery cell suddenly drops (e.g., a voltage drop exceeding 0.5V) and environmental characteristic parameters (hydrogen gas, electrolyte vapor) fluctuate drastically, it is assessed as a Level 3 risk. The system then skips all intermediate strategies and immediately triggers the directional fire suppression execution unit 40 to intervene.

[0048] In one embodiment, the physical topology and interaction relationship between the directional fire suppression execution unit 40 and the battery box provided by the present invention are as follows: Figure 4 As shown. The directional fire extinguishing execution unit 40 includes a fire extinguishing medium storage container, a main solenoid valve, and branch selection valves corresponding to each battery box.

[0049] The extinguishing medium storage container is filled with perfluorohexanone (Perfluorohexanone). The extinguishing agent is maintained at a driving pressure of 2.5 MPa to 4.2 MPa inside the container by nitrogen gas. The branch pipelines are distributed in a ring shape inside the battery box, and multiple atomizing nozzles are installed on the branch pipelines, with their positions corresponding to the spacing between the battery modules.

[0050] In this embodiment, the fire protection linkage control unit 30 controls the opening degree of the target branch selection valve through a pulse width modulation (PWM) signal. Specifically, the system adjusts the PWM duty cycle based on the fire load (real-time heating power calculated based on internal resistance changes and temperature rise slope) assessed by the battery management system core processing unit 20, thereby precisely controlling the instantaneous flow rate of the branch selection valve. The extinguishing medium enters the branch via the main solenoid valve and forms a fine water mist of perfluorohexanone clouds between the battery modules through atomizing nozzles on the ring pipeline. Utilizing its extremely high heat absorption capacity and chemical inhibition effect, it rapidly extinguishes the initial fire and reduces the temperature of the battery cell body.

[0051] In one embodiment, the fire protection system for the energy storage battery pack based on the battery management system further includes a self-diagnostic algorithm and remote operation and maintenance logic. The core processing unit 20 of the battery management system periodically (e.g., every 30 seconds) checks the online status of the sensors in the multi-dimensional parameter sensing unit 10 and the loop integrity of the fire protection linkage control unit 30.

[0052] If the ADC value returned by a sensor remains constant for multiple consecutive sampling periods (i.e., a "dead value"), or if the closed-loop resistance of the fire alarm linkage circuit exceeds the preset safety range (indicating aging or open circuit in the wiring), the core processing unit 20 triggers a system fault alarm. Simultaneously, the data storage and remote communication module uploads the fault code, real-time data, and historical action records to the cloud monitoring platform, enabling digital and transparent safe operation and maintenance of the energy storage site.

[0053] Thus, this invention constructs a full-link safety barrier from coordinated sensing of "electricity / heat / gas" to precise intervention of "electrical cutoff / directional spraying" through deep coupling of multi-dimensional parameter fusion and targeted fire suppression execution. The system utilizes the microsecond-level computing power of the battery management system and the physical fire extinguishing properties of perfluorohexanone to ensure effective intervention at the very early stages of thermal runaway, greatly improving the system's safety under extreme conditions.

[0054] The fire protection system for energy storage battery packs based on a battery management system proposed in this invention has the following significant advantages: 1. Accuracy of multi-criteria fusion early warning: By using multi-dimensional coupling judgment based on voltage noise spectrum, internal resistance change, characteristic gas concentration and electrode temperature, the early warning time of thermal runaway is advanced to 5-10 minutes before the open flame occurs, effectively solving the false alarm and missed alarm phenomenon caused by a single sensor.

[0055] 2. Precision of fire extinguishing medium delivery: The coordinated action of the directional fire extinguishing actuator and the branch selection valve, combined with PWM flow control, achieves "targeted spraying" of the faulty battery box, maximizing the protection of battery assets in non-faulty areas and avoiding insulation damage caused by total flooding fire extinguishing.

[0056] 3. Dynamic environmental compensation capability: By utilizing a local circulating fan to eliminate the gas stratification effect and combining it with high-frequency sampling by a thin-film temperature sensor, the system's response consistency is ensured in complex enclosure environments.

[0057] 4. Completeness of the intrinsically safe system: A three-level protection gradient is constructed, from heat dissipation enhancement and electrical shutdown to directional fire suppression. Combined with a self-diagnostic algorithm, the reliable operation of the entire protection system is ensured throughout its entire life cycle.

[0058] In summary, this invention provides an irreplaceable engineering solution for the fire safety of large-scale energy storage power stations through in-depth mining of the underlying data of the battery management system and physical optimization of the fire-fighting actuators.

[0059] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0060] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Although preferred embodiments of the present invention have been described, those skilled in the art, once they understand the basic inventive concept, can make other changes and modifications to these embodiments. Finally, it should be noted that relational terms such as "first" and "second" are merely 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. In this document, specific examples have been used to illustrate the principles and implementation methods of the present invention. The above description of the embodiments is only for the purpose of helping to understand the method and core ideas of the present invention and should not be construed as a limitation of the present invention.

Claims

1. A fire protection system for energy storage battery packs based on a battery management system, characterized in that, include: The multi-dimensional parameter sensing unit is used to collect in real time the voltage data, current data, surface temperature data of each individual cell in the energy storage battery pack, as well as the environmental characteristic parameters inside the battery box, including hydrogen concentration, carbon monoxide concentration and electrolyte vapor concentration. The core processing unit of the battery management system is connected to the multi-dimensional parameter sensing unit. It is used to calculate the rate of change of internal resistance of a single cell based on the received voltage data and current data, and to perform multi-criteria fusion analysis by combining the rate of change of surface temperature data and the time-series gradient of environmental characteristic parameters to determine the thermal runaway risk level of a single cell, and to generate corresponding fire control instructions based on the thermal runaway risk level. The fire protection linkage control unit is connected to the core processing unit of the battery management system. It is used to receive the fire control command and, according to the risk level corresponding to the fire control command, selectively execute electrical circuit disconnection and / or send drive signals to the directional fire extinguishing execution unit. The directional fire extinguishing execution unit includes a fire extinguishing medium storage container, a main solenoid valve, and a branch selection valve corresponding to each of the battery boxes. The fire protection linkage control unit controls the opening of the main solenoid valve and the branch selection valve corresponding to the target battery box to achieve quantitative and precise spraying of fire extinguishing medium to the specific battery box that has malfunctioned.

2. The fire protection system for energy storage battery packs based on a battery management system according to claim 1, characterized in that, The multidimensional parameter sensing unit includes a composite gas sensor located at the top of the battery box and a thin-film temperature sensor attached to the terminal of the individual battery cell. The composite gas sensor monitors the volume fraction changes of multiple characteristic gases simultaneously through a built-in microelectromechanical system chip. The thin-film temperature sensor monitors the terminal temperature through a thermistor and converts the temperature signal into a frequency signal, which is then transmitted to the core processing unit of the battery management system.

3. The fire protection system for energy storage battery packs based on a battery management system according to claim 1, characterized in that, The core processing unit of the battery management system has a built-in early thermal runaway feature extraction model. The model extracts the voltage noise spectral density features by sampling the terminal voltage of the individual cells at high frequency. When an abnormal change in the voltage noise spectral density is detected in a specific frequency band and accompanied by an increase in the internal resistance of the individual cell exceeding 15%, the individual cell is determined to have entered the gas evolution warning stage.

4. The fire protection system for energy storage battery packs based on a battery management system according to claim 1, characterized in that, The core processing unit of the battery management system executes the following logic when determining the thermal runaway risk level: when the rate of increase of the surface temperature data exceeds 3 degrees Celsius per minute and the hydrogen concentration in the environmental characteristic parameter reaches 50 parts per million, it is determined to be a level 1 risk; when the rate of increase of the surface temperature data exceeds 10 degrees Celsius per minute or the carbon monoxide concentration continues to rise, it is determined to be a level 2 risk; when the voltage of a single cell drops by more than 0.5V within 1 second and the rate of change of hydrogen concentration or carbon monoxide concentration within 1 second exceeds 50%, it is determined to be a level 3 risk.

5. The fire protection system for energy storage battery packs based on a battery management system according to claim 1, characterized in that, When the core processing unit of the battery management system performs multi-criteria fusion analysis, it adopts a multi-dimensional parameter fusion algorithm based on variable weight theory, and specifically executes the following steps: Constructing risk feature vectors ,in The risk factor is the rate of change of internal resistance. As a risk factor for the rate of temperature rise, For gas concentration characteristic risk factors; Normalize each risk factor and map the physical quantity to... The dimensionless risk range, in which: Risk factor for rate of change of internal resistance ; Temperature rise rate risk factor ; Gas concentration characteristic risk factors ,in Hydrogen concentration, This refers to the carbon monoxide concentration. Set the basic weight vector ,in , , Introducing incentive-based state-weighted vectors The calculation formula is: ,in To adjust the coefficient, As the excitation threshold, For the first Normalized values ​​of each risk factor; Through formula Calculate the dynamic weights, where and These are all index numbers of risk factors. Indicates the first The base weight values ​​of each risk factor In the summation term of the denominator, the first term is represented by the first term. The base weight values ​​of each risk factor Indicates the adjusted number Dynamic weights of each risk factor; Calculate the comprehensive risk index And determine the thermal runaway risk level based on the quantification boundary: when The situation is then determined to be risk-free or normal. when It was determined to be a Level 1 risk at that time; when It was determined to be a level 2 risk at that time; when It was determined to be a level three risk.

6. The fire protection system for energy storage battery packs based on a battery management system according to claim 4, characterized in that, The fire protection linkage control unit includes a logic control module and a drive circuit module; when the logic control module receives a first-level risk signal, it controls the heat dissipation system of the energy storage system to switch to full-power operation mode; when it receives a second-level risk signal, it controls the contactor to disconnect to shut off the charging and discharging circuit; when it receives a third-level risk signal, it triggers the directional fire extinguishing execution unit.

7. The fire protection system for energy storage battery packs based on a battery management system according to claim 1, characterized in that, The branch selection valve is controlled by a pulse width modulation signal to adjust the spray intensity according to the fire load assessed by the core processing unit of the battery management system.

8. The fire protection system for energy storage battery packs based on a battery management system according to claim 1, characterized in that, It also includes a data storage and remote communication module, used to upload the real-time data collected by the multi-dimensional parameter sensing unit and the action records of the fire control commands to the cloud monitoring platform.

9. The fire protection system for energy storage battery packs based on a battery management system according to claim 1, characterized in that, The branch pipelines in the directional fire extinguishing unit are arranged in a ring inside the battery box, and multiple atomizing nozzles are installed on the branch pipelines. The arrangement of the atomizing nozzles corresponds to the arrangement gaps of the battery modules.

10. The fire protection system for energy storage battery packs based on a battery management system according to claim 3, characterized in that, After determining that the individual battery cell has entered the gas evolution warning stage, the core processing unit of the battery management system starts a local circulation fan to guide the gas in the battery box to flow through the composite gas sensor, so as to eliminate the monitoring lag caused by gas stratification in the box.

Images