Battery thermal runaway detection system based on early warning function

Abstract

The invention discloses a battery thermal runaway detection system based on an early warning function, and relates to the technical field of battery thermal runaway, and the system comprises a supervision center which is used for carrying out the real-time supervision of the data information of a plurality of batteries, carrying out the early warning of the time data of the battery thermal runaway, and facilitating the timely issuing of warning information and notification announcements, and a monitoring device which is used for monitoring the data information of a plurality of batteries. The monitoring device is used for collecting thermal runaway parameters of each detection node of a plurality of batteries, the thermal runaway parameters comprise battery voltage, temperature, current and pressure, and the protection device is used for carrying out delayed protection operation on the monitoring device. The battery thermal runaway detection system based on the early warning function establishes a thermal runaway early warning model by fusing multi-parameter data of heat, force, electricity and the like and historical data of a thermal runaway phenomenon and by utilizing various learning algorithms, monitors battery parameters and sets simple judgment standards and threshold values such as a non-working state current threshold value and the like, so that the battery thermal runaway early warning model is established. Early detection of battery thermal runaway is realized, and monitoring and early warning effects are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of battery thermal runaway, and in particular to a battery thermal runaway detection system based on early warning function. Background Art

[0002] Thermal runaway refers to the phenomenon that the internal temperature of a battery rises uncontrollably under specific conditions (such as overcharging, short circuiting, heating, etc.). Especially in the fields of electric vehicles and energy storage systems, due to the large number of batteries and high energy density, once thermal runaway occurs, it may cause serious safety accidents such as battery fire or explosion. Therefore, thermal runaway detection is needed to ensure the safety of the battery. However, the existing thermal runaway detection system can only detect the current battery status and cannot provide early warning. Thermal runaway often occurs relatively quickly, making it impossible for relevant personnel to take timely measures such as heat dissipation and flame retardant, posing a major safety hazard. In addition, the thermal runaway detection system often performs thermal runaway detection through detection methods such as temperature and voltage sensors. There is a possibility that a line failure may result in the inability to output valid data in a timely manner, and it is easy to miss reports.

[0003] Based on this, a battery thermal runaway detection system based on early warning function is now provided, which can eliminate the drawbacks of the existing technical solutions. Summary of the invention

[0004] The purpose of the present invention is to provide a battery thermal runaway detection system based on early warning function to solve the problem in the background technology that early warning cannot be given and data cannot be output after a line failure, resulting in missed reports.

[0005] To achieve the above object, the present invention provides the following technical solutions: A battery thermal runaway detection system based on early warning function, comprising: The supervision center is used to monitor the data information of multiple batteries in real time and warn the time data of battery thermal runaway, so as to facilitate the timely release of warning information and notification announcements; A monitoring device, used to collect thermal runaway parameters of each detection node of multiple batteries, wherein the thermal runaway parameters include battery voltage, temperature, current and pressure; A protection device, used for delaying protection operation of the monitoring device; The supervision center includes a network database, an experimental subsystem, a processor and an execution terminal. The network database is used to collect, store and provide historical data and big data information of battery thermal runaway, and divide the data in the corresponding information into several groups according to time, voltage, temperature, current and pressure parameters. The experimental subsystem is used to establish a thermal runaway risk warning model and warn the time of battery thermal runaway according to the model data. The processor is used to receive and output information results from the supervision center, the network database and the experimental subsystem. The execution terminal is used to receive coordination instructions from the processor and publish information according to the instructions.

[0006] Preferably, the monitoring device includes a plurality of voltage sensors, temperature sensors, current sensors and pressure sensors, the voltage sensor is used to detect voltage changes at multiple detection nodes of the battery, the temperature sensor is used to detect temperature changes at multiple detection nodes of the battery, the current sensor is used to detect current changes at multiple detection nodes of the battery, and the pressure sensor is used to detect pressure changes at multiple detection nodes of the battery, and one side of the sensor is provided with a diagnostic component for determining whether a fault occurs at the corresponding detection node.

[0007] Preferably, the diagnostic component includes an electrically connected fault judgment module and an indicator light, wherein the fault judgment module is used to identify fault conditions of different sensors and circuits, and to indicate whether the sensors and circuits meet the fault conditions through the indicator light.

[0008] Preferably, the protection device includes a protection cover and a fire extinguishing device, the protection cover is arranged on the outside of the monitoring device, and the fire extinguishing device is electrically connected to the execution terminal.

[0009] Preferably, the experimental subsystem includes: The preprocessing module is used to remove outliers and duplicate data and convert data of different dimensions into the same dimension; Feature extraction module, used to extract characteristic information that can reflect battery thermal runaway from the original data, including temperature change trend, pressure change rate, current and voltage change rate; Model training module, which is used to train models using historical data through different learning algorithms, and obtain a preliminary thermal runaway warning model by adjusting model parameters and feature selection; Model optimization module, which compares the prediction models and data of different algorithms and obtains the optimal early warning model through feature fusion; The thermal runaway judgment module determines whether the battery will experience thermal runaway and when thermal runaway will occur based on historical data.

[0010] Preferably, the model training module adopts prediction models of long short-term memory network, temporal convolutional network and GRU neural network types.

[0011] Preferably, the thermal runaway judgment module sets the upper limit of the thermal runaway threshold to E according to the historical data of the battery thermal runaway. 上 , the lower limit of thermal runaway threshold is set to E 下 , the variation ranges of voltage, temperature, current and pressure parameters of some of the batteries when they are working normally are all within the range of upper and lower limits of the thresholds.

[0012] Preferably, a monitoring node set is also provided on one side of the battery, and the monitoring node set is used to monitor the surface state and surrounding environment of the battery in real time, and transmit the above information to the result display module.

[0013] Preferably, the result display module is used to receive data information transmitted by the processor, convert it into the form of growth curves and statistical charts, and display the results.

[0014] It also includes a method for using a battery thermal runaway detection system based on an early warning function, and the specific steps of use are as follows: S1. Collect the voltage, current, temperature and pressure parameters of several fault-free batteries in different time periods through the monitoring device, and transmit the data information to the experimental subsystem through the processor; S2, using the diagnostic component to determine in real time whether the lines and sensors at multiple detection nodes are faulty, determine whether the data information is accurate, and transmit the above information to the result display module; S3. Establish a thermal runaway warning model, input the voltage, current, temperature and pressure parameters of a fault-free battery into the model, and perform a battery thermal runaway simulation analysis; S4. The thermal runaway judgment module is provided with upper and lower limits of thermal runaway thresholds. When the predicted parameter data is not within the threshold range, the terminal outputs safety control instructions, which include disconnecting the connection line and sounding a buzzer alarm.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention provides a battery thermal runaway detection system based on early warning function, which establishes a thermal runaway early warning model by integrating data of multiple physical parameters such as heat, force, electricity and historical data of thermal runaway phenomena using a variety of learning algorithms, monitors battery parameters, and sets simple judgment standards and thresholds such as non-working current thresholds and temperature thresholds, thereby achieving early detection of battery thermal runaway. It has the effects of rapid and accurate monitoring and early warning, realizes comprehensive collection, storage, analysis and processing of battery data information, as well as accurate early warning and efficient response to thermal runaway events, and provides strong guarantee for the safe operation of the battery system. The system is also provided with a diagnostic component, which, under the cooperation of the indicator light and the fault judgment module, enables real-time fault judgment of sensors and lines, avoids problems in data output, and facilitates relevant personnel to perform timely inspection and maintenance operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the present invention.

[0017] Figure 2 It is an overall schematic diagram of the present invention.

[0018] Figure 3 It is a schematic diagram of the supervision center of the present invention.

[0019] Figure 4 Schematic diagram of the monitoring device of the present invention.

[0020] Figure 5 Schematic diagram of the protective device of the present invention.

[0021] Figure 6 Schematic diagram of the experimental subsystem of the present invention.

[0022] Figure 7 The figure is a schematic diagram of the method for using the present invention.

[0023] Notes on figure marks: supervision center 100, network database 110, experimental subsystem 120, preprocessing module 121, feature extraction module 122, model training module 123, model optimization module 124, thermal runaway judgment module 125, processor 130, execution terminal 140, result display module 150, monitoring device 200, voltage sensor 210, temperature sensor 220, current sensor 230, pressure sensor 240, fault judgment module 250, indicator light 260, protection device 300, protective cover 310, fire extinguishing equipment 320. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0025] In this embodiment, if Figure 1-Figure 7 As shown, a battery thermal runaway detection system based on early warning function, the system selects several charged batteries for thermal runaway test, inputs their voltage, temperature, current and pressure parameter data into the early warning model, determines the boundary conditions of battery thermal runaway, and then obtains the final early warning model through multiple learning algorithm training and optimization operations. Then, the early warning model is used to conduct comprehensive and real-time data information supervision on multiple batteries used subsequently to ensure the safe operation of the battery system. The system includes: The monitoring center 100 is used to monitor the data information of multiple batteries in real time and warn the time data of battery thermal runaway, so as to facilitate the timely release of warning information and notification announcements, and automatically identify abnormal data based on preset safety thresholds and analysis models, predict the risk of battery thermal runaway, and trigger the output of safety control instructions in the first place. The safety control instructions include but are not limited to issuing warning sounds, abnormal data result notifications, and other methods to ensure that relevant personnel can respond quickly; The monitoring device 200 is used to collect thermal runaway parameters of each detection node of multiple batteries. The thermal runaway parameters include battery voltage, temperature, current and pressure. The voltage sensor 210 is used to monitor the battery operating voltage to determine whether the battery is in a normal charge and discharge state. The temperature sensor 220 is used to detect the surface and internal temperature of the battery in real time to prevent thermal runaway caused by overheating. The current sensor 230 is used to monitor the battery charge and discharge current to ensure that the current value fluctuates within a safe range. The pressure sensor 240 is used to monitor the internal pressure change of certain specific types of batteries (such as lithium-ion batteries) to prevent safety problems caused by internal gas accumulation; The protection device 300 is used to delay the protection operation of the monitoring device 200 to reduce or avoid the consequences of battery thermal runaway; The supervision center 100 includes a network database 110, an experimental subsystem 120, a processor 130 and an execution terminal 140. The network database 110, the experimental subsystem 120, the processor 130 and the execution terminal 140 communicate with each other through the network. The network database 110 is used to collect, store and provide historical data and big data information of battery thermal runaway, and divide the data in the corresponding information into several groups according to time, voltage, temperature, current and pressure parameters, and store the collected data in a preset format and structure to ensure the integrity and traceability of the data, and provide the required data support for the experimental subsystem 120. The experimental subsystem 120 is used to establish a thermal runaway risk warning model, and warn the time of battery thermal runaway according to the model data. The processor 130 is used to receive and output the information results of the supervision center 100, the network database 110 and the experimental subsystem 120. The execution terminal 140 is used to receive the coordination instructions of the processor 130 and publish information according to the instructions. The information release includes but is not limited to the release of warning information and system status update.

[0026] Among them Figure 2 and Figure 4 As shown, the monitoring device 200 includes a plurality of voltage sensors 210, a temperature sensor 220, a current sensor 230 and a pressure sensor 240. The voltage sensor 210 is used to detect voltage changes at multiple detection nodes of the battery, and provide key data for analyzing the working state, charge and discharge performance and potential fault hazards of the battery. The temperature sensor 220 is used to detect temperature changes at multiple detection nodes of the battery, including parameters such as the self-heating starting temperature, thermal runaway starting temperature, and thermal runaway maximum temperature of the battery. The current sensor 230 is used to detect current changes at multiple detection nodes of the battery. The pressure sensor 240 is used to detect pressure changes at multiple detection nodes of the battery, which is convenient for judging whether the battery package is intact, whether the electrolyte is leaking, and whether the battery is swollen. A diagnostic component for judging whether a fault occurs at the corresponding detection node is provided on one side of the sensor, which can improve the reliability and stability of the monitoring device 200, ensure accurate monitoring and timely response of the battery state, facilitate understanding whether a line or sensor fails, and avoid data loss resulting in failure to import data into the model in time, which is inconvenient for subsequent early warning operations.

[0027] Among them Figure 4 As shown, the diagnostic component includes an electrically connected fault judgment module 250 and an indicator light 260. The fault judgment module 250 is used to identify the fault conditions of different sensors and lines, and to prompt whether the sensors and lines meet the fault conditions through the indicator light 260. Through the fault judgment module 250, the circuits of the sensors and lines can be inspected to avoid circuit short circuits. When the sensors and lines fail, the indicator light 260 emits red light to facilitate subsequent shooting operations of the monitoring node set.

[0028] Among them Figure 2 and Figure 5 As shown, the protective device 300 includes a protective cover 310 and a fire extinguishing device 320, and may also be provided with a heat dissipation and cooling device and an exhaust device. The heat dissipation and cooling device includes but is not limited to a fan, a coolant circulation, etc., to reduce the battery temperature. The exhaust device can reduce the possibility of the battery generating harmful gases and accumulating them to cause an explosion. The protective cover 310 is disposed on the outside of the monitoring device 200, and the fire extinguishing device 320 is electrically connected to the execution terminal 140, so as to facilitate the issuance of a fire extinguishing command through the execution terminal 140, thereby ensuring the overall practicality of the system.

[0029] Among them Figure 2 and Figure 6 As shown, the experimental subsystem 120 includes: The preprocessing module 121 is used to remove abnormal values ​​and duplicate data and convert data of different dimensions into the same dimension. Abnormal values ​​may be caused by sensor failure, data transmission error, etc., which will interfere with subsequent analysis and prediction. The preprocessing module 121 will identify and delete these abnormal and duplicate data to ensure the accuracy of the analysis basis; The feature extraction module 122 is used to extract characteristic information that can reflect battery thermal runaway from the original data, including temperature change trend, pressure change rate, current and voltage change rate. The feature extraction module 122 can accurately capture these subtle and important signals, providing a strong basis for building an early warning model; The model training module 123 is used to train the model using historical data through different learning algorithms, and obtain a preliminary thermal runaway warning model by adjusting model parameters and feature selection. During the training process, the module will continuously iterate and optimize the model parameters to improve the prediction accuracy of the model; The model optimization module 124 compares the prediction models and data of different algorithms and obtains the optimal early warning model through feature fusion to ensure the reliability of the model in practical applications; The thermal runaway judgment module 125 judges whether the battery will experience thermal runaway and the time of thermal runaway based on historical data. The module receives data from the monitoring device 200 in real time and inputs it into the early warning model. The model outputs a prediction result, indicating the probability of the battery experiencing thermal runaway in the future. When the prediction result exceeds the set threshold, the module triggers the early warning mechanism and sends early warning information to relevant personnel.

[0030] Among them Figure 6 As shown, the model training module 123 adopts prediction models of long short-term memory network, time convolution network and GRU neural network types, couples the above types with equal weights, combines their respective advantages, avoids the problem of excessive deviation of coefficients trained by each model, and uses the compared early warning model as the optimal detection model. Since the model is trained and tested using multi-battery parameter data, the prediction results obtained based on real-time monitoring data are also applicable to the development of the working status of the corresponding battery.

[0031] Among them Figure 6 As shown, the thermal runaway judgment module 125 sets the upper limit of the thermal runaway threshold to E according to the historical data of the battery thermal runaway. 上 , the lower limit of thermal runaway threshold is set to E 下When the voltage, temperature, current and pressure parameters of several batteries are working normally, the variation ranges are all within the range of the upper and lower limits of the thresholds. The thermal runaway judgment module 125 receives the real-time prediction data from the thermal runaway warning model, and compares these data with the set thresholds. When any parameter exceeds the upper threshold or is lower than the lower threshold, it is judged that the battery may be in a thermal runaway state, and a warning signal is sent to the processor 130, so that relevant personnel can make instructions in time. Subsequently, the sensors at different positions can be analyzed and judged according to the parameter data in this time period.

[0032] Among them Figure 1 As shown, a monitoring node set is also provided on one side of the battery, and the monitoring node set is used to monitor the surface state of the battery and the surrounding environment in real time. The surface state includes but is not limited to the humidity, deformation and other states of the battery surface, so as to facilitate timely detection of abnormal conditions on the battery surface. The surrounding environment includes but is not limited to the state of the components surrounding the battery, etc., and the above information is transmitted to the result display module 150 so that relevant personnel can intuitively understand the real-time state of the battery and its surrounding environment.

[0033] Among them Figure 2 and Figure 3 As shown, the result display module 150 is used to receive the data information transmitted by the processor 130, and convert it into the form of a growth curve and a statistical chart, and display the results. The growth curve can display the changing trend of battery performance over time, and can also display out-of-control data, including but not limited to voltage-time data, temperature-time data, pressure-time data and current-time data within a certain time range before and after thermal runaway, which is convenient for subsequent analysis. The statistical chart can display the distribution of various parameters, abnormal values, etc., which is convenient for displaying the converted visualization results to relevant personnel, which helps relevant personnel to quickly understand the operating status of the battery system and promptly discover potential safety risks.

[0034] Among them Figure 7 As shown, a method for using a battery thermal runaway detection system based on a warning function is also included, and the specific steps of use are as follows: S1, collecting voltage, current, temperature and pressure parameters of several fault-free batteries in different time periods through the monitoring device 200, and transmitting the data information to the experimental subsystem 120 through the processor 130; S2, using the diagnostic component to determine in real time whether the lines and sensors at multiple detection nodes are faulty, determine whether the data information is accurate, and transmit the above information to the result display module 150; S3. Establish a thermal runaway warning model, input the voltage, current, temperature and pressure parameters of a fault-free battery into the model, and perform a battery thermal runaway simulation analysis; S4. The thermal runaway judgment module 125 is provided with upper and lower limits of thermal runaway thresholds. When the predicted parameter data is not within the threshold interval, the execution terminal 140 outputs a safety control instruction, which includes disconnecting the connection line and sounding a buzzer alarm.

[0035] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A battery thermal runaway detection system based on early warning function, characterized in that: include: A monitoring center (100) is used to monitor the data information of multiple batteries in real time and to warn of the time data of battery thermal runaway, so as to facilitate the timely release of warning information and notification announcements; A monitoring device (200), used for collecting thermal runaway parameters of each detection node of a plurality of batteries, wherein the thermal runaway parameters include battery voltage, temperature, current and pressure; A protection device (300), used for delaying a protection operation on the monitoring device (200); The supervision center (100) includes a network database (110), an experimental subsystem (120), a processor (130) and an execution terminal (140). The network database (110) is used to collect, store and provide historical data and big data information of battery thermal runaway, and divide a number of data in the corresponding information into a number of groups according to time, voltage, temperature, current and pressure parameters. The experimental subsystem (120) is used to establish a thermal runaway risk warning model and warn the time of battery thermal runaway according to the model data. The processor (130) is used to receive and output information results of the supervision center (100), the network database (110) and the experimental subsystem (120). The execution terminal (140) is used to receive coordination instructions from the processor (130) and publish information according to the instructions.

2. The battery thermal runaway detection system based on early warning function according to claim 1 is characterized in that: The monitoring device (200) comprises a plurality of voltage sensors (210), a temperature sensor (220), a current sensor (230) and a pressure sensor (240); the voltage sensor (210) is used to detect voltage changes at a plurality of detection nodes of a battery; the temperature sensor (220) is used to detect temperature changes at a plurality of detection nodes of a battery; the current sensor (230) is used to detect current changes at a plurality of detection nodes of a battery; the pressure sensor (240) is used to detect pressure changes at a plurality of detection nodes of a battery; and a diagnostic component for determining whether a fault occurs at a corresponding detection node is provided on one side of each of the sensors.

3. The battery thermal runaway detection system based on early warning function according to claim 2 is characterized in that: The diagnostic component comprises an electrically connected fault judgment module (250) and an indicator light (260); the fault judgment module (250) is used to identify fault conditions of different sensors and circuits, and to indicate whether the sensors and circuits meet the fault conditions through the indicator light (260).

4. The battery thermal runaway detection system based on early warning function according to claim 1 is characterized in that: The protection device (300) comprises a protection cover (310) and a fire extinguishing device (320); the protection cover (310) is arranged outside the monitoring device (200); and the fire extinguishing device (320) is electrically connected to the execution terminal (140).

5. The battery thermal runaway detection system based on early warning function according to claim 1 is characterized in that: The experimental subsystem (120) includes: A preprocessing module (121) is used to remove outliers and duplicate data and convert data of different dimensions into the same dimension; A feature extraction module (122) is used to extract feature information that can reflect battery thermal runaway from the original data, including temperature change trend, pressure change rate, and current and voltage change rate; A model training module (123) is used to perform model training using historical data through different learning algorithms, and obtain a preliminary thermal runaway warning model by adjusting model parameters and feature selection; The model optimization module (124) compares the prediction models and data of different algorithms and obtains the optimal early warning model through feature fusion; The thermal runaway judgment module (125) judges whether the battery will experience thermal runaway and the time when the thermal runaway will occur based on historical data.

6. The battery thermal runaway detection system based on early warning function according to claim 5 is characterized in that: The model training module (123) adopts prediction models of long short-term memory network, temporal convolution network and GRU neural network type.

7. The battery thermal runaway detection system based on early warning function according to claim 5 is characterized in that: The thermal runaway judgment module (125) sets the upper limit of the thermal runaway threshold to E according to the historical data of the battery thermal runaway. 上 , the lower limit of thermal runaway threshold is set to E 下 , the variation ranges of voltage, temperature, current and pressure parameters of some of the batteries when they are working normally are all within the range of upper and lower limits of the thresholds.

8. The battery thermal runaway detection system based on early warning function according to claim 1 is characterized in that: A monitoring node set is also provided on one side of the battery, and the monitoring node set is used to monitor the surface state and surrounding environment of the battery in real time, and transmit the above information to the result display module (150).

9. The battery thermal runaway detection system based on early warning function according to claim 1 is characterized in that: The result display module (150) is used to receive data information transmitted by the processor (130), convert it into the form of growth curves and statistical charts, and display the results.

10. The battery thermal runaway detection system based on early warning function according to claim 1, characterized in that: It also includes a method for using a battery thermal runaway detection system based on an early warning function, and the specific steps of use are as follows: S1, collecting voltage, current, temperature and pressure parameters of a plurality of fault-free batteries in different time periods through a monitoring device (200), and transmitting the data information to an experimental subsystem (120) through a processor (130); S2, using the diagnostic component to determine in real time whether the lines and sensors at multiple detection nodes are faulty, determine whether the data information is accurate, and transmit the above information to the result display module (150); S3. Establish a thermal runaway warning model, input the voltage, current, temperature and pressure parameters of a fault-free battery into the model, and perform a battery thermal runaway simulation analysis; S4. The thermal runaway judgment module (125) is provided with upper and lower limits of thermal runaway thresholds. When the predicted parameter data is not within the threshold range, a safety control instruction is output through the execution terminal (140). The safety control instruction includes disconnecting the connection line and sounding a buzzer alarm.

Images