A multi-parameter fusion early warning method and system for thermal runaway of lithium iron phosphate batteries

Abstract

The present invention discloses a multi-parameter fusion early warning method for thermal runaway of a lithium iron phosphate battery, the method comprising: when a thermal runaway occurs in an experimental lithium iron phosphate battery for data collection, data information of multiple characteristic physical quantities is collected; data processing is performed on the data information, and characteristic parameters are extracted from the processed data to obtain a first characteristic parameter; the first characteristic parameter is used to calculate a priori probability; data information of multiple characteristic physical quantities is collected for the lithium iron phosphate battery to be tested, a second characteristic parameter is obtained, the second characteristic parameter is fused, and the posterior probability of thermal runaway occurring under the current data information after fusion is output to determine whether thermal runaway occurs; when it is determined that thermal runaway occurs, timely early warning is given to the thermal runaway event in the early stage of the occurrence of thermal runaway. The multi-parameter monitoring method of the present invention greatly advances the early warning time, providing more time for fault handling.

Description

Technical Field

[0001] The present invention relates to the field of thermal runaway detection of lithium batteries, and in particular to a multi-parameter fusion early warning method and system for thermal runaway of lithium iron phosphate batteries. Background Art

[0002] As traditional fossil energy sources are gradually depleted, lithium battery technology, as a favorable candidate technology for energy structure transformation and achieving carbon neutrality, has a huge application market in electric vehicles, renewable energy storage systems and consumer electronics. During the use of lithium batteries, their lifespan and safety have always received high attention. When lithium batteries are subjected to external mechanical damage, electrical abuse, and thermal abuse, there is a risk of thermal runaway failure, which can cause fire or even explosion. At present, serious accidents caused by thermal runaway of lithium batteries continue to occur, resulting in a large number of casualties and property losses. Therefore, studying how to monitor and warn when thermal runaway failures occur in lithium batteries is of great significance to the large-scale use of lithium batteries.

[0003] Studies have shown that when the battery is subjected to external forces such as extrusion, collision, and puncture, it may cause deformation and stress of the battery, leading to mechanical failure of the internal diaphragm, electrode material and other components of the battery. When the battery is in a state of electrical abuse such as overcharge or overdischarge for a long time, the electrode material structure is severely damaged, the electrolyte decomposes to produce a large amount of gas and causes a sharp increase in internal pressure, leading to thermal runaway or explosion of the battery. In the case of thermal abuse, the temperature inside the battery rises abnormally, causing the electrolyte to decompose and produce a large amount of gas at 60-80°C. When the temperature rises to more than 180°C, the battery will short-circuit. If the diaphragm shrinks or melts during this process, the battery will eventually explode. In short, battery thermal runaway is the result of various adverse phenomena inside the battery, including internal pressure, gas, and heat reaching a certain level. Real-time monitoring of changes in physical (voltage, stress, temperature) and chemical parameters (gas) inside the battery is the fundamental way to prevent the development of thermal runaway and provide timely warnings.

[0004] At present, the early warning methods related to lithium battery safety still remain at the characterization and detection of a single thermal runaway parameter, such as temperature detection method based on thermocouples, electrochemical impedance method, terminal voltage method, smoke detection method, gas sensor method, etc. However, due to the diversity and complexity of battery internal parameters, when thermal runaway occurs, the electrochemical reaction, structural stress, fluid and heat transfer mechanism inside the battery interact with each other, and different levels of sensor information need to complement each other, through multi-source signals to more comprehensively and systematically monitor the diverse and changing information inside the battery, better warn the battery status, and effectively avoid the occurrence of battery accidents. Summary of the invention

[0005] In order to solve the above technical problems, the purpose of the present invention is to propose a multi-parameter fusion early warning method for thermal runaway of lithium iron phosphate batteries, which is suitable for early warning of thermal runaway failures occurring in lithium iron phosphate batteries.

[0006] In order to achieve the above object, the present invention adopts the following scheme.

[0007] A multi-parameter fusion early warning method for thermal runaway of a lithium iron phosphate battery, the method comprising the following steps:

[0008] S100, when a thermal runaway occurs in an experimental lithium iron phosphate battery used for data collection, data information of multiple characteristic physical quantities is collected;

[0009] S200, processing the data information, and extracting characteristic parameters from the processed data to obtain first characteristic parameters; the first characteristic parameters are used to calculate a priori probability;

[0010] S300, collecting data information of multiple characteristic physical quantities that are the same as S100 for the lithium iron phosphate battery to be tested, processing the data information, extracting characteristic parameters from the processed data, obtaining second characteristic parameters, fusing the second characteristic parameters, and outputting the posterior probability of thermal runaway occurring under the current data information after fusion, to determine whether thermal runaway occurs;

[0011] S400: When it is determined that thermal runaway occurs, timely warning of the thermal runaway event is provided in an early stage of the thermal runaway.

[0012] Optionally, the multiple characteristic physical quantities include: voltage, temperature, pressure, and gas concentration.

[0013] Optionally, the second characteristic parameter is fused using a thermal runaway multi-parameter fusion warning model of a Bayesian network, wherein the characteristic parameter is discretized into different intervals according to different development stages of thermal runaway of the lithium battery.

[0014] Optionally, the thermal runaway multi-parameter fusion early warning model of the Bayesian network includes:

[0015] Step 301: Determine the Bayesian network nodes;

[0016] Step 302: Determine conditional probability and prior probability;

[0017] Step 303: Calculate the Bayesian target fusion probability of multiple sensors;

[0018] Step 304: Determine the probability of thermal runaway failure occurring based on Bayesian.

[0019] A multi-parameter early warning system for thermal runaway of a lithium iron phosphate battery, the system comprising:

[0020] An information collection module, which is used to collect data information of multiple characteristic physical quantities when a thermal runaway occurs in an experimental lithium iron phosphate battery used for data collection;

[0021] A signal transmission module, which is used to process the data information and extract characteristic parameters from the processed data to obtain a first characteristic parameter; the first characteristic parameter is used to calculate a priori probability;

[0022] A multi-source fusion calculation module is used to collect data information of multiple characteristic physical quantities that are the same as S100 for the lithium iron phosphate battery to be tested, process the data information, extract characteristic parameters from the processed data, obtain second characteristic parameters, fuse the second characteristic parameters, and output the posterior probability of thermal runaway occurring under the current data information after fusion, so as to determine whether thermal runaway occurs;

[0023] The multi-source fusion computing module is used to provide timely warning of thermal runaway events in the early stages of thermal runaway when it is determined that thermal runaway has occurred.

[0024] Optionally, the system further includes: a battery thermal runaway sealing test chamber module, and the battery thermal runaway sealing test chamber module includes: a vacuum pump, a control console, and a stainless steel circular chamber.

[0025] Optionally, the information acquisition module includes: a data recorder, which is used to monitor the voltage in real time.

[0026] Optionally, the information acquisition module further includes: a thermocouple, which is used to measure the temperature inside the sealed cavity.

[0027] Optionally, the information acquisition module further includes: a pressure transmitter, which is used to measure the pressure in the sealed cavity.

[0028] Optionally, the information acquisition module also includes: an H2 sensor, a CO sensor and an electrolyte sensor.

[0029] Compared with the prior art, the present invention has the following beneficial technical effects:

[0030] 1. Compared with the thermal runaway warning method using a single type of sensor, the method of the present invention eliminates the uncertainty caused by a single measurement and improves the accuracy of the warning.

[0031] 2. The multi-parameter monitoring method of voltage, temperature, stress, and gas (H2 concentration, CO concentration, electrolyte vapor concentration) proposed in the present invention greatly advances the warning time compared with other parameter monitoring schemes, providing more time for fault handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings illustrate exemplary embodiments of the present invention and together with the description serve to explain the principles of the present invention. These drawings are included to provide a further understanding of the present invention and are incorporated in and constitute a part of this specification.

[0033] Figure 1 It is a flow chart of a multi-parameter early warning method for thermal runaway of a lithium battery according to an embodiment of the present invention;

[0034] Figure 2 is a schematic diagram of a lithium battery thermal runaway monitoring system according to an embodiment of the present invention;

[0035] Figure 3 is a flow chart of information fusion based on Bayesian network according to an embodiment of the present invention;

[0036] Figure 4 This is an analysis diagram of a gas production process during simulation of thermal runaway of a lithium battery according to an embodiment of the present invention;

[0037] Figure 5 This is a data graph obtained by conducting a simulated lithium battery thermal runaway experiment according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The following is combined with Figures 1 to 5 The present invention is further described in detail with reference to the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant contents, rather than to limit the present invention. It is also necessary to explain that, for ease of description, only the parts related to the present invention are shown in the accompanying drawings.

[0039] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0040] Unless otherwise specified, the exemplary embodiments / embodiments shown will be understood as exemplary features that provide various details of some ways in which the technical concept of the present invention can be implemented in practice. Therefore, unless otherwise specified, the features of the various embodiments / embodiments can be combined, separated, interchanged and / or rearranged without departing from the technical concept of the present invention.

[0041] The use of cross-hatching and / or shading in the accompanying drawings is generally used to make the boundaries between adjacent components clear. As such, unless otherwise specified, the presence or absence of cross-hatching or shading does not convey or indicate any preference or requirement for the specific materials, material properties, dimensions, proportions, commonalities between the components shown, and / or any other characteristics, attributes, properties, etc. of the components. In addition, in the accompanying drawings, the sizes and relative sizes of the components may be exaggerated for clarity and / or descriptive purposes. When the exemplary embodiments can be implemented differently, the specific process sequence can be performed in a different order than described. For example, two successively described processes can be performed substantially simultaneously or in an order opposite to the described order. In addition, the same figure numbers represent the same components.

[0042] When a component is referred to as being "on" or "over," "connected to," or "coupled to" another component, the component may be directly on, directly connected to, or directly coupled to the other component, or intervening components may be present. However, when a component is referred to as being "directly on," "directly connected to," or "directly coupled to" another component, there are no intervening components. For this purpose, the term "connected" may refer to a physical connection, an electrical connection, etc., with or without intervening components.

[0043] For descriptive purposes, the present invention may use spatially relative terms such as "below", "beneath", "under", "lower", "above", "upper", "above", "higher", and "side (e.g., as in "sidewall")" to describe the relationship of one component to another (other) component as shown in the accompanying drawings. The spatially relative terms are intended to encompass different orientations of the device in use, operation, and / or manufacture in addition to the orientation depicted in the accompanying drawings. For example, if the device in the accompanying drawings is turned over, components described as "below" or "beneath" other components or features would then be positioned "above" the other components or features. Thus, the exemplary term "below" can encompass both the "above" and "below" orientations. Furthermore, the device may be otherwise oriented (e.g., rotated 90 degrees or at other orientations), and the spatially relative descriptors used herein should be interpreted accordingly.

[0044] The terms used here are for the purpose of describing specific embodiments, and are not intended to be restrictive. As used here, unless the context clearly indicates otherwise, the singular forms "one (kind, person)" and "said (the)" are also intended to include plural forms. In addition, when the terms "comprise" and / or "include" and their variations are used in this specification, it is explained that there are stated features, integral bodies, steps, operations, parts, assemblies and / or their groups, but it is not excluded that there are or add one or more other features, integral bodies, steps, operations, parts, assemblies and / or their groups. It should also be noted that, as used here, the terms "substantially", "approximately" and other similar terms are used as approximate terms and not as degree terms, so that they are used to explain the inherent deviations of the measured values, calculated values ​​and / or the values ​​provided that will be recognized by those of ordinary skill in the art.

[0045] In one embodiment, the present invention provides a multi-parameter fusion early warning method for thermal runaway of a lithium iron phosphate battery, the method comprising the following steps:

[0046] S100, when a thermal runaway occurs in an experimental lithium iron phosphate battery used for data collection, data information of multiple characteristic physical quantities is collected;

[0047] S200, processing the data information, and extracting characteristic parameters from the processed data to obtain first characteristic parameters; the first characteristic parameters are used to calculate a priori probability;

[0048] S300, collecting data information of multiple characteristic physical quantities that are the same as S100 for the lithium iron phosphate battery to be tested, processing the data information, extracting characteristic parameters from the processed data, obtaining second characteristic parameters, fusing the second characteristic parameters, and outputting the posterior probability of thermal runaway occurring under the current data information after fusion, to determine whether thermal runaway occurs;

[0049] S400: When it is determined that thermal runaway occurs, timely warning of the thermal runaway event is provided in an early stage of the thermal runaway.

[0050] Optionally, the multiple characteristic physical quantities include: voltage, temperature, pressure, and gas concentration.

[0051] Optionally, the second characteristic parameter is fused using a thermal runaway multi-parameter fusion warning model of a Bayesian network, wherein the characteristic parameter is discretized into different intervals according to different development stages of thermal runaway of the lithium battery.

[0052] Optionally, the thermal runaway multi-parameter fusion early warning model of the Bayesian network includes:

[0053] Step 301: Determine the Bayesian network nodes;

[0054] Step 302: Determine conditional probability and prior probability;

[0055] Step 303: Calculate the Bayesian target fusion probability of multiple sensors;

[0056] Step 304: Determine the probability of thermal runaway failure occurring based on Bayesian.

[0057] In one embodiment, if Figure 1 As shown, the present invention provides a multi-parameter fusion early warning method for thermal runaway of a lithium iron phosphate battery, the method comprising the following steps:

[0058] S100, when the lithium iron phosphate battery has thermal runaway, collect data information of characteristic physical quantities; the characteristic physical quantities include: voltage, temperature, pressure, gas concentration; the gas concentration includes: H2 concentration, CO concentration, electrolyte vapor concentration;

[0059] Among them, when the battery is punctured, squeezed, overcharged, over-discharged, or thermally abused in the sealed cavity of the lithium battery, the physical quantities of different characteristics are collected through voltage, temperature, pressure, H2, CO, and DMC sensors;

[0060] S200, transmitting the data information to a host computer through a DAQM multi-channel acquisition module, and the host computer processes the data and extracts characteristic parameters from the processed data;

[0061] S300, deploying the sensor near the lithium battery, collecting data information of the same characteristic physical quantity as S100 for the lithium iron phosphate battery to be tested, processing the data information, extracting and fusing characteristic parameters of the processed data, outputting the posterior probability of thermal runaway occurring under the current data information after fusion, and determining whether thermal runaway occurs;

[0062] S400: When it is determined that thermal runaway occurs, timely warning of the thermal runaway event is provided in an early stage of the thermal runaway.

[0063] In this embodiment, if Figure 2 As shown, S100 includes:

[0064] 1. Place the battery cell discharged to 0% SOC in a 4 L self-made sealed chamber, which consists of a vacuum pump, a control console, and a stainless steel cylindrical chamber; remove the current limiting and temperature tripping safety devices from the battery cell (remove the battery cell cover), and leave the test battery in the chamber for 30 minutes to ensure that the voltage and test temperature remain constant;

[0065] 2. Start the thermal runaway experiment and use the SIN-R5000C data recorder to monitor the battery voltage in real time. Use a K-type (±0.4%) thermocouple to measure the temperature inside the sealed cavity, and a pressure transmitter (0.1-0.5 MPa) to measure the pressure inside the sealed cavity. Place an H2 sensor (TGS821), a CO sensor (TGS5042) and a DMC sensor (TGS1820) on the inner wall of the cavity to detect the gas released by the thermal runaway of the battery. Use a Hikvision 4K professional-grade camera to collect image data in real time.

[0066] In S200, the data information is transmitted to the host computer through the DAQM multi-channel acquisition module, and the host computer processes the data and extracts features from the processed data;

[0067] The host computer uses a data acquisition and display system written in Visual Basic. By reading the data of voltage, temperature, pressure, and gas concentration, the corresponding data acquisition channel is opened to display the data change curve in real time. Since thermal runaway is a dynamic process, the data changes of various parameters per unit time are not obvious. The average of all data collected per minute is taken, and the characteristic values ​​of each sensor are discretized as the input data of the Bayesian network.

[0068] In this embodiment, if Figure 3 As shown, in S300, the sensor is deployed near the lithium battery, and data information of the characteristic physical quantities that are the same as those of S100 are collected for the lithium iron phosphate battery to be tested. The data information is processed, and characteristic parameters are extracted from the processed data. The characteristic parameters are fused using a thermal runaway multi-parameter fusion warning model of a Bayesian network, and the posterior probability of thermal runaway occurring under the current data information after fusion is output, so as to facilitate timely warning of thermal runaway events in the early stages of thermal runaway.

[0069] In order to facilitate the use of the Bayesian network method, according to the different development stages of thermal runaway of lithium batteries, the characteristic parameters of voltage, temperature, pressure, and gas concentration are discretized and divided into the following different intervals.

[0070] Thermal runaway of lithium batteries can be divided into four stages: in the first stage, the battery temperature continues to rise, the stress and voltage in the cavity remain almost unchanged, a series of chemical reactions occur inside the battery, and gas is released; in the second stage, the negative potential of the lithium battery shifts, the voltage rises sharply, the battery safety valve opens, a large amount of gas and electrolyte vapor are released, and the internal stress rises sharply; the third stage is the stage of severe thermal runaway of the battery, the surface temperature of the battery rises exponentially, and a large amount of gas is released, and a voltage plateau period appears; in the fourth stage, when the internal temperature of the battery rises to a certain level, the diaphragm ruptures, a large-scale short circuit occurs inside the battery, the voltage increases exponentially, and the violent side reactions cause the internal temperature of the battery cell to rise further, the reaction rate between the chemical substances reaches a peak, and a large amount of gas is released. In the process of thermal runaway, the characteristic parameters will continue to change continuously with the development of the thermal runaway process. According to the characteristics of the above-mentioned different stages of thermal runaway, the characteristic parameters are discretized and applied to the Bayesian network.

[0071] Thermal runaway stage 1, voltage range is 3-4V, temperature range is 20-30℃, chamber pressure is 100-105 kPa, H2 concentration is 0-10 ppm, CO concentration is 0-10 ppm, DMC concentration is 0-10 ppm;

[0072] Thermal runaway stage 2, voltage range is 4-6V, temperature range is 30-50℃, chamber pressure is 105-110 kPa, H2 concentration is 10-400 ppm, CO concentration is 10-100 ppm, DMC concentration is 10-100 ppm;

[0073] Thermal runaway stage 3, voltage range is 4-6V, temperature range is 50-100℃, chamber pressure is 110-120 kPa, H2 concentration is 400-1000 ppm, CO concentration is 10-600 ppm, DMC concentration is 100-500 ppm;

[0074] Thermal runaway stage 4, voltage range>6V, temperature range>100 degrees Celsius, chamber pressure>120 kPa, H2 concentration>1000 ppm, CO concentration>600 ppm, DMC concentration>500 ppm;

[0075] The thermal runaway multi-parameter fusion early warning model of the Bayesian network includes the following steps:

[0076] Step 1: Determine the Bayesian network nodes;

[0077] In the fusion network of thermal runaway warning, the measured values ​​B of voltage, temperature, cavity pressure, H2 concentration and CO concentration are taken as the root node, and the thermal runaway event A is taken as the child node; the probability P(A) represents the probability of thermal runaway event, which is the "prior probability", and the observed value B affects the observation of thermal runaway event A, which is the "posterior knowledge"; the probability of event A after the observation B is tested is expressed as the conditional probability: P(A|B), at this time:

[0078] ;

[0079] Step 2: Determine the conditional probability and prior probability; Use 6 sensors to measure the voltage, temperature, chamber pressure, H2 concentration, CO concentration, and DMC concentration parameters when thermal runaway occurs. Assume that event A1 is thermal runaway, A2 is no thermal runaway, and B j is the target identity description given by the jth sensor, and now we have:

[0080] ,

[0081] ;

[0082] Step 3: Calculate the Bayesian target fusion probability of multiple sensors;

[0083] Known P(A i |B j ), when the observation results of the six sensors are independent of each other and the observation feature quantities are independent, it can be known that the decision result of whether the battery thermal runaway occurs after the fusion of the six sensor information in the system is A i The posterior probability is:

[0084] ;

[0085] Step 4: Determine the probability of thermal runaway failure based on Bayesian;

[0086] After obtaining the fusion probabilities of thermal runaway and non-thermal runaway, the fusion probabilities of A1 and A2 are compared to determine whether thermal runaway occurs. The identification strategy is as follows:

[0087] .

[0088] The measured sample data is used as the learning sample of the Bayesian network model. Six sensors are used to measure the voltage, temperature, chamber pressure, H2 concentration, and CO concentration parameters when thermal runaway occurs. It is assumed that event A1 is thermal runaway, A2 is no thermal runaway, and B j For the target identity description given by the jth sensor, the “prior data” is:

[0089]

[0090]

[0091] The observed battery status monitoring data is input to calculate the Bayesian posterior probability:

[0092]

[0093] After obtaining the fusion probability of thermal runaway and non-thermal runaway, determine whether the battery has thermal runaway.

[0094] .

[0095] According to the Bayesian probability formula, the probability of thermal runaway under the current monitoring parameters can be calculated, that is, the "prior" determines the "posterior". If the probability of thermal runaway is greater than the probability of no thermal runaway, it is judged that the battery has thermal runaway.

[0096] Table 1 Multi-parameter fusion warning results of lithium battery thermal runaway based on Bayesian network

[0097]

[0098] Table 1 lists the results of early warning of battery thermal runaway by the Bayesian network multi-parameter fusion method in this embodiment. Compared with the early warning results of a single parameter, the Bayesian multi-source fusion method enables the multi-layer information of physical and chemical property changes when thermal runaway occurs to complement each other, greatly eliminating the uncertainty of the system and improving the effectiveness of early warning. The multi-parameter monitoring method of the present invention uses the fault gases H2, CO and DMC first generated before thermal runaway as judgment parameters. Compared with other parameter monitoring schemes, the early warning time is greatly advanced, providing more time for fault handling.

[0099] In one embodiment, referring to Figure 2 In order to verify that the temperature, voltage and stress sensors in the method described in the present invention can reflect the physical and chemical states of the four different development stages of thermal runaway from initial to severe, and to prove the effectiveness of using H2, CO gas and DMC gas sensors to monitor the gas concentration and the early warning effect of thermal runaway, the following experiments were carried out.

[0100] 1. Conduct consistency testing before conducting thermal runaway experiments on lithium batteries;

[0101] Specifically, the battery device was placed in a constant temperature box at 25°C, and a Neware tester was used to cycle between 2.5 V and 3.65 V voltage limits for 3 times to select batteries with good consistency.

[0102] 2. The battery was placed in a 4L homemade sealed chamber for acupuncture or overcharge. The sealed chamber consisted of a vacuum pump, a console, and a stainless steel cylindrical chamber. A SIN-R5000C data recorder was used to monitor the battery voltage in real time. A K-type (±0.4%) thermocouple was used to measure the temperature in the sealed chamber, and a pressure transmitter (0.1-0.5 MPa) was used to measure the pressure in the sealed chamber. An H2 sensor (TGS821), a CO sensor (TGS5042), and a DMC sensor (TGS1820) were placed on the inner wall of the chamber to detect the gas released by thermal runaway of the battery. A Hikvision 4K professional-grade camera was used to collect image data in real time.

[0103] 3. Transmit the data to the host computer through the DAQM multi-channel acquisition module and perform feature extraction on the processed data.

[0104] After the thermal runaway is over, the exhaust gas in the chamber is collected into a gas bag by the ATEST ATS-BC vacuum gas sampling pump. Two Agilent 8860 gas chromatographs with different configurations are used to separate, identify and quantify the gaseous products collected after the thermal runaway. One of the chromatographs uses an Al2O3 column, an MS5A column and an HS Q column for chromatographic separation. Both the MS 5A and HS Q columns use hydrogen as the GC carrier gas. Both chromatographs are equipped with thermal conductivity detectors for the detection and quantitative analysis of species. At the same time, the Al2O3 column uses nitrogen as the GC carrier gas and is equipped with a flame ionization detector. This gas chromatograph is used to analyze CO2 and hydrocarbons. The other gas chromatograph is equipped with an HP-Al2O3 column, N2 as the GC carrier gas, and a flame ionization detector. The gas chromatograph was calibrated for CO, H2, and DMC, and each test was repeated three times to ensure the accuracy of the experimental results. According to the carrier gas composition analyzed by the above gas chromatograph, H2, CO, and DMC sensors were placed respectively. It proves that the selected gas is an effective early warning for the thermal runaway process.

[0105] Depend on Figure 5 From the results of the H2, CO, and DMC sensors monitoring the thermal runaway gas production process, it can be seen that the H2, CO, and DMC sensors responded 579 s (T4-T2) before the start of thermal runaway. The H2, CO, and DMC sensors have a good early warning effect on battery thermal runaway.

[0106] Table 2 shows the test results of thermal runaway of three groups of batteries under this embodiment, and statistics the advance time of thermal runaway warning by different sensors. Compared with commercial CH4, C2H4 gas sensors and voltage, temperature, and stress sensors, this method can predict thermal runaway up to 579s in advance, greatly improving the warning time.

[0107] Table 2 H2 CO DMC sensor advance effect

[0108]

[0109] Depend on Figure 5 The voltage, temperature, and stress sensors shown in the figure provide early warning data for battery thermal runaway. It is found that during the thermal runaway process, the monitored battery voltage, temperature, and stress all changed dramatically and the patterns of change were different. The above parameters can all be applied to multi-parameter early warning of thermal runaway of lithium batteries.

[0110] In one embodiment, the present invention provides a multi-parameter early warning system for thermal runaway of a lithium iron phosphate battery, the system comprising:

[0111] An information collection module, which is used to collect data information of multiple characteristic physical quantities when a thermal runaway occurs in an experimental lithium iron phosphate battery used for data collection;

[0112] A signal transmission module, which is used to process the data information and extract characteristic parameters from the processed data to obtain a first characteristic parameter; the first characteristic parameter is used to calculate a priori probability;

[0113] A multi-source fusion calculation module is used to collect data information of multiple characteristic physical quantities that are the same as S100 for the lithium iron phosphate battery to be tested, process the data information, extract characteristic parameters from the processed data, obtain second characteristic parameters, fuse the second characteristic parameters, and output the posterior probability of thermal runaway occurring under the current data information after fusion, so as to determine whether thermal runaway occurs;

[0114] The multi-source fusion computing module is used to provide timely warning of thermal runaway events in the early stages of thermal runaway when it is determined that thermal runaway has occurred.

[0115] Optionally, the system further includes: a battery thermal runaway sealing test chamber module, and the battery thermal runaway sealing test chamber module includes: a vacuum pump, a control console, and a stainless steel circular chamber.

[0116] Optionally, the information acquisition module includes: a data recorder, which is used to monitor the voltage in real time.

[0117] Optionally, the information acquisition module further includes: a thermocouple, which is used to measure the temperature inside the sealed cavity.

[0118] Optionally, the information acquisition module further includes: a pressure transmitter, which is used to measure the pressure in the sealed cavity.

[0119] Optionally, the information acquisition module also includes: an H2 sensor, a CO sensor and an electrolyte sensor.

[0120] In one embodiment, referring to Figure 2 , the present invention provides a multi-parameter early warning system for thermal runaway of a lithium iron phosphate battery, the system comprising: a battery thermal runaway parameter monitoring system;

[0121] The battery thermal runaway parameter monitoring system includes: a battery thermal runaway sealing test cavity module, an information acquisition module, a signal transmission module, a multi-source fusion calculation module, and a multi-source fusion calculation module.

[0122] The battery thermal runaway sealed test chamber module includes: a vacuum pump, a console, and a stainless steel circular chamber; the information acquisition module includes: a SIN-R5000C data recorder for real-time voltage monitoring; a K-type (±0.4%) thermocouple for measuring the temperature in the sealed chamber; a pressure transmitter (0.1-0.5 MPa) for measuring the pressure in the sealed chamber; an H2 sensor (TGS821), a CO sensor (TGS5042), and an electrolyte sensor (TGS1820) placed on the inner wall of the chamber for detecting the gas released by the battery thermal runaway; and a Hikvision 4K professional-grade camera for real-time image data acquisition. The present invention can be applied to early warning of thermal runaway scenarios of lithium batteries in portable electronic devices such as smartphones.

[0123] In one embodiment, the cavity module cavity volume may be 5L, which is used to test cylindrical LiFePO4 batteries.

[0124] In the description of this specification, the description with reference to the terms "one embodiment / method", "some embodiments / methods", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment / method or example are included in at least one embodiment / method or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment / method or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments / methods or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments / methods or examples described in this specification and the features of the different embodiments / methods or examples, unless they are contradictory.

[0125] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0126] It should be understood by those skilled in the art that the above embodiments are only for the purpose of clearly illustrating the present invention, and are not intended to limit the scope of the present invention. For those skilled in the art, other changes or modifications may be made based on the above disclosure, and these changes or modifications are still within the scope of the present invention.

Claims

1. A multi-parameter fusion early warning method for thermal runaway of lithium iron phosphate batteries, characterized in that: The method comprises the following steps: S100, when a thermal runaway occurs in an experimental lithium iron phosphate battery used for data collection, data information of multiple characteristic physical quantities is collected; S200, processing the data information, and extracting characteristic parameters from the processed data to obtain first characteristic parameters; the first characteristic parameters are used to calculate a priori probability; S300, collecting data information of multiple characteristic physical quantities that are the same as S100 for the lithium iron phosphate battery to be tested, processing the data information, extracting characteristic parameters from the processed data, obtaining second characteristic parameters, fusing the second characteristic parameters, and outputting the posterior probability of thermal runaway occurring under the current data information after fusion, to determine whether thermal runaway occurs; S400: when it is determined that thermal runaway occurs, timely warning of the thermal runaway event is provided in the early stage of the thermal runaway; Among them, in S300, the sensor is deployed near the lithium battery, and the data information of the characteristic physical quantity same as that of S100 is collected for the lithium iron phosphate battery to be tested, and the data information is processed, and the characteristic parameters are extracted from the processed data, and the characteristic parameters are fused by using the thermal runaway multi-parameter fusion warning model of the Bayesian network, and the posterior probability of thermal runaway occurring under the current data information after fusion is output, so as to facilitate timely warning of thermal runaway events in the early stage of thermal runaway; In order to facilitate the use of the Bayesian network method, according to the different development stages of thermal runaway of lithium batteries, the characteristic parameters of voltage, temperature, pressure, and gas concentration are discretized and divided into the following different intervals; Lithium battery thermal runaway is divided into four stages: In the first stage, the battery temperature continues to rise, the stress and voltage in the cavity remain almost unchanged, a series of chemical reactions occur inside the battery, and gas is released; In the second stage, the negative potential of the lithium battery shifts, the voltage rises sharply, the battery safety valve opens in this stage, a large amount of gas and electrolyte vapor are released, and the internal stress rises sharply; The third stage is the stage of severe thermal runaway of the battery, the surface temperature of the battery rises exponentially, and a large amount of gas is released, and a voltage plateau period appears; In the fourth stage, when the internal temperature of the battery rises to a certain level, the diaphragm ruptures, a large-scale short circuit occurs inside the battery, the voltage increases exponentially, and the violent side reactions cause the internal temperature of the battery cell to rise further, the reaction rate between the chemical substances reaches a peak, and a large amount of gas is released; In the process of thermal runaway, the characteristic parameters will continue to change with the development of the thermal runaway process. According to the characteristics of the above-mentioned different stages of thermal runaway, the characteristic parameters are discretized and applied to the Bayesian network; Thermal runaway stage 1, voltage range is 3-4V, temperature range is 20-30℃, chamber pressure is 100-105 kPa, H2 concentration is 0-10 ppm, CO concentration is 0-10 ppm, DMC concentration is 0-10 ppm; Thermal runaway stage 2, voltage range is 4-6V, temperature range is 30-50℃, chamber pressure is 105-110 kPa, H2 concentration is 10-400 ppm, CO concentration is 10-100 ppm, DMC concentration is 10-100 ppm; Thermal runaway stage 3, voltage range is 4-6V, temperature range is 50-100℃, chamber pressure is 110-120 kPa, H2 concentration is 400-1000 ppm, CO concentration is 10-600 ppm, DMC concentration is 100-500 ppm; Thermal runaway stage 4, voltage range>6V, temperature range>100 degrees Celsius, chamber pressure>120 kPa, H2 concentration>1000ppm, CO concentration>600 ppm, DMC concentration>500 ppm; The thermal runaway multi-parameter fusion early warning model of the Bayesian network includes the following steps: Step 1: Determine the Bayesian network nodes; In the fusion network of thermal runaway warning, the measured values ​​B of voltage, temperature, cavity pressure, H2 concentration and CO concentration are taken as the root node, and the thermal runaway event A is taken as the child node; the probability P(A) represents the probability of the occurrence of the thermal runaway event, which is the "prior probability", and the observed value B affects the observation of the thermal runaway event A, which is the "posterior knowledge"; the probability of the occurrence of event A after the observation B is tested is expressed as the conditional probability: P(A|B), at this time: ； Step 2: Determine the conditional probability and prior probability; Use 6 sensors to measure the voltage, temperature, chamber pressure, H2 concentration, CO concentration, and DMC concentration parameters when thermal runaway occurs. Assume that event A1 is thermal runaway, A2 is no thermal runaway, and B j is the target identity description given by the jth sensor, and now we have: ， ； Step 3: Calculate the Bayesian target fusion probability of multiple sensors; Known P(A i |B j ), when the observation results of the six sensors are independent of each other and the observation feature quantities are independent, the decision result of whether the battery thermal runaway occurs after the information fusion of the six sensors in the system is A i The posterior probability is: ； Step 4: Determine the probability of thermal runaway failure based on Bayesian; After obtaining the fusion probabilities of thermal runaway and non-thermal runaway, the fusion probabilities of A1 and A2 are compared to determine whether thermal runaway occurs. The identification strategy is as follows: ； The measured sample data is used as the learning sample of the Bayesian network model. Six sensors are used to measure the voltage, temperature, chamber pressure, H2 concentration, and CO concentration parameters when thermal runaway occurs. It is assumed that event A1 is thermal runaway, A2 is no thermal runaway, and B j For the target identity description given by the jth sensor, the "prior data" is: ， ， The observed battery status monitoring data is input to calculate the Bayesian posterior probability: ， After obtaining the fusion probability of thermal runaway and non-thermal runaway, determine whether the battery has thermal runaway. ； According to the Bayesian probability formula, the probability of thermal runaway under the current monitoring parameters is calculated, that is, the "prior" determines the "posterior"; if the probability of thermal runaway is greater than the probability of not occurring thermal runaway, it is judged that the battery has experienced thermal runaway at this time.

2. A multi-parameter early warning system for thermal runaway of lithium iron phosphate batteries, characterized in that: The system is used to implement the multi-parameter fusion early warning method for thermal runaway of a lithium iron phosphate battery according to claim 1, and the system comprises: An information collection module, which is used to collect data information of multiple characteristic physical quantities when a thermal runaway occurs in an experimental lithium iron phosphate battery used for data collection; A signal transmission module, which is used to process the data information and extract characteristic parameters from the processed data to obtain a first characteristic parameter; the first characteristic parameter is used to calculate a priori probability; A multi-source fusion calculation module is used to collect data information of multiple characteristic physical quantities that are the same as S100 for the lithium iron phosphate battery to be tested, process the data information, extract characteristic parameters from the processed data, obtain second characteristic parameters, fuse the second characteristic parameters, and output the posterior probability of thermal runaway occurring under the current data information after fusion, so as to determine whether thermal runaway occurs; The multi-source fusion computing module is used to provide timely warning of thermal runaway events in the early stages of thermal runaway when it is determined that thermal runaway has occurred.

3. The system according to claim 2, characterized in that The system further comprises: a battery thermal runaway sealing test cavity module, and the battery thermal runaway sealing test cavity module comprises: a vacuum pump, a control console, and a stainless steel circular cavity.

4. The system according to claim 2, characterized in that The information acquisition module includes: a data recorder, which is used to monitor the voltage in real time.

5. The system according to claim 4, characterized in that The information acquisition module also includes: a thermocouple, which is used to measure the temperature inside the sealed cavity.

6. The system according to claim 5, characterized in that The information acquisition module also includes: a pressure transmitter, which is used to measure the pressure in the sealed cavity.

7. The system according to claim 6, characterized in that The information acquisition module also includes: a H2 sensor, a CO sensor and an electrolyte sensor.

Images