A method and system for thermal runaway alarm of power battery based on multi-source information fusion

Abstract

This invention relates to the field of new energy vehicle power battery technology, and more specifically, to a method and system for power battery thermal runaway alarm based on multi-source information fusion. This invention performs basic probability assignment processing on the current thermal runaway characteristic parameter data and obtains weighting factors through methods such as information entropy. The basic probability assignment function is then weighted to eliminate the uncertainty in the collected thermal runaway characteristic parameter data and obtain an accurate judgment result of the current thermal runaway state. This invention employs a multi-task parallel processing approach to simultaneously analyze N power batteries within the battery pack, thereby locating the position of thermal runaway within the battery pack, facilitating subsequent thermal runaway processing and preventing further propagation of thermal runaway.

Description

Technical Field

[0001] This invention relates to the field of power battery technology for new energy vehicles, and more specifically, to a method and system for alarming thermal runaway of power batteries based on multi-source information fusion. Background Technology

[0002] The root cause of accidents involving new energy vehicles is thermal runaway caused by power battery failure.

[0003] Thermal runaway is a major safety issue. When a power battery malfunctions, the new energy power battery may experience a chain reaction of exothermic reaction within a very short time, causing the battery temperature to rise sharply. If the monitoring system fails to detect and alarm in a timely and accurate manner, it will further develop into thermal runaway, leading to a further expansion of the fault, threatening surrounding batteries, vehicles, and occupants, seriously affecting the safety of vehicle operation, and ultimately causing smoke, fire, or even explosion accidents.

[0004] Existing traditional thermal runaway alarm methods simply rely on thresholds to determine and trigger alarms. This alarm method has the following problems:

[0005] (1) Due to the complex and variable thermal runaway environment of the power battery, the data collected by the sensor is uncertain, which reduces the accuracy of the judgment;

[0006] (2) If the sensor fails, it will be impossible to effectively determine the current state of the battery, which may lead to misjudgment and missed reporting, thereby reducing the accuracy of the thermal runaway judgment result. Summary of the Invention

[0007] Therefore, it is necessary to provide a power battery thermal runaway alarm method and system based on multi-source information fusion to address the problem of inaccurate thermal runaway alarms caused by uncertainties in the data collected in existing alarm methods.

[0008] This invention is achieved using the following technical solution:

[0009] In a first aspect, the present invention discloses a method for thermal runaway alarm of power batteries based on multi-source information fusion, which is used to perform thermal runaway alarm for power batteries of new energy vehicles.

[0010] The alarm method for thermal runaway of power batteries includes the following steps:

[0011] Step 1: Obtain the data p of the i-th thermal runaway characteristic parameters at the current time. i ;i∈[1,n], where n represents the type of thermal runaway characteristic parameter, n=4; thermal runaway characteristic parameters include the internal temperature of the battery box, the CO concentration inside the battery box, the smoke concentration inside the battery box, and the temperature of the I-th power battery, I∈[1,N];

[0012] Step two, based on p i The basic probability assignment function m1(p) for not experiencing thermal runaway was calculated respectively. i The basic probability assignment function for thermal runaway is m2(p). i );

[0013] Step 3, for m1(p) i m2(p) i Performing the same processing, we obtain the weighted basic probability assignment function m1′(p) for the absence of thermal runaway. i The weighted basic probability assignment function for thermal runaway is m2′(p i ), to eliminate p i Uncertainty; among which, the methods for handling it include:

[0014] First, calculate the information entropy and variance of the basic probability assignment function; then, construct the fuzzy preference matrix based on the information entropy and variance; next, calculate the consistency matrix based on the fuzzy preference matrix; then, calculate the consistency ranking value and use it as the confidence level; then, normalize the confidence level and use it as the weighting factor; finally, perform a weighted average of the weighting factor and the basic probability assignment function to obtain the weighted basic probability assignment function.

[0015] Step 4, based on m1′(p i ), m2′(p i The fusion results are calculated according to the DS evidence theory synthesis rules. If the fusion result shows that at least one of the N power batteries has thermal runaway, an alarm is triggered.

[0016] This method for alarming thermal runaway of power batteries based on multi-source information fusion implements the method or process according to embodiments of this disclosure.

[0017] Secondly, the present invention discloses a power battery thermal runaway alarm system based on multi-source information fusion, which uses the power battery thermal runaway alarm method of the first aspect.

[0018] The power battery thermal runaway alarm system based on multi-source information fusion includes: a data acquisition unit, a basic probability assignment function calculation unit, a basic probability assignment function weighting unit, an evidence fusion unit, and an alarm unit.

[0019] The data acquisition unit is used to acquire data p of the i-th thermal runaway characteristic parameters at the current time. i i∈[1,n], where n represents the type of thermal runaway characteristic parameter. The basic probability assignment function calculation unit is used to calculate based on p i The basic probability assignment function m1(p) for not experiencing thermal runaway was calculated respectively. i The basic probability assignment function for thermal runaway is m2(p).i The basic probability assignment function weighting unit is used to assign values ​​to m1(p). i m2(p) i Performing the same processing, we obtain the weighted basic probability assignment function m1′(p) for the absence of thermal runaway. i The weighted basic probability assignment function for thermal runaway is m2′(p i ), to eliminate p i The uncertainty. Evidence fusion units are used based on m1′(p i ), m2′(p i The fusion results are calculated according to the DS evidence theory synthesis rules. The alarm unit is used to issue an alarm when the fusion result shows that at least one of the N power batteries has experienced thermal runaway.

[0020] The power battery thermal runaway alarm system based on multi-source information fusion implements the method or process according to embodiments of this disclosure.

[0021] Compared with the prior art, the present invention has the following beneficial effects:

[0022] 1. This invention performs basic probability assignment processing on the thermal runaway characteristic parameter data at the current moment and obtains weighting factors through methods such as information entropy. The basic probability assignment function is then weighted to eliminate the uncertainty in the collected thermal runaway characteristic parameter data and obtain an accurate judgment result of the thermal runaway state at the current moment.

[0023] 2. This invention adopts a multi-task parallel processing method to simultaneously analyze N power batteries in the battery box, thereby locating the location of thermal runaway in the battery box, which facilitates subsequent handling of thermal runaway and prevents further spread of thermal runaway. Attached Figure Description

[0024] Figure 1 This is a flowchart of the power battery thermal runaway alarm method based on multi-source information fusion in Embodiment 1 of the present invention;

[0025] Figure 2 This is a schematic diagram of the arrangement of the data acquisition unit in Embodiment 2 of the present invention;

[0026] Figure 3 This is a schematic diagram of data transmission in Embodiment 2 of the present invention;

[0027] Figure 4 This is a flowchart of the operation of each unit in Embodiment 2 of the present invention. Detailed Implementation

[0028] 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 embodiments of the present invention, and not all embodiments. 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.

[0029] It should be noted that when a component is referred to as being "mounted on" another component, it may be directly on the other component or there may be a central component. When a component is considered to be "set on" another component, it may be directly set on the other component or there may be a central component. When a component is considered to be "fixed to" another component, it may be directly fixed to the other component or there may be a central component.

[0030] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the specification of this invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "or / and" as used herein includes any and all combinations of one or more of the associated listed items.

[0031] Example 1

[0032] Please see Figure 1 , Figure 1 This is a flowchart of the power battery thermal runaway alarm method based on multi-source information fusion in this invention. As is known, the power batteries of new energy vehicles are installed in a battery box; therefore, this power battery thermal runaway alarm method is used to trigger thermal runaway alarms for N power batteries installed in the battery box of a new energy vehicle.

[0033] The alarm method for thermal runaway of power batteries includes the following steps:

[0034] Step 1: Obtain the data p of the i-th thermal runaway characteristic parameters at the current time. i ;i∈[1,n], where n represents the type of thermal runaway characteristic parameter, n=4.

[0035] Specifically, the thermal runaway characteristic parameters include the internal temperature of the battery box, the CO concentration inside the battery box, the smoke concentration inside the battery box, and the temperature of the I-th power battery, where I∈[1,N].

[0036] It should be noted that since there are N power batteries inside the battery box, this method involves N tasks processed synchronously and in parallel to achieve simultaneous detection of the N power batteries: that is, simultaneously acquiring the temperature of each of the N power batteries at the current moment, and then combining this temperature with the current internal temperature of the battery box, the CO concentration inside the battery box, and the smoke concentration inside the battery box to form N sets of data. The i-th data set includes data p of the i-th thermal runaway characteristic parameter. i .

[0037] Step two, based on p i The basic probability assignment function m1(p) for not experiencing thermal runaway was calculated respectively. i The basic probability assignment function for thermal runaway is m2(p). i ).

[0038] Specifically, based on p i Obtain the corresponding threshold interval A for no thermal runaway and the threshold interval B for thermal runaway, and calculate p respectively. i Euclidean distance Q(p) from A i A) p i Euclidean distance Q(p) from B i B).

[0039] Taking A as an example, A = [a - a + ], where a - Let a be the left threshold of the interval A. + Let be the right threshold of the interval A. Therefore,

[0040] Where Q(p) i A) The smaller the value, the greater the probability that thermal runaway has not occurred; conversely, the greater the probability that thermal runaway has occurred. In this way, the Euclidean distance objectively reflects the probability of real-time data being in each stage.

[0041] And Q(p) i Similarly, B) will not be elaborated further.

[0042] It should be noted that the threshold interval A for no thermal runaway and the threshold interval B for thermal runaway were both obtained experimentally beforehand, and a corresponding relationship table has been constructed here. Therefore, the measured p... i A and B can then be found.

[0043] Based on Q(p) i A), calculate the basic probability assignment function m1(p) for each thermal runaway characteristic parameter at the current moment to determine if thermal runaway has not occurred. i );in,

[0044] Based on Q(p) iB), calculate the basic probability assignment function m2(p) for each thermal runaway characteristic parameter at the current moment to determine the occurrence of thermal runaway. i );in,

[0045] Step 3, for m1(p) i m2(p) i Performing the same processing, we obtain the weighted basic probability assignment function m1′(p) for the absence of thermal runaway. i The weighted basic probability assignment function for thermal runaway is m2′(p i ), to eliminate p i Uncertainty.

[0046] In general, the methods for handling this include:

[0047] First, calculate the information entropy and variance of the basic probability assignment function; then, construct the fuzzy preference matrix based on the information entropy and variance; next, calculate the consistency matrix based on the fuzzy preference matrix; then, calculate the consistency ranking value and use it as the confidence level; then, normalize the confidence level and use it as a weighting factor; finally, perform a weighted average of the weighting factor and the basic probability assignment function to obtain the weighted basic probability assignment function.

[0048] (1) For m1(p i Specifically:

[0049] Calculate m1(p) i Information Entropy IV i and its variance Iσ i ;

[0050] in, Iσ i =Var(IV1,IV2,…,IV) n ).

[0051] Based on IV i 、Iσ i Construct the fuzzy preference matrix E;

[0052] in,

[0053] e ij This represents the element in row i and column j of E. In other words, the elements in E satisfy:

[0054] Calculate its consistency matrix based on E.

[0055] in,

[0056] express The element in the i-th row and j-th column.

[0057] Calculate the consistency ranking value R i And used as confidence level Cred i ;

[0058] in,

[0059] For Cred i Normalization is performed and used as a weighting factor w i ;

[0060] in,

[0061] w i With m1(p i We perform a weighted average to obtain the weighted basic probability assignment function m1′(p i );

[0062] in,

[0063] (2) Calculate m2(p) i Information Entropy IV i ′ and its variance Iσ′ i ;

[0064] in, Iσ′ i =Var(IV1′,IV′2,…,IV′ n ).

[0065] Based on IV i ′、Iσ′ i Construct the fuzzy preference matrix E′;

[0066] in,

[0067] e′ ij This represents the element in row i and column j of E′. In other words, the elements in E′ satisfy:

[0068] Calculate its consistency matrix based on E′.

[0069] in

[0070] express The element in the i-th row and j-th column.

[0071] Calculate the consistency ranking value R′i and used as the confidence Cred′ i ;

[0072] Among them,

[0073] normalize Cred′ i and use it as the weight factor w′ i ;

[0074] Among them,

[0075] weightedly average w′ i with m2(p i ) to obtain the weighted basic probability assignment function m2′(p i );

[0076] Among them,

[0077] After the above processing, after the basic probability assignment function is corrected by evidence weighting, the uncertainty existing in the thermal runaway environment is eliminated.

[0078] Step 3, based on m1′(p i ) and m2′(p i ), calculate the fusion result according to the DS evidence theory combination rule respectively.

[0079] It should be noted that according to the above, the state of the power battery is divided into the state of not having a thermal runaway and the state of having a thermal runaway. Therefore, the purpose of Step 3 is to determine which state the power battery belongs to and accordingly determine whether to issue an alarm.

[0080] Calculate the probability M(u1) of not having a thermal runaway according to the DS evidence theory combination rule for m1′(p i ); among them,

[0081] Calculate the probability M(u2) of having a thermal runaway according to the DS evidence theory combination rule for m2′(p i ); among them,

[0082] Compare M(u1) and M(u2) to obtain the fusion result;

[0083] Among them, if M(u1) > M(u2), it means that the I-th power battery has not had a thermal runaway;

[0084] If M(u1) < M(u2), it means that the I-th power battery has had a thermal runaway.

[0085] Of course, M(u1) + M(u2) is not necessarily equal to 1; there is still a probability of being in an uncertain state. therefore, Before comparing M(u1) and M(u2), we must first ensure that The value should not be too large, thus ensuring the accuracy of the judgment.

[0086] In summary, if the fusion result shows that at least one of the N power batteries has experienced thermal runaway, an alarm will be triggered. Otherwise, no alarm will be triggered.

[0087] In addition, while triggering the alarm, nitrogen gas is injected into the battery compartment. Nitrogen is used to prevent further spread of thermal runaway.

[0088] Of course, since the fusion results can reflect which one or more power batteries have thermal runaway, the filling port can be moved to the power battery that has thermal runaway when filling with nitrogen, thereby ensuring the immediate control effect of thermal runaway.

[0089] Example 2

[0090] This embodiment 2 discloses a power battery thermal runaway alarm system based on multi-source information fusion, which uses the power battery thermal runaway alarm method based on multi-source information fusion from embodiment 1.

[0091] See Figure 4 The power battery thermal runaway alarm system based on multi-source information fusion includes: a data acquisition unit, a basic probability assignment function calculation unit, a basic probability assignment function weighting unit, an evidence fusion unit, and an alarm unit.

[0092] The data acquisition unit is used to acquire data p of the i-th thermal runaway characteristic parameters at the current time. i ; i∈[1,n], where n represents the type of thermal runaway characteristic parameter. For details, see [link to documentation]. Figure 2 The data acquisition unit consists of multiple sensors: for power battery monitoring, surface-mount temperature sensors are installed on each of the N power batteries to monitor their temperature. For power battery box monitoring, temperature sensors, smoke sensors, and CO sensors are installed to monitor the temperature, smoke concentration, and CO concentration inside the power battery box.

[0093] The basic probability assignment function calculation unit, the basic probability assignment function weighting unit, and the evidence fusion unit are all essentially data processing components. The basic probability assignment function calculation unit is used to calculate based on p... i The basic probability assignment function m1(p) for not experiencing thermal runaway was calculated respectively. i The basic probability assignment function for thermal runaway is m2(p). i The basic probability assignment function weighting unit is used to assign values ​​to m1(p).i m2(p) i Performing the same processing, we obtain the weighted basic probability assignment function m1′(p) for the absence of thermal runaway. i The weighted basic probability assignment function for thermal runaway is m2′(p i ), to eliminate p i The uncertainty. Evidence fusion units are used based on m1′(p i ), m2′(p i The fusion results were calculated according to the DS evidence theory synthesis rules.

[0094] Specifically, the aforementioned data processing modules are integrated into the MCU. The MCU is a high-performance chip with powerful processing capabilities, and it is programmed using the FreeRTOS system for multi-tasking, adapting to multi-tasking processing. This allows for the simultaneous generation of N fused results to pinpoint the location of thermal runaway within the battery pack. Since data processing is handled by the MCU, edge computing is employed, thus reducing the operational burden on the vehicle controller.

[0095] The alarm unit is used to issue an alarm when at least one of the N power batteries in the fusion result has experienced thermal runaway. Specifically, issuing an alarm involves the MCU packaging the current thermal runaway characteristic parameters and the current thermal runaway state, and sending them to the vehicle controller / user terminal, enabling the driver to monitor the situation promptly and take emergency measures. If no alarm is needed, data acquisition and processing continue.

[0096] Additionally, a thermal runaway suppression module can be installed to simultaneously charge the battery compartment with nitrogen gas while triggering an alarm. Specifically, the thermal runaway suppression module includes a nitrogen generator connected to the battery compartment and an N2 control valve located at the generator's outlet. Upon triggering the alarm, the N2 control valve opens, and the nitrogen generator charges the battery compartment with nitrogen gas.

[0097] It should be noted that, Figure 2 The example only shows the method of directly connecting the nitrogen generator to the battery box. Referring to Example 1, to ensure effectiveness, the outlet of the nitrogen generator can be connected to a flexible metal hose, which extends into the battery box, with the outlet of the metal hose serving as the filling port. A robotic arm with at least two degrees of freedom is installed inside the battery box, enabling movement along the length and width of the battery box. In this way, by controlling the robotic arm to move the flexible metal hose, the filling port can be moved to the power battery where thermal runaway has occurred.

[0098] The data transmission method between the above units is designed according to actual needs. See [link / reference] Figure 3For example, the data acquisition unit, alarm unit, and thermal runaway suppression module are connected to the MCU via CAN bus communication. The MCU is connected to the vehicle controller via CAN bus communication. The MCU communicates with the user terminal (e.g., the driver's mobile phone terminal) via GPRS remote communication.

[0099] In summary, the workflow of each of the above units can be found in [link to documentation]. Figure 4 .

[0100] Example 3

[0101] This embodiment 3 discloses a readable storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the power battery thermal runaway alarm method based on multi-source information fusion in embodiment 1 is executed.

[0102] When applying the method of Example 1, it can be applied in the form of software, such as by designing it as a program that can run independently on a computer-readable storage medium. The computer-readable storage medium can be a USB flash drive, designed as a USB security token, and the program can be designed to start the entire method through an external trigger.

[0103] Example 4

[0104] This embodiment 4 verifies the method of embodiment 1. Taking a single battery as an example, its state at four different times is measured: 1, 2, and 3, where thermal runaway did not actually occur; and 4, where thermal runaway actually occurred. See Table 1 for specific data.

[0105] Table 1. Data on measured thermal runaway characteristic parameters

[0106]

[0107] The data in Table 1 were processed according to the method in Example 1 to obtain M(u1) and M(u2). As shown in Table 2.

[0108] Table 2 Fusion Results

[0109]

[0110] As shown in Table 2, the four groups The values ​​are all small: in sequence 1, Although it exceeds 0.2, it is still significantly smaller than M(u1); in sequences 2 and 3, All are less than 0.1; in sequence 4, It is slightly greater than 0.1 and significantly less than M(u2). The above data meets the requirements for making a judgment.

[0111] Among the first three groups, M(u1) > M(u2), indicating that thermal runaway has not occurred, which is consistent with the actual situation. In the fourth group, M(u1) < M(u2), indicating that thermal runaway has occurred, which is consistent with the actual situation. That is, the effectiveness and accuracy of this method are verified.

[0112] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0113] The above-described embodiments only express several implementation manners of the present invention. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the invention patent shall be subject to the appended claims.

Claims

1. A method for thermal runaway alarm of power batteries based on multi-source information fusion, which is used to alarm the thermal runaway of batteries installed in the battery box of new energy vehicles. N Each power battery is equipped with a thermal runaway alarm; its features include: The method for alarming thermal runaway of power batteries includes the following steps: Step 1, obtain the current time of the first step. i Data on thermal runaway characteristic parameters p i ; i ∈[1, n ], n Indicates the types of characteristic parameters of thermal runaway. n =4; The thermal runaway characteristic parameters include the internal temperature of the battery box, the CO concentration inside the battery box, the smoke concentration inside the battery box, and the first I The temperature of the power battery I ∈[1, N ]; In step one, the current time is obtained synchronously. N The temperature of each power battery is then compared with the current internal temperature of the battery pack, the CO concentration inside the battery pack, and the smoke concentration inside the battery pack to form a composite data set. N Group of data; where, the first i The data group includes the first i Data on thermal runaway characteristic parameters p i ; Step two, based on p i The basic probability assignment functions for not experiencing thermal runaway were calculated respectively. m 1 ( p i ), Basic probability assignment function for thermal runaway m 2 ( p i ); Step 3, for m 1 ( p i ), m 2 ( p i Perform the same processing to obtain the weighted basic probability assignment function for preventing thermal runaway. The weighted basic probability assignment function for thermal runaway To eliminate p i Uncertainty; among which, the methods for handling it include: First, calculate the information entropy and its variance of the basic probability assignment function; then construct a fuzzy preference matrix based on the information entropy and its variance; next, calculate its consistency matrix based on the fuzzy preference matrix; then calculate the sorting value of consistency and use it as the confidence level; then normalize the confidence level and use it as the weight factor; finally, perform weighted averaging on the weight factor and the basic probability assignment function to obtain the weighted basic probability assignment function. Step 4, based on , The fusion results were calculated according to the DS evidence theory synthesis rules; where, if the fusion result is N An alarm will be triggered if at least one of the power batteries experiences thermal runaway.

2. The method for alarming thermal runaway of a power battery based on multi-source information fusion according to claim 1, characterized in that, Step two includes: in accordance with p i Obtain the corresponding threshold range in which thermal runaway has not occurred. A Threshold range for thermal runaway B and calculate respectively p i and A European distance Q ( p i , A ), p i and B European distance Q ( p i , B ); based on Q ( p i , A ), calculate the basic probability assignment function for each thermal runaway characteristic parameter at the current moment that thermal runaway has not occurred. m 1 ( p i );in, ; based on Q ( p i , B ), calculate the basic probability assignment function for thermal runaway at the current moment for each thermal runaway characteristic parameter. m 2 ( p i );in, .

3. The method for alarming thermal runaway of a power battery based on multi-source information fusion according to claim 2, characterized in that, Step three includes: Calculated information entropy IV i and its variance m 1 ( p i ) Iσ i ; in, , ; based on IV i , Iσ i Construct the fuzzy preference matrix E; in, , e ij This represents the element in row i and column j of E. ; Calculate its consistency matrix based on E. ; in, ; express The element in the i-th row and j-th column; Calculate the consistency ranking value R i And used as confidence level Cred i ; in, ; right Cred i Normalization was performed and used as a weighting factor. w i ; in, ; Will w i and m 1 ( p i Perform a weighted average to obtain the weighted basic probability assignment function. ; in, .

4. The method for alarming thermal runaway of a power battery based on multi-source information fusion according to claim 3, characterized in that, Step three further includes: calculate m 2 ( p i Information entropy and its variance ; in, , ; based on , Constructing a fuzzy preference matrix ; in, , express The element in the i-th row and j-th column, ; based on Calculate its consistency matrix ; in, ; express The element in the i-th row and j-th column; Calculate the consistency ranking value And used as confidence level ; in, ; right Normalization was performed and used as a weighting factor. ; in, ; Will and m 2 ( p i Perform a weighted average to obtain the weighted basic probability assignment function. ; in, .

5. The method for alarming thermal runaway of a power battery based on multi-source information fusion according to claim 4, characterized in that, Step four includes: Will The probability M(u1) of not experiencing thermal runaway is calculated according to the synthesis rules of the DS evidence theory; where, ； Will The probability M(u2) of thermal runaway is calculated according to the synthesis rules of the DS evidence theory; where, ； Compare M(u1) and M(u2) to obtain the fusion result. Among them, if M(u1) > M(u2), it indicates that the I-th power battery has not experienced thermal runaway. If M(u1) < M(u2), it indicates that the I-th power battery has experienced thermal runaway.

6. The method for alarming thermal runaway of a power battery based on multi-source information fusion according to claim 5, characterized in that, Step four further includes: Calculate the probability of being in an uncertain state based on M(u1) and M(u2). ; in, .

7. The method for alarming thermal runaway of a power battery based on multi-source information fusion according to claim 6, characterized in that, Step four further includes: While alarming, inject nitrogen into the battery box.

8. A power battery thermal runaway alarm system based on multi-source information fusion, characterized in that, It uses the method for alarming thermal runaway of power batteries based on multi-source information fusion as described in any one of claims 1-4. The power battery thermal runaway alarming system includes: The data acquisition unit is used to obtain the data at the current time. i Data on thermal runaway characteristic parameters p i ; i ∈[1, n ], n Indicates the types of characteristic parameters of thermal runaway; The basic probability assignment function calculation unit is used to calculate based on... p i The basic probability assignment functions for not experiencing thermal runaway were calculated respectively. m 1 ( p i ), Basic probability assignment function for thermal runaway m 2 ( p i ); The basic probability assignment function weighting unit is used to assign values ​​to the basic probability assignment function weighting unit. m 1 ( p i ), m 2 ( p i Perform the same processing to obtain the weighted basic probability assignment function for preventing thermal runaway. The weighted basic probability assignment function for thermal runaway To eliminate p i Uncertainty; Evidence fusion unit, which is used for evidence fusion based on , The fusion results were calculated according to the DS evidence theory synthesis rules, respectively; and An alarm unit is used when the fusion result is... N An alarm will be triggered if at least one of the power batteries experiences thermal runaway.

9. The power battery thermal runaway alarm system based on multi-source information fusion according to claim 8, characterized in that, The power battery thermal runaway alarming system further includes: A thermal runaway suppression module, which is used to inject nitrogen into the battery box while alarming.

Images