A stress and temperature-based battery thermal runaway early warning method and system

Abstract

The application discloses a battery thermal runaway early warning method and system based on stress and temperature, comprising: acquiring the temperature and stress data of each single battery in the battery system in real time, and establishing a time sequence with a set length; performing mean value processing and normalization processing on the temperature and stress data in the time sequence respectively, then decoupling and classifying the time sequence characteristics of the temperature and stress data by using a DBSCAN algorithm to obtain clustering results; calculating the clustering centers according to the clustering results, taking the clustering set with the most members as a reference object, and calculating the Euclidean distance of the reference object and other clustering centers; establishing corresponding time sequence data according to the calculated Euclidean distance of the clustering centers, calculating the change rate of the time sequence data based on the Euclidean distance of the clustering centers by using a least square method, and judging whether thermal runaway early warning is needed according to the change rate of the time sequence data. The method reduces the noise and abnormal value interference of traditional real-time data, and timely and accurately performs early warning on the battery thermal runaway.

Description

Technical Field

[0001] This invention belongs to the field of battery management technology, specifically relating to a battery thermal runaway early warning method based on stress and temperature. Background Technology

[0002] Lithium-ion batteries possess advantages such as high energy density and long cycle life, making them widely used in electric vehicles and energy storage. However, during repeated charging and discharging processes, reversible lithium intercalation expansion and irreversible expansion due to overcharging and over-discharging can occur, manifesting as stress. This stress threatens the battery's health and safety, hindering the large-scale market application of lithium-ion batteries. Therefore, stress- and temperature-based early warning methods for battery thermal runaway are particularly important.

[0003] CN112485678A discloses a method for real-time status monitoring and thermal runaway alarm of lithium batteries. By detecting lithium battery surface temperature data, deformation data, CO concentration data and VOC concentration data when lithium battery leakage occurs, it accurately reflects the three typical stages of thermal runaway: over-temperature, over-pressure and gas leakage, and monitors the real-time status of lithium batteries.

[0004] CN112067155A discloses a method for dynamic temperature monitoring of lithium batteries based on OFDR. The method involves arranging sensing optical fibers horizontally and vertically along the surface of the lithium battery to form a distributed sensing optical fiber network. The Rayleigh scattering signal in the optical fiber is collected by OFDR technology, and after demodulation, the real-time temperature change at each position on the optical fiber is obtained, forming a two-dimensional temperature distribution map of the lithium battery surface to intuitively display the surface temperature and realize real-time temperature monitoring.

[0005] The aforementioned existing technologies do not provide a solution for how to use temperature and stress data to perform decoupled analysis over time to achieve early warning of battery thermal runaway. Summary of the Invention

[0006] The technical problem to be solved by this invention is: how to decouple and analyze temperature and stress data in the time dimension based on data collected by the battery management system, so as to realize data anomaly detection and early warning of battery thermal runaway.

[0007] To address the aforementioned technical problems, this invention provides a battery thermal runaway early warning method based on stress and temperature, comprising the following steps:

[0008] Step S1: Real-time acquisition of temperature and stress data of each individual cell in the battery system, and establishment of a time series of a set length;

[0009] Step S2: The temperature and stress data in the time series are processed by mean and normalization respectively. Then, the DBSCAN algorithm is used to decouple and classify the time series features of temperature and stress data to obtain clustering results.

[0010] Step S3: Calculate the cluster centers based on the clustering results in Step S2, take the cluster with the most members as the reference object, and calculate the Euclidean distance between the reference object and other cluster centers.

[0011] Step S4: Establish corresponding time-series data based on the Euclidean distance of the cluster centers calculated in Step S3, and calculate the rate of change of the time-series data based on the Euclidean distance of the cluster centers using the least squares method. Based on the rate of change of time series data To determine whether a thermal runaway warning is needed, if the rate of change... If the value exceeds the threshold, a thermal runaway warning will be issued.

[0012] In the aforementioned battery thermal runaway early warning method based on stress and temperature, step S2 involves averaging the temperature and stress data over a time series, as shown in equations (1) and (2). The length of the time series. Represents the first time series. Temperature value at time, This represents the average temperature over the time series. Represents the first time series. Stress value at time 10:00 This represents the average stress over the time series.

[0013] (1)

[0014] (2)

[0015] In the aforementioned battery thermal runaway early warning method based on stress and temperature, step S2 involves data normalization calculation formulas as shown in equations (3) and (4):

[0016] (3)

[0017] (4)

[0018] in, Indicates the first The average temperature of the battery cell over this time series. This represents the maximum value among all battery temperature averages. This represents the minimum value among all battery temperature averages. Indicates the first The normalized average temperature of the battery; Indicates the first The average stress of the battery over this time series. This represents the maximum value among all average battery stress values. This represents the minimum value among all average battery stress values. Indicates the first The normalized average stress of the battery.

[0019] The aforementioned battery thermal runaway early warning method based on stress and temperature, in step S2, includes the following steps during the battery clustering analysis using the DBSCAN algorithm:

[0020] 21) Set the scan radius to eps;

[0021] 22) Select based on the mean of temperature time series and stress time series mean As a clustering factor; the Euclidean distance is calculated based on the characteristic data of each individual cell, where the first... Battery and the first Battery-saving European distance The calculation formula is shown in equation (5). The representative feature dimension, 0-1 corresponds to the normalized average temperature and average stress;

[0022] d ij = ∑ k = 0 1 ( X i [ k ] − X j [ k ]) 2 (5);

[0023] X i [ k ] Indicates the first Features of each dataset X i [ 0 ] Indicates the first The normalized average temperature of the battery. X i [ 1 ] Indicates the first The normalized average stress of the battery. X j [ 0 ] Indicates the first The normalized average temperature of the battery. X j [ 1 ] Indicates the first The normalized average stress of the battery;

[0024] 23) If the Euclidean distance is less than the scanning radius eps, then the corresponding individual cells are included in the same set;

[0025] 23) Determine whether the Euclidean distance between any member within the set and any member outside the set is less than the scanning radius eps. If so, include the corresponding member outside the set into the same set. The member is the normalized average stress and average temperature of a single cell.

[0026] 24) Repeat steps 21)-23) until all batteries are sorted.

[0027] In the aforementioned battery thermal runaway early warning method based on stress and temperature, the cluster center calculation formula in step S3 is shown in equation (6), that is, the feature of each dimension is taken as the average value of all members in the set.

[0028] (6)

[0029] in Represents the cluster center of set A. , These represent the temperature and pressure coordinates of the cluster center of set A, respectively; {} denote the coordinates;

[0030] The formula for calculating the Euclidean distance between cluster centers is shown in equation (7):

[0031] d AB = ∑ k = 0 1 ( X A [ k ] − X B [ k ]) 2 (7)

[0032] in The Euclidean distance represents the cluster centers of set A and set B.

[0033] In the aforementioned method for early warning of battery thermal runaway based on stress and temperature, in step S4, the Euclidean distance time series data between each cluster center is shown in equation (8). For cluster centers A and B, we have...

[0034] (8)

[0035] Based on the Euclidean distance time series data of each cluster center, the rate of change of the time series data was calculated using the least squares method. As shown in equation (9),

[0036] (9)

[0037] for The Euclidean distance between the cluster centers of set A and the cluster centers of set B at time t. This refers to the duration of the time.

[0038] In the aforementioned battery thermal runaway early warning method based on stress and temperature, the threshold C is set according to a selected time interval unit.

[0039] A computer device / apparatus / system includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above-described method.

[0040] A computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0041] A computer program product includes a computer program / instructions that, when executed by a processor, implement the steps of the above-described method.

[0042] The beneficial effects achieved by this invention are as follows: The method of this invention obtains battery state characteristics by decoupling the analysis of temperature and stress data in the time dimension, which reduces the noise and outlier interference of traditional real-time data, and provides timely and accurate early warning of battery thermal runaway. At the same time, it calculates the distance between cluster centers through DBSCAN clustering analysis, establishes time-series data of cluster center distance, and uses the least squares method to judge the rate of change, which reduces the false triggering of warnings by traditional threshold warning strategies and also solves the problem that the threshold needs to be adjusted in different scenarios in traditional methods. Attached Figure Description

[0043] Figure 1 Flowchart of the DBSCAN clustering algorithm in Embodiment 1 of this invention;

[0044] Figure 2 This is a flowchart of the battery thermal runaway early warning method based on temperature and stress in Embodiment 1 of the present invention. Detailed Implementation

[0045] The method of the present invention will now be described in further detail with reference to the accompanying drawings.

[0046] Example 1

[0047] This embodiment provides a battery thermal runaway early warning method based on stress and temperature, including the following steps:

[0048] Step S1: Real-time acquisition of temperature and stress data of each individual cell in the battery system, and establishment of a time series of a set length;

[0049] Step S2: The temperature and stress data in the time series are processed by mean and normalization respectively. Then, the DBSCAN algorithm is used to decouple and classify the time series features of temperature and stress data to obtain clustering results.

[0050] In step S2, the temperature and stress data within the time series are averaged, and the calculation formulas are shown in equations (1) and (2), where The length of the time series. Represents the first time series. Temperature value at time, This represents the average temperature over the time series. Represents the first time series. Stress value at time 10:00 This represents the average stress over the time series.

[0051] (1)

[0052] (2)

[0053] In step S2, the calculation formulas for normalizing the data are shown in equations (3) and (4):

[0054] (3)

[0055] (4)

[0056] in, Indicates the first The average temperature of the battery cell over this time series. This represents the maximum value among all battery temperature averages. This represents the minimum value among all battery temperature averages. Indicates the first The normalized average temperature of the battery; Indicates the first The average stress of the battery over this time series. This represents the maximum value among all average battery stress values. This represents the minimum value among all average battery stress values. Indicates the first The normalized average stress of the battery.

[0057] In step S2, as shown in Figure 1, the process of clustering the batteries using the DBSCAN algorithm includes the following steps:

[0058] 21) Set the scan radius to eps, which is 0.5, and the minimum number of points to minPts, which can be 1;

[0059] 22) Calculate the Euclidean distance based on the characteristic data of each individual cell, where the first... Battery and the first Battery-saving European distance The calculation formula is shown in equation (5). The representative feature dimension, 0-1 corresponds to the normalized average temperature and average stress;

[0060] d ij = ∑ k = 0 1 ( X i [ k ] − X j [ k ]) 2 (5);

[0061] X i [ k ] Indicates the first Features of each dataset X i [ 0 ] Indicates the first The normalized average temperature of the battery. X i [ 1 ] Indicates the first The normalized average stress of the battery. X j [ 0 ] Indicates the first The normalized average temperature of the battery. X j [ 1 ] Indicates the first The normalized average stress of the battery.

[0062] 23) If the Euclidean distance is less than the scanning radius eps, then the corresponding individual cells are included in the same set;

[0063] 23) Determine whether the Euclidean distance between any member within the set and any member outside the set is less than the scanning radius eps. If so, include the corresponding member outside the set into the same set. The member is the normalized average stress and average temperature of a single cell.

[0064] 24) Until all batteries are sorted.

[0065] In step S2, during the cluster analysis of battery temperature and stress data using the DBSCAN algorithm, the average value based on the temperature time series is selected. and stress time series mean The clustering results obtained using these factors are shown in Table 3. The parameters extracted in this embodiment are shown in Table 1.

[0066] Table 1. Mean values ​​of battery time series before normalization

[0067]

[0068] The parameters after normalization are shown in Table 2.

[0069] Table 2. Normalized mean of battery time series

[0070]

[0071] The battery data clustering results are shown in Table 3.

[0072] Table 3. Clustering results of battery data

[0073]

[0074] Step S3: Calculate cluster centers based on the clustering results in step S2, take the cluster with the most members as the reference object, and calculate the Euclidean distance between the reference object and other cluster centers.

[0075] The formula for calculating cluster centers is shown in equation (6), where each dimension of the feature is taken as the average value of all members in the set, where The cluster centers of set A are shown in Table 4.

[0076] (6)

[0077] , These represent the temperature and pressure coordinates of the cluster center of set A, respectively; {} denote the coordinates;

[0078] Table 4 Cluster center coordinates

[0079]

[0080] The formula for calculating the Euclidean distance between cluster centers is shown in equation (7), where The Euclidean distance between the cluster centers of set A and set B is shown in Table 5. Since cluster A has the most members, the Euclidean distance between other clusters is calculated with cluster A as the reference.

[0081] d AB = ∑ k = 0 1 ( X A [ k ] − X B [ k ]) 2 (7)

[0082] Table 5. Distance between cluster centers

[0083]

[0084] Step S4: Establish corresponding time-series data based on the Euclidean distance of the cluster centers calculated in Step S3, and calculate the rate of change of the time-series data based on the Euclidean distance of the cluster centers using the least squares method. Based on the rate of change of time series data To determine whether a thermal runaway warning is needed, if the rate of change... If the value exceeds the threshold, a thermal runaway warning will be issued.

[0085] In step S4, the time series data of the Euclidean distance between each cluster center is shown in equation (8), with... For example, there are

[0086] (8)

[0087] Table 6. Time series data on distances between cluster centers

[0088]

[0089] Based on the Euclidean distance time series data of each cluster center, the rate of change of the time series data was calculated using the least squares method. As shown in equation (9),

[0090] (9)

[0091] for The Euclidean distance between the cluster centers of set A and the cluster centers of set B at time t. The actual value of the threshold C, representing the time duration, is related to the selected time interval unit. In this embodiment, the time interval is in seconds, and the threshold C is 0.01. Take 5. =0.01, =0.001, Since the value is greater than or equal to C, it is necessary to provide fault warnings for the batteries in set B.

[0092] Example 2

[0093] A computer device / apparatus / system includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above-described method.

[0094] Example 3

[0095] A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that the computer program / instructions, when executed by a processor, implement the steps of the above-described method.

[0096] A computer program product includes a computer program / instructions that, when executed by a processor, implement the steps of the above-described method.

[0097] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0098] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0099] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0100] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for early warning of battery thermal runaway based on stress and temperature, characterized in that, Includes the following steps: Step S1: Real-time acquisition of temperature and stress data of each individual cell in the battery system, and establishment of a time series of a set length; Step S2: The temperature and stress data in the time series are processed by mean and normalization respectively. Then, the DBSCAN algorithm is used to decouple and classify the time series features of temperature and stress data to obtain clustering results. Step S3: Calculate the cluster centers based on the clustering results in Step S2, take the cluster with the most members as the reference object, and calculate the Euclidean distance between the reference object and other cluster centers. Step S4: Establish corresponding time-series data based on the Euclidean distance of the cluster centers calculated in Step S3, and calculate the rate of change of the time-series data based on the Euclidean distance of the cluster centers using the least squares method. Based on the rate of change of time series data To determine whether a thermal runaway warning is needed, if the rate of change... If the value exceeds the threshold, a thermal runaway warning will be issued.

2. The battery thermal runaway early warning method based on stress and temperature according to claim 1, characterized in that, In step S2, the temperature and stress data within the time series are averaged, and the calculation formulas are shown in equations (1) and (2). (1)； (2)； in The length of the time series. Represents the first time series. Temperature value at time, This represents the average temperature over the time series. Represents the first time series. Stress value at time 10:00 This represents the average stress over the time series.

3. The battery thermal runaway early warning method based on stress and temperature according to claim 2, characterized in that, In step S2, the calculation formulas for normalizing the data are shown in equations (3) and (4): (3)； (4)； in, Indicates the first The average temperature of the battery cell over this time series. This represents the maximum value among all battery temperature averages. This represents the minimum value among all battery temperature averages. Indicates the first The normalized average temperature of the battery; Indicates the first The average stress of the battery over this time series. This represents the maximum value among all average battery stress values. This represents the minimum value among all average battery stress values. Indicates the first The normalized average stress of the battery.

4. The battery thermal runaway early warning method based on stress and temperature according to claim 3, characterized in that, In step S2, the process of clustering the batteries using the DBSCAN algorithm includes the following steps: 21) Set the scan radius to eps; 22) Select based on the mean of temperature time series and stress time series mean As a clustering factor; the Euclidean distance is calculated based on the characteristic data of each individual cell, where the first... Battery and the first Battery-saving European distance The calculation formula is shown in equation (5). The representative feature dimension, 0-1 corresponds to the normalized average temperature and average stress; (5)； Indicates the first Features of each dataset Indicates the first The normalized average temperature of the battery. Indicates the first The normalized average stress of the battery. Indicates the first The normalized average temperature of the battery. Indicates the first The normalized average stress of the battery; 23) If the Euclidean distance is less than the scanning radius eps, then the corresponding individual cells are included in the same set; 23) Determine whether the Euclidean distance between any member within the set and any member outside the set is less than the scanning radius eps. If so, include the corresponding member outside the set into the same set. The member is the normalized average stress and average temperature of a single cell. 24) Repeat steps 21)-23) until all batteries are sorted.

5. A battery thermal runaway early warning method based on stress and temperature according to claim 4, characterized in that, In step S3, the cluster center calculation formula is shown in equation (6), that is, each dimension feature is taken as the average value of all members in the set. (6)； in Represents the cluster center of set A. , These represent the temperature and pressure coordinates of the cluster center of set A, respectively; {} denote the coordinates; The formula for calculating the Euclidean distance between cluster centers is shown in equation (7): (7) ； in The Euclidean distance represents the cluster centers of set A and set B.

6. The battery thermal runaway early warning method based on stress and temperature according to claim 1, characterized in that, In step S4, the time series data of the Euclidean distance between each cluster center is shown in equation (8). For cluster centers of set A and set B, we have (8)； Based on the Euclidean distance time series data of each cluster center, the rate of change of the time series data was calculated using the least squares method. As shown in equation (9), （9）； for The Euclidean distance between the cluster centers of set A and the cluster centers of set B at time t. This refers to the duration of the time.

7. A battery thermal runaway early warning method based on stress and temperature according to claim 6, characterized in that, The threshold C is set according to the selected time interval unit.

8. A computer system comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method as described in any one of claims 1-7.

9. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method as described in any one of claims 1-7.

10. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method as described in any one of claims 1-7.

Images