Method and device for determining thermal runaway risk index of battery pack and electronic equipment

Abstract

The invention discloses a battery pack thermal runaway risk index determination method and device and electronic equipment. The method comprises the following steps: acquiring operation data corresponding to a target battery pack; determining arrangement parameters respectively corresponding to the plurality of sub-batteries; determining a heat propagation path parameter corresponding to the target battery pack according to the plurality of sub-batteries and the arrangement parameters corresponding to the plurality of sub-batteries; determining heat propagation characteristic parameters respectively corresponding to the plurality of operation time parameters according to the operation data and the heat propagation path parameters; and determining a thermal runaway risk index corresponding to the target battery pack according to the thermal propagation characteristic parameters corresponding to the plurality of operation time parameters. According to the method and the device, the technical problem that the thermal runaway risk index is determined inaccurately when the thermal runaway risk index of the battery pack is determined in related technologies is solved.

Description

Technical Field

[0001] The present invention relates to the field of batteries, and in particular to a method, device and electronic equipment for determining a thermal runaway risk index of a battery pack. Background Art

[0002] Battery pack thermal runaway is a potential safety hazard in scenarios such as electric vehicles and energy storage power stations. The resulting high temperatures, high pressures, and combustion can damage equipment and even threaten personal safety. Therefore, to prevent thermal runaway, it is necessary to determine a battery pack thermal runaway risk index. However, in the prior art, determining the thermal runaway risk index for battery packs often results in inaccurate results.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] Embodiments of the present invention provide a method, device, and electronic device for determining a thermal runaway risk index of a battery pack, to at least address the technical problem in related art of inaccurate determination of the thermal runaway risk index of a battery pack.

[0005] According to one aspect of an embodiment of the present invention, a method for determining a thermal runaway risk index of a battery pack is provided, comprising: obtaining operating data corresponding to a target battery pack, wherein the target battery pack includes a plurality of sub-batteries, and the operating data includes a plurality of operating time parameters; determining arrangement parameters corresponding to the plurality of sub-batteries respectively; determining heat propagation path parameters corresponding to the target battery pack based on the plurality of sub-batteries and the arrangement parameters corresponding to the plurality of sub-batteries respectively; determining heat propagation characteristic parameters corresponding to the plurality of operating time parameters respectively based on the operating data and the heat propagation path parameters; and determining a thermal runaway risk index corresponding to the target battery pack based on the heat propagation characteristic parameters corresponding to the plurality of operating time parameters respectively.

[0006] Optionally, determining the heat propagation characteristic parameters corresponding to the multiple operating time parameters respectively based on the operating data and the heat propagation path parameters includes: when the heat propagation path parameters include a heat propagation path graph, determining the adjacency matrix and degree matrix corresponding to the heat propagation path graph, wherein the heat propagation path graph includes multiple nodes obtained based on multiple sub-batteries, the adjacency matrix is ​​a matrix representing the relationship between the corresponding node and other nodes, and the degree matrix represents the matrix of the number of nodes connected to the corresponding node; determining the spatial feature matrix corresponding to the heat propagation path graph based on the adjacency matrix and the degree matrix, wherein the diagonal elements of the spatial feature matrix are used to represent the node features corresponding to the multiple nodes in the heat propagation path graph, and the non-diagonal elements of the spatial feature matrix are used to represent the adjacency features corresponding to the multiple nodes in the heat propagation path graph; determining the heat propagation characteristic parameters corresponding to the multiple operating time parameters respectively based on the operating data and the spatial feature matrix.

[0007] Optionally, determining the heat propagation characteristic parameters corresponding to the multiple operation time parameters respectively based on the operation data and the spatial characteristic matrix includes: determining the spatial characteristic parameters corresponding to the multiple operation time parameters respectively based on the operation data and the spatial characteristic matrix; determining the time characteristic parameters corresponding to the multiple operation time parameters respectively based on the spatial characteristic parameters corresponding to the multiple operation time parameters; determining the heat propagation characteristic parameters corresponding to the multiple operation time parameters respectively based on the spatial characteristic parameters and time characteristic parameters corresponding to the multiple operation time parameters respectively.

[0008] Optionally, determining the time characteristic parameters corresponding to the multiple running time parameters respectively based on the spatial characteristic parameters corresponding to the multiple running time parameters includes: determining an initial time characteristic parameter corresponding to a heat propagation characteristic sequence, wherein the heat propagation characteristic sequence includes the spatial characteristic parameters corresponding to the multiple running time parameters respectively; determining the first time characteristic parameter corresponding to the first running time parameter according to the time sequence of the multiple running time parameters based on the initial time characteristic parameter and the first spatial characteristic parameter corresponding to the first running time parameter; determining the next time characteristic parameter corresponding to the next running time parameter based on the first time characteristic parameter and the next spatial characteristic parameter corresponding to the next running time parameter, until the multiple running time parameters are processed and the time characteristic parameters corresponding to the multiple running time parameters are obtained.

[0009] Optionally, before determining the adjacency matrix corresponding to the heat propagation path graph, it also includes: when the heat propagation path parameter includes a heat propagation path graph and the arrangement parameter includes an arrangement position relationship, determining the voltage change parameters corresponding to the multiple sub-batteries respectively; determining a plurality of nodes based on the multiple sub-batteries, wherein the multiple nodes correspond one-to-one to the multiple sub-batteries; determining a plurality of edges based on the arrangement position relationships corresponding to the multiple sub-batteries respectively, wherein the multiple edges correspond one-to-one to the multiple arrangement position relationships; determining the edge weights corresponding to the multiple edges based on the voltage change parameters corresponding to the multiple sub-batteries respectively; and determining the heat propagation path graph corresponding to the target battery pack based on the multiple nodes, the multiple edges, and the edge weights corresponding to the multiple edges respectively.

[0010] Optionally, determining the thermal runaway risk index corresponding to the target battery pack based on the thermal propagation characteristic parameters corresponding to the multiple operating time parameters includes: determining the thermal propagation characteristic distribution parameters corresponding to the target battery pack based on the thermal propagation characteristic parameters corresponding to the multiple operating time parameters; determining the thermal propagation fluctuation index and the thermal propagation trend index corresponding to the target battery pack based on the thermal propagation characteristic distribution parameters; and determining the thermal runaway risk index corresponding to the target battery pack based on the thermal propagation fluctuation index and the thermal propagation trend index.

[0011] Optionally, determining the thermal runaway risk index corresponding to the target battery pack based on the thermal propagation characteristic parameters corresponding to the multiple operating time parameters includes: retrieving a target model, wherein the target model is obtained by training an initial model based on sample data, the sample data includes thermal runaway sample data and non-thermal runaway sample data, and the thermal runaway risk index corresponding to the thermal runaway sample data is greater than or equal to a risk threshold; determining the thermal runaway risk index corresponding to the target battery pack based on the thermal propagation characteristic parameters corresponding to the multiple operating time parameters and the target model.

[0012] According to one aspect of an embodiment of the present invention, a device for determining a thermal runaway risk index of a battery pack is provided, comprising: an acquisition module for acquiring operating data corresponding to a target battery pack, wherein the target battery pack includes a plurality of sub-batteries, and the operating data includes a plurality of operating time parameters; a first determination module for determining arrangement parameters respectively corresponding to the plurality of sub-batteries; a second determination module for determining heat propagation path parameters corresponding to the target battery pack based on the plurality of sub-batteries and the arrangement parameters respectively corresponding to the plurality of sub-batteries; a third determination module for determining heat propagation characteristic parameters respectively corresponding to the plurality of operating time parameters based on the operating data and the heat propagation path parameters; and a fourth determination module for determining a thermal runaway risk index corresponding to the target battery pack based on the heat propagation characteristic parameters respectively corresponding to the plurality of operating time parameters.

[0013] According to one aspect of an embodiment of the present invention, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement any of the above methods for determining a thermal runaway risk index of a battery pack.

[0014] According to one aspect of an embodiment of the present invention, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute any of the above-mentioned methods for determining a thermal runaway risk index of a battery pack.

[0015] In an embodiment of the present invention, operating data corresponding to a target battery pack is obtained, wherein the target battery pack includes multiple sub-batteries and the operating data includes multiple operating time parameters; arrangement parameters corresponding to each of the multiple sub-batteries are determined; heat propagation path parameters corresponding to the target battery pack are determined based on the multiple sub-batteries and the arrangement parameters corresponding to the multiple sub-batteries; heat propagation characteristic parameters corresponding to each of the multiple operating time parameters are determined based on the operating data and the heat propagation path parameters; and a thermal runaway risk index corresponding to the target battery pack is determined based on the heat propagation characteristic parameters corresponding to the multiple operating time parameters. By analyzing the arrangement parameters corresponding to each of the multiple sub-batteries in the target battery pack, the heat propagation within the battery pack can be quantitatively reflected to accurately determine the heat propagation path parameters of the target battery pack. By combining the operating data and the heat propagation path parameters of the target battery pack, the heat propagation characteristic parameters within the target battery pack at different time points can be determined to accurately determine the thermal runaway risk index corresponding to the target battery pack. This solves the technical problem of inaccurate determination of the thermal runaway risk index for a battery pack in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0017] Figure 1 is a flow chart of a method for determining a thermal runaway risk index of a battery pack according to an embodiment of the present invention;

[0018] Figure 2 This is a flowchart of a lithium battery pack thermal runaway propagation warning in an optional embodiment of the present invention;

[0019] Figure 3 is a diagram of a variational autoencoder network structure in an optional embodiment of the present invention;

[0020] Figure 4 4 is a structural block diagram of a device for determining a thermal runaway risk index of a battery pack according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] First, some nouns or terms that appear in the description of the embodiments of the present application are subject to the following interpretations:

[0024] ST-GCN: ST-GCN (Spatiotemporal Graph Convolutional Network) is a network architecture in the field of deep learning that combines the ideas of graph convolutional networks (GCN) and convolutional neural networks (CNN) for processing graph data.

[0025] Graph Convolutional Network: Graph Convolutional Network is a deep learning model for processing graph structured data.

[0026] LSTM: LSTM (Long Short-Term Memory) is a variant of Recurrent Neural Network (RNN) that is used to handle long-term dependencies in sequential data.

[0027] VAE: VAE (Variational Autoencoder) is a generative model used to learn the latent representation and probability distribution of data.

[0028] GRU model: The GRU (Gated Recurrent Unit) model is a simplified version of the LSTM and is also used to process sequence data.

[0029] Adam optimizer: Adam is an optimization algorithm with adaptive learning rate for training deep learning models.

[0030] Example 1

[0031] According to an embodiment of the present invention, an embodiment of a method for determining a thermal runaway risk index of a battery pack is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0032] Figure 1 FIG. 1 is a flow chart of a method for determining a thermal runaway risk index of a battery pack according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0033] S102, acquiring operating data corresponding to a target battery pack, wherein the target battery pack includes a plurality of sub-batteries, and the operating data includes a plurality of operating time parameters;

[0034] In step S102 provided in the present application, operation data corresponding to the target battery pack is acquired.

[0035] The target battery pack is used to determine the thermal runaway risk index, and includes battery packs for electric vehicles and energy storage devices.

[0036] This involves operating data, which reflects the operating status and performance of the target battery pack. For example, this operating data includes sub-battery voltage, total battery pack voltage, current during charge and discharge, temperature data, mileage, insulation resistance, etc.

[0037] This involves multiple sub-cells, which are the basic units that make up the target battery pack. In the target battery pack, multiple sub-cells are connected together in a predetermined series, parallel, or series-parallel combination to work together to meet higher power and energy requirements. Each sub-cell has its own independent operating parameters and status.

[0038] Therein, multiple operating time parameters are involved, which are time-related parameters of the target battery pack during operation. For example, the multiple operating time parameters may be specific timestamps during the operation of the battery pack.

[0039] The operating data can reflect the operating status of the target battery pack, and the operating data includes multiple operating time parameters, which can help to subsequently analyze the operating characteristics of the battery pack under different time parameters and provide a data basis for the subsequent determination of the thermal runaway risk index of the target battery pack.

[0040] S104, determining arrangement parameters corresponding to the plurality of sub-batteries;

[0041] In step S104 provided in the present application, arrangement parameters corresponding to the plurality of sub-cells are determined.

[0042] Among them, arrangement parameters are involved, which describe the layout and connection method of sub-cells within the battery pack. For example, these arrangement parameters include the relative spatial position of sub-cells, electrical connections (such as series, parallel, or mixed connections), contact area between sub-cells, insulation material properties, heat sink layout, cooling channel design, etc.

[0043] The arrangement parameters directly affect the thermal conduction relationship and electrical interaction between sub-batteries. By determining the arrangement parameters corresponding to multiple sub-batteries, it helps to subsequently analyze the heat propagation characteristics between the sub-batteries (such as the accumulation and diffusion of heat energy within the battery pack), thereby improving the accuracy and reliability of determining the thermal runaway risk index of the target battery pack.

[0044] S106, determining a heat transfer path parameter corresponding to the target battery pack based on the plurality of sub-batteries and the arrangement parameters corresponding to the plurality of sub-batteries;

[0045] In step S106 provided in the present application, heat transfer path parameters corresponding to the target battery group are determined based on the plurality of sub-batteries and the arrangement parameters corresponding to the plurality of sub-batteries.

[0046] This involves heat propagation path parameters, which describe the path along which heat propagates from one sub-cell to another within the target battery pack. These parameters include a heat propagation path diagram. These parameters can be used to quantitatively describe the temperature distribution within the battery pack, temperature gradients, and the path and speed of heat energy propagation.

[0047] By integrating multiple sub-cells and the arrangement parameters of each sub-cell, it is possible to accurately identify which sub-cells have direct or indirect heat conduction paths, and then understand how heat energy flows in the battery pack, so as to accurately determine the heat propagation path parameters of the target battery pack.

[0048] S108, determining heat propagation characteristic parameters corresponding to the plurality of operation time parameters respectively based on the operation data and the heat propagation path parameters;

[0049] In step S108 provided in the present application, heat propagation characteristic parameters corresponding to the plurality of operation time parameters are determined according to the operation data and the heat propagation path parameters.

[0050] Among them, the heat propagation characteristic parameters are involved. The heat propagation characteristic parameters are parameters that reflect the heat energy propagation characteristics inside the battery pack. The heat propagation characteristic parameters can reveal the heat energy distribution state, temperature gradient (temperature difference between different sub-batteries inside the battery pack), propagation speed, heat energy accumulation trend, heat propagation mode (such as linear propagation, diffusion propagation or circulation propagation, etc.) inside the battery pack at different time points.

[0051] The operating data includes key physical quantities during the operation of the target battery pack, such as voltage, current, temperature, etc. These are basic indicators of heat energy transfer, while the heat transfer path parameters are determined based on the target battery pack structure (the arrangement and connection method of multiple sub-batteries). They can clearly define the path and method of heat energy transfer. By combining these two types of information, the heat transfer characteristic parameters of the target battery pack under each operating time parameter can be accurately determined.

[0052] S110 , determining a thermal runaway risk index corresponding to a target battery pack based on heat propagation characteristic parameters corresponding to a plurality of operating time parameters.

[0053] In step S110 provided in the present application, a thermal runaway risk index corresponding to the target battery pack is determined based on the heat propagation characteristic parameters corresponding to the plurality of operating time parameters.

[0054] Among them, a thermal runaway risk index is involved. This thermal runaway risk index is used to assess the probability and severity of thermal runaway in a target battery pack at different runtime parameters. The thermal runaway risk index can include a risk value, thermal runaway probability, and risk level. For the risk value, a higher value indicates a greater risk of thermal runaway in the target battery pack at the corresponding runtime parameter.

[0055] The heat propagation characteristic parameters can quantitatively describe the temperature distribution, temperature gradient changes, heat energy propagation path and speed inside the target battery pack. Based on the heat propagation characteristic parameters under each time parameter, it is possible to dynamically analyze the heat propagation characteristics of the target battery pack that change with time in the time dimension. Therefore, based on the heat propagation characteristic parameters corresponding to multiple operating time parameters, the thermal runaway risk index corresponding to the target battery pack can be accurately determined.

[0056] Through the above steps S102-S110, operating data corresponding to a target battery pack is obtained, wherein the target battery pack includes multiple sub-batteries, and the operating data includes multiple operating time parameters; arrangement parameters corresponding to each of the multiple sub-batteries are determined; heat propagation path parameters corresponding to the target battery pack are determined based on the multiple sub-batteries and the arrangement parameters corresponding to each of the multiple sub-batteries; heat propagation characteristic parameters corresponding to each of the multiple operating time parameters are determined based on the operating data and the heat propagation path parameters; and a thermal runaway risk index corresponding to the target battery pack is determined based on the heat propagation characteristic parameters corresponding to each of the multiple operating time parameters. By analyzing the arrangement parameters corresponding to each of the multiple sub-batteries in the target battery pack, the heat propagation within the battery pack can be quantitatively reflected to accurately determine the heat propagation path parameters of the target battery pack. By combining the operating data and the heat propagation path parameters of the target battery pack, the heat propagation characteristic parameters within the target battery pack at different time points can be determined to accurately determine the thermal runaway risk index corresponding to the target battery pack, thereby solving the technical problem of inaccurate determination of the thermal runaway risk index of a battery pack in the related art.

[0057] As an optional embodiment, based on the operating data and the heat propagation path parameters, heat propagation characteristic parameters corresponding to multiple operating time parameters are determined, including: when the heat propagation path parameters include a heat propagation path graph, an adjacency matrix and a degree matrix corresponding to the heat propagation path graph are determined, wherein the heat propagation path graph includes multiple nodes obtained based on multiple sub-batteries, the adjacency matrix is ​​a matrix indicating whether the corresponding node is connected to other nodes, and the degree matrix is ​​a matrix indicating the number of nodes connected to the corresponding node; based on the adjacency matrix and the degree matrix, a spatial feature matrix corresponding to the heat propagation path graph is determined, wherein the diagonal elements of the spatial feature matrix are used to represent the node features corresponding to multiple nodes in the heat propagation path graph, and the non-diagonal elements of the spatial feature matrix are used to represent the adjacency features corresponding to multiple nodes in the heat propagation path graph; based on the operating data and the spatial feature matrix, the heat propagation characteristic parameters corresponding to multiple operating time parameters are determined.

[0058] In this embodiment, specific steps of determining heat propagation characteristic parameters corresponding to a plurality of operation time parameters respectively based on operation data and heat propagation path parameters are described.

[0059] This involves a heat propagation path diagram, which is a network structure that describes the heat propagation paths between multiple sub-cells within a target battery pack. In this heat propagation path diagram, each sub-cell is represented as a node, and the edges between nodes represent the heat propagation paths. The edge weights reflect the heat propagation intensity (including heat propagation efficiency) between the sub-cells.

[0060] This involves the adjacency matrix, which describes the connection relationship between nodes in the heat propagation path graph. In the adjacency matrix, the rows and columns correspond to the nodes in the graph, and the elements of the matrix indicate whether there is a connection between the two nodes. For example, if there is a direct heat energy propagation path between nodes a and b, the corresponding position in the adjacency matrix (row a, column b, and row b, column a) has a value of 1; otherwise, the value of the position is 0.

[0061] This involves a degree matrix, which is a diagonal matrix whose diagonal elements represent the number of other nodes directly connected to each node in the heat propagation path graph. The degree matrix is ​​used to quantify the degree of connectivity of each subcell (node), that is, how many direct neighbors can exchange thermal energy through the heat propagation path.

[0062] This involves multiple nodes, which represent individual sub-batteries within a battery pack in a heat propagation path diagram. Each node carries relevant heat propagation characteristics, such as temperature, heat capacity, and thermal conductivity, which affect the distribution and propagation of heat energy within the target battery pack.

[0063] This involves a spatial feature matrix, which is a matrix used to represent node characteristics and inter-node adjacency characteristics, reflecting the propagation characteristics of heat energy between multiple sub-batteries in the target battery pack in the spatial dimension. For the heat propagation path diagram, the diagonal elements of the spatial feature matrix represent the node characteristics of each sub-battery (node), including thermal attribute characteristics such as initial temperature and heat capacity; the off-diagonal elements represent the adjacency characteristics of the node, such as the heat propagation characteristics between two nodes, including thermal conduction intensity or efficiency. This spatial feature matrix can be represented by a Laplace matrix.

[0064] Among them, diagonal elements are involved, which are elements on the diagonal line extending from the upper left corner to the lower right corner of the matrix (such as the spatial feature matrix), and non-diagonal elements are other elements in the matrix except the diagonal elements.

[0065] In the steps involved in this embodiment, the heat propagation path diagram intuitively represents the propagation path and intensity of heat energy inside the battery pack through the structure of nodes and edges. By constructing the heat propagation path diagram, an adjacency matrix and a degree matrix are formed. The adjacency matrix clearly shows the heat propagation path diagram which sub-batteries have direct connections for heat energy transfer and the strength of such connections, while the degree matrix can accurately represent the centrality of each sub-battery (node) in the heat propagation path, that is, how many other nodes it has direct heat energy propagation paths with. Then, by combining the adjacency matrix and the degree matrix to generate a spatial feature matrix, the heat energy propagation status of the target battery pack under the corresponding time parameters in the spatial dimension can be fully reflected.

[0066] As an optional embodiment, determining heat propagation characteristic parameters corresponding to multiple operation time parameters respectively based on operation data and a spatial characteristic matrix includes: determining spatial characteristic parameters corresponding to multiple operation time parameters respectively based on the operation data and the spatial characteristic matrix; determining time characteristic parameters corresponding to multiple operation time parameters respectively based on the spatial characteristic parameters corresponding to the multiple operation time parameters; and determining heat propagation characteristic parameters corresponding to the multiple operation time parameters respectively based on the spatial characteristic parameters and time characteristic parameters corresponding to the multiple operation time parameters respectively.

[0067] In this embodiment, specific steps of determining heat propagation characteristic parameters corresponding to a plurality of operating time parameters respectively based on operating data and a spatial characteristic matrix are described.

[0068] Among them, the spatial feature parameters are involved, which are the thermal propagation spatial features of the target battery pack under the corresponding operating time parameters (such as time nodes), including the target thermal propagation spatial features of each sub-battery (node) within the target battery pack. Specifically, the target thermal propagation spatial features integrate the thermal propagation spatial features of the node and the thermal propagation spatial features of the adjacent nodes corresponding to the node. For example, the acquisition of the spatial feature parameters can adopt a graph convolutional network to aggregate the features of the adjacent nodes of each node and update the thermal propagation spatial features of the corresponding node.

[0069] Among them, the time characteristic parameter is involved, which is the characteristic of the thermal energy state of the target battery pack changing over time. On the basis of the spatial characteristic parameters, the heat propagation characteristics of the target battery pack in the time dimension under each time characteristic parameter are further analyzed from the time dimension. The time characteristic parameter can be a spatial characteristic parameter corresponding to multiple operating time parameters, and a time series analysis (such as using a recurrent neural network such as LSTM or GRU) is performed to capture the time characteristics of heat energy propagation within the battery pack, such as the temperature fluctuation pattern over time, the heat energy accumulation rate, etc. The time characteristic parameter can reflect the evolution of the thermal state of the battery pack at different operating stages, and is one of the indispensable dimensions for assessing the risk of thermal runaway.

[0070] In the steps involved in this embodiment, by running data and the spatial feature matrix, the spatial feature parameters of each node under different time parameters are updated and determined, which can fully reflect the complex spatial relationship of heat propagation inside the target battery pack. On this basis, the time feature parameters are further determined according to the spatial feature parameters, which can capture the dynamic law of thermal energy changing with time. Therefore, by combining the spatial feature parameters and the time feature parameters, the thermal runaway risk can be comprehensively and finely analyzed from the time and space dimensions.

[0071] As an optional embodiment, determining time characteristic parameters corresponding to multiple running time parameters respectively based on spatial characteristic parameters corresponding to multiple running time parameters includes: determining an initial time characteristic parameter corresponding to a heat propagation characteristic sequence, wherein the heat propagation characteristic sequence includes spatial characteristic parameters corresponding to multiple running time parameters respectively; determining a first time characteristic parameter corresponding to the first running time parameter according to the time sequence of the multiple running time parameters based on the initial time characteristic parameter and the first spatial characteristic parameter corresponding to the first running time parameter; determining a next time characteristic parameter corresponding to the next running time parameter based on the first time characteristic parameter and the next spatial characteristic parameter corresponding to the next running time parameter, until the multiple running time parameters are processed and the time characteristic parameters corresponding to the multiple running time parameters are obtained.

[0072] In this embodiment, specific steps of determining the time characteristic parameters respectively corresponding to the plurality of runtime parameters based on the spatial characteristic parameters respectively corresponding to the plurality of runtime parameters are described.

[0073] Herein, a heat propagation characteristic sequence is involved, which is a sequence of time-related heat propagation spatial characteristic parameters.

[0074] Here, an initial time characteristic parameter is involved, and the initial time characteristic parameter is a time characteristic parameter of a predetermined heat propagation characteristic sequence.

[0075] The first running time parameter is involved. The first running time parameter is the first running time parameter of the heat propagation feature sequence and is the starting time for subsequent heat propagation analysis and time feature parameter extraction.

[0076] Among them, the next running time parameter is involved. The next running time parameter is the next running time parameter on the heat propagation feature sequence relative to the time parameter of the current analysis, and is used to dynamically analyze the change of heat energy propagation over time.

[0077] Herein, a first spatial characteristic parameter is involved, and the first spatial characteristic parameter is a heat propagation spatial characteristic corresponding to a first operating time parameter.

[0078] Among them, a first time characteristic parameter is involved, which is obtained based on the initial time characteristic parameter and the first space characteristic parameter, and reflects the characteristics of the thermal energy state of the target battery pack at the first operating time parameter changing with time.

[0079] Here, the next spatial characteristic parameter is involved, and the next spatial characteristic parameter is the spatial characteristic parameter corresponding to the next running time parameter relative to the time parameter of the current analysis.

[0080] Among them, the next spatial characteristic parameter is involved, which is obtained based on the current time characteristic parameter and the next spatial characteristic parameter, and reflects the time dynamic characteristics of heat energy propagation of the target battery pack at the next operating time parameter.

[0081] In the steps involved in this embodiment, the time characteristic parameters of the next time parameter are predicted and updated based on the spatial characteristic parameters of the current time parameter and the time characteristic parameters of the previous time parameter. Through iterative analysis, starting from the first operating time parameter, the time characteristic parameters of subsequent time points are gradually determined. This can accurately capture the time dynamic characteristics of heat energy propagation, including the rate of heat energy accumulation, the temperature fluctuation pattern over time, etc., thereby achieving accurate capture of the time dynamic characteristics of heat energy propagation of the target battery pack.

[0082] As an optional embodiment, before determining the adjacency matrix corresponding to the heat propagation path graph, it also includes: when the heat propagation path parameters include the heat propagation path graph and the arrangement parameters include the arrangement position relationship, determining the voltage change parameters corresponding to the multiple sub-batteries respectively; determining multiple nodes based on the multiple sub-batteries, wherein the multiple nodes correspond one-to-one to the multiple sub-batteries; determining multiple edges based on the arrangement position relationships corresponding to the multiple sub-batteries respectively, wherein the multiple edges correspond one-to-one to the multiple arrangement position relationships; determining the edge weights corresponding to the multiple edges based on the voltage change parameters corresponding to the multiple sub-batteries respectively; and determining the heat propagation path graph corresponding to the target battery pack based on the multiple nodes, the multiple edges, and the edge weights corresponding to the multiple edges respectively.

[0083] In this embodiment, the specific steps before determining the adjacency matrix corresponding to the heat propagation path graph are described.

[0084] This involves the arrangement position relationship, which refers to the physical layout and spatial position relationship of the sub-cells in the target battery pack, including the adjacency, distance, and arrangement between sub-cells. This arrangement position relationship directly affects the transmission path and efficiency of heat energy from one sub-cell to another, and is crucial for understanding how heat energy propagates within the battery pack.

[0085] The voltage variation parameter is a characteristic parameter of the voltage of each sub-battery over time during the operation of the target battery pack. The voltage variation parameter includes the voltage variation rate, voltage variation amplitude, voltage variation trend, etc.

[0086] Therein, multiple edges are involved, and the multiple edges are used to represent the connection relationship between sub-batteries when constructing a heat propagation path diagram, that is, the path of heat energy propagation.

[0087] This involves edge weights, which represent the importance of an edge (i.e., the heat transfer path between sub-cells) to heat propagation. Edge weights can be determined based on the voltage variation parameters of the sub-cells and reflect the efficiency or ease of heat transfer between the two sub-cells. A larger edge weight indicates more significant heat transfer along this path.

[0088] In the steps involved in this embodiment, based on the sub-batteries and their arrangement and positional relationships, a heat propagation network for the target battery pack can be accurately constructed, visualizing the heat propagation paths. Furthermore, when thermal runaway risk occurs, the sub-battery voltages will experience abnormal changes. By determining edge weights based on the sub-battery voltage change parameters, the importance of different heat propagation paths can be accurately quantified.

[0089] As an optional embodiment, a thermal runaway risk index corresponding to a target battery pack is determined based on the thermal propagation characteristic parameters corresponding to a plurality of operating time parameters, including: determining the thermal propagation characteristic distribution parameters corresponding to the target battery pack based on the thermal propagation characteristic parameters corresponding to the plurality of operating time parameters; determining the thermal propagation fluctuation index and the thermal propagation trend index corresponding to the target battery pack based on the thermal propagation characteristic distribution parameters; and determining the thermal runaway risk index corresponding to the target battery pack based on the thermal propagation fluctuation index and the thermal propagation trend index.

[0090] In this embodiment, specific steps of determining a thermal runaway risk index corresponding to a target battery pack based on heat propagation characteristic parameters corresponding to a plurality of operating time parameters are described.

[0091] This involves heat propagation characteristic distribution parameters, which are statistics that describe how these parameters are distributed throughout the battery pack under different operating time parameters. These parameters, including their mean, variance, and distribution shape, quantify the spatial and temporal characteristics of thermal energy propagation. By analyzing these parameters, we can understand common patterns and abnormalities in battery pack thermal energy propagation, providing a foundation for subsequent risk assessment.

[0092] This involves the heat transfer fluctuation index, which quantifies the degree of fluctuation of heat transfer characteristic parameters over time. It reflects the stability of heat transfer in the battery pack. A high fluctuation index may indicate unstable heat transfer and the potential risk of thermal runaway. For example, the heat transfer fluctuation index can be determined by the variance or standard deviation of multiple heat transfer characteristic parameters over time.

[0093] This involves the heat propagation trend index, which describes the long-term trend of heat propagation characteristic parameters over time. This index can help identify whether heat energy propagation is showing a trend of continuous growth, decrease, or stability, and is crucial for predicting the potential development of thermal runaway events. The index can be determined using a mean value.

[0094] In the steps involved in this embodiment, the heat propagation characteristic distribution parameters can reveal the common patterns and abnormal signs of heat energy propagation within the battery pack. The heat propagation fluctuation index quantifies the degree of change of the heat propagation characteristic parameters over time, which helps to identify the instability of heat energy propagation in the battery pack. The heat propagation trend index can analyze the long-term change trend of the heat propagation characteristic parameters. By comprehensively analyzing the fluctuations and trends of heat propagation, it can help to capture early signs of thermal runaway in a timely and accurate manner, thereby helping to accurately determine the thermal runaway risk index of the target battery pack.

[0095] It should be noted that this step can be implemented through a variational autoencoder network structure.

[0096] As an optional embodiment, a thermal runaway risk index corresponding to a target battery pack is determined based on heat propagation characteristic parameters corresponding to a plurality of operating time parameters, including: retrieving a target model, wherein the target model is obtained by training an initial model based on sample data, the sample data includes thermal runaway sample data and non-thermal runaway sample data, and the thermal runaway risk index corresponding to the thermal runaway sample data is greater than or equal to a risk threshold; and determining a thermal runaway risk index corresponding to the target battery pack based on the heat propagation characteristic parameters corresponding to a plurality of operating time parameters and the target model.

[0097] In this embodiment, specific steps of determining a thermal runaway risk index corresponding to a target battery pack based on heat propagation characteristic parameters corresponding to a plurality of operating time parameters are described.

[0098] The target model is obtained by training and optimizing the initial model using sample data and is used to determine the thermal runaway risk index. The target model may include a variational autoencoder network structure design.

[0099] This involves sample data, which is a dataset used to train and validate the target model. It contains two types of data: thermal runaway sample data and non-thermal runaway sample data. This data is used to adjust the model parameters so that it can accurately distinguish and predict the normal operation and thermal runaway risk states of the battery pack.

[0100] This involves an initial model, which is the original model before the training process begins, without any adjustments to the sample data. This initial model has parameters that are randomly initialized or set based on some theoretical assumptions and preliminary rules. Through training, the initial model gradually transforms into a target model that can make effective predictions.

[0101] This involves thermal runaway sample data, which includes data such as the operating time and heat propagation characteristic parameters of the first sample battery pack during a thermal runaway event. This thermal runaway sample data typically has a high thermal runaway risk index and at least meets or exceeds the risk threshold, which helps the model learn to identify patterns and signs of thermal runaway.

[0102] This involves non-thermal runaway sample data. This data, in contrast to the thermal runaway sample data, records the operating time and thermal propagation characteristics of the second sample battery pack under normal operating conditions. This type of data has a lower thermal runaway risk index, helping the model establish a baseline for normal operation and more accurately identify abnormal conditions.

[0103] This involves a risk threshold, a preset threshold used to distinguish between thermal runaway sample data and non-thermal runaway sample data. If the thermal runaway risk index predicted by the target model reaches or exceeds this threshold, it indicates that the battery pack may be at risk of thermal runaway, requiring further diagnostic or preventive measures.

[0104] In the steps involved in this embodiment, the target model is trained based on a large amount of thermal runaway sample data and non-thermal runaway sample data, and can effectively distinguish between normal operation and complex patterns with different thermal runaway risk indices. By calling and using the pre-trained target model, the thermal runaway risk index of the target battery pack can be quickly and accurately determined.

[0105] Based on the above embodiment and optional embodiment, an optional implementation manner is provided, which is described in detail below.

[0106] In related technologies, battery pack thermal runaway is a potential safety hazard in scenarios such as electric vehicles and energy storage power stations. The resulting high temperatures, high voltages, and combustion can damage equipment and even threaten personal safety. Therefore, to prevent thermal runaway, it is necessary to determine a battery pack thermal runaway risk index. However, in related technologies, determining the thermal runaway risk index for battery packs can be inaccurate.

[0107] In view of this, an optional embodiment of the present invention provides a method for determining the thermal runaway risk index of a battery pack, which can also be called a thermal runaway propagation warning method for a lithium battery pack. It can effectively solve the technical problem in related technologies of inaccurate determination of the thermal runaway risk index when determining the thermal runaway risk index of a battery pack.

[0108] Figure 2 This is a flowchart of the thermal runaway propagation warning of a lithium battery pack in an optional embodiment of the present invention. Figure 3 is a variational autoencoder network structure diagram in an optional embodiment of the present invention, such as Figure 2 ,as well as Figure 3 As shown, the following is a detailed introduction.

[0109] S1: Acquire multimodal data (ie, operating data before preprocessing) of a lithium-ion battery, ie, a battery pack (same as the target battery pack described above).

[0110] The operating data of lithium-ion batteries is transmitted in real time through the battery management system (BMS) and stored in the cloud platform database. The multimodal data obtained includes but is not limited to: single cell voltage, total battery pack voltage, current during charge and discharge, temperature data, mileage, insulation resistance, etc.

[0111] S2: Preprocess multimodal data.

[0112] Specifically, S2 includes:

[0113] S21: Remove duplicate data, missing data, or data frames with obvious errors;

[0114] S22: For data frames with abnormal feature jumps, the mean filtering method is used for processing. That is, a fixed window size is set, the mean of the data within the window is calculated, and the mean is used as the result feature value to smooth data fluctuations and reduce the impact of abnormal values ​​on the analysis results;

[0115] S23: Normalize the data of different dimensions so that they have the same scale range, and obtain preprocessed multimodal data (same as the above-mentioned operating data).

[0116] S3: Construct a battery pack space diagram (same as the above-mentioned heat propagation path diagram, wherein the heat propagation path parameters include the heat propagation path diagram) and implement dynamic diagram update.

[0117] Specifically, S3 includes:

[0118] S31: The battery pack includes multiple battery cells (same as the multiple sub-batteries mentioned above). Each battery cell (same as the sub-battery mentioned above) is defined as a node in the battery pack spatial graph. Node characteristics include voltage, temperature, insulation resistance, etc. Edges are constructed based on the module arrangement relationship of the battery pack (same as the arrangement parameters mentioned above). The edge weight reflects the voltage change rate between cells (same as the voltage change parameter mentioned above).

[0119] S32: Dynamically adjust edge weights based on real-time monitoring data.

[0120] S4: Spatiotemporal graph convolution (ST-GCN) modeling to generate a feature matrix (heat propagation feature parameters corresponding to the above multiple runtime parameters).

[0121] S41: Use graph convolutional networks to aggregate features of adjacent nodes and capture the spatial dependencies between cells. Specifically, based on the spatial graph (same as the heat propagation path graph), the adjacent node features (same as the adjacent features) are weighted aggregated through the Laplacian matrix (same as the spatial feature matrix). The result is the output of the spatial feature matrix X for each time step for all battery cells. t (spatial feature parameters corresponding to the above multiple runtime parameters), the dimension is (number of monomers x feature dimension), where the Laplacian matrix is ​​constructed from the adjacency matrix and the degree matrix;

[0122] S42: Combine the long short-term memory network to process the time series data (same as the above heat propagation feature sequence) to capture the time dynamics of thermal runaway propagation. Specifically, the spatial feature matrix X of each time step (same as the above running time parameter) is converted to tAs the input sequence of LSTM, the hidden state h of each time step is finally output t , the dimensions are: number of hidden units;

[0123] S42: Generate the battery pack spatial feature matrix (same as the above heat propagation feature parameters) for each time step to reflect the thermal runaway propagation trend between cells. Specifically, the hidden state h t Stacking forms a three-dimensional tensor H (heat propagation characteristic parameters corresponding to the above multiple runtime parameters), with the dimensions of: number of time steps - number of monomers - number of hidden units.

[0124] S5: Design the variational autoencoder (VAE, same as the initial model above) network structure.

[0125] Specifically, the network structure of the variational autoencoder is designed, including the encoder, decoder and latent space representation.

[0126] Specifically:

[0127] S51: The encoder and decoder models use a two-layer GRU model with 64 hidden dimensions;

[0128] S52: The latent space between the encoder and decoder has 64 dimensions;

[0129] S53: The mileage constraint model uses a two-layer multilayer perceptron model with 32 hidden dimensions;

[0130] S54: Training is performed using the Adam optimizer with a learning rate of 0.01 and a batch size of 128 samples.

[0131] S6: Construct training objective function.

[0132] In order to train the initial model to obtain the target model, the objective function for training the initial model is constructed as follows:

[0133] l all =l1+l2

[0134] in:

[0135] l all represents the joint training loss;

[0136] l1 represents the reconstruction loss;

[0137] l2 represents the regularization loss.

[0138] Assuming N is the total number of samples (same as the sample data above), then for each sample n, the specific calculation formula of the loss function is:

[0139]

[0140] in:

[0141] l n represents the loss of sample n;

[0142] x n represents the predicted value;

[0143] y n Represents the true value.

[0144] For the reconstruction loss, the calculation formula is as follows:

[0145]

[0146] For the regularization loss, the calculation formula is as follows:

[0147]

[0148] in:

[0149] For the latent space, v i represents the variance, μ i Indicates mean (Mean), logv i is the logarithm of the variance.

[0150] S7: Train the early warning model (i.e., variational autoencoder, same as the initial model above).

[0151] S71: Using sample data, including historical thermal runaway data (same as the thermal runaway sample data described above) and normal operating condition data (non-thermal runaway sample data), to jointly train a variational autoencoder (i.e., a VAE model);

[0152] S72: Input the multi-time-step spatial feature matrix H (the heat propagation feature parameters corresponding to the above-mentioned multiple runtime parameters) output by ST-GCN into the VAE encoder to obtain the decoded output result, and calculate the reconstruction loss and regularization loss.

[0153] S8: Determine the battery warning requirement based on the alarm threshold.

[0154] When the thermal runaway risk index exceeds the alarm threshold, an alarm is triggered. That is, after the model is deployed, the battery pack status is monitored in real time. Based on the set threshold, an alarm is triggered when the target loss value (same as the thermal runaway risk index) exceeds the warning threshold, prompting manual intervention.

[0155] Through the above optional implementation, at least the following beneficial effects can be achieved:

[0156] (1) Compared with the related art, the present invention can quantitatively reflect the heat propagation inside the battery pack by analyzing the arrangement parameters corresponding to multiple sub-batteries in the target battery pack, so as to accurately determine the heat propagation path parameters of the target battery pack, and determine the heat propagation characteristic parameters inside the target battery pack at different time points by integrating the operating data and heat propagation path parameters of the target battery pack, so as to accurately determine the thermal runaway risk index corresponding to the target battery pack, thereby solving the technical problem of inaccurate determination of the thermal runaway risk index when determining the thermal runaway risk index of the battery pack in the related art.

[0157] (2) Compared with the related art, the present invention forms an adjacency matrix and a degree matrix by constructing a heat propagation path diagram. The adjacency matrix clearly shows the heat propagation path diagram which sub-batteries have direct connections for heat energy transfer and the strength of such connections, while the degree matrix can accurately represent the centrality of each sub-battery in the heat propagation path, that is, how many other nodes it has direct heat energy transfer paths with. Then, by combining the adjacency matrix and the degree matrix, a spatial feature matrix is ​​generated, which can comprehensively reflect the heat energy propagation status of the target battery group under the corresponding time parameters in the spatial dimension.

[0158] (3) Compared with related technologies, the present invention updates and determines the spatial characteristic parameters of each node under different time parameters by running data and spatial characteristic matrix, which can fully reflect the complex spatial relationship of heat propagation inside the target battery pack. On this basis, the time characteristic parameters are further determined according to the spatial characteristic parameters, which can capture the dynamic law of thermal energy changing with time. Therefore, by combining the spatial characteristic parameters and the time characteristic parameters, the thermal runaway risk can be comprehensively and finely analyzed from the time and space dimensions.

[0159] (4) Compared with related technologies, the present invention can reveal the general patterns and abnormal signs of heat energy propagation in the battery pack through the heat propagation characteristic distribution parameters. The heat propagation fluctuation index quantifies the degree of change of the heat propagation characteristic parameters over time, which helps to identify the instability of heat energy propagation in the battery pack. The heat propagation trend index can analyze the long-term change trend of the heat propagation characteristic parameters. By comprehensively analyzing the fluctuations and trends of heat propagation, it can help to capture early signs of thermal runaway in a timely and accurate manner, and thus help to accurately determine the thermal runaway risk index of the target battery pack.

[0160] (5) Compared with related technologies, the present invention aggregates the spatial characteristics of cells in the battery pack through a graph convolutional network (GCN), dynamically adjusts the spatial topological relationship, and adapts to the evolution of the correlation between cells during the propagation of thermal runaway; combines the long short-term memory network (LSTM) to process time series data and capture the temporal dynamics of thermal runaway propagation; generates latent variables through a variational autoencoder (VAE) to capture the overall state of the battery pack and the potential laws of thermal runaway propagation, breaking through the limitation of traditional methods that only focus on cell anomalies. This space-time-propagation integrated modeling method is more adaptable to complex real-world scenarios.

[0161] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should be aware that the present invention is not limited by the order of the actions described, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0162] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0163] Example 2

[0164] According to an embodiment of the present invention, a device for implementing the above-mentioned method for determining the thermal runaway risk index of a battery pack is also provided. Figure 4 FIG. 1 is a structural block diagram of a device for determining a thermal runaway risk index of a battery pack according to an embodiment of the present invention. Figure 4 As shown, the device includes: an acquisition module 402, a first determination module 404, a second determination module 406, a third determination module 408 and a fourth determination module 410. The device will be described in detail below.

[0165] An acquisition module 402 is used to acquire operating data corresponding to a target battery pack, wherein the target battery pack includes multiple sub-batteries and the operating data includes multiple operating time parameters; a first determination module 404 is connected to the above-mentioned acquisition module 402 and is used to determine the arrangement parameters corresponding to the multiple sub-batteries respectively; a second determination module 406 is connected to the above-mentioned first determination module 404 and is used to determine the heat propagation path parameters corresponding to the target battery pack based on the multiple sub-batteries and the arrangement parameters corresponding to the multiple sub-batteries respectively; a third determination module 408 is connected to the above-mentioned second determination module 406 and is used to determine the heat propagation characteristic parameters corresponding to the multiple operating time parameters respectively based on the operating data and the heat propagation path parameters; a fourth determination module 410 is connected to the above-mentioned third determination module 408 and is used to determine the thermal runaway risk index corresponding to the target battery pack based on the heat propagation characteristic parameters corresponding to the multiple operating time parameters respectively.

[0166] It should be noted here that the above-mentioned acquisition module 402, first determination module 404, second determination module 406, third determination module 408 and fourth determination module 410 correspond to steps S102 to S110 in implementing the method for determining the thermal runaway risk index of a battery pack. The instances and application scenarios implemented by the multiple modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiment 1.

[0167] Example 3

[0168] According to another aspect of an embodiment of the present invention, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions, wherein the processor is configured to execute instructions to implement any of the above methods for determining a battery pack thermal runaway risk index.

[0169] Example 4

[0170] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute any of the above-mentioned methods for determining the thermal runaway risk index of a battery pack.

[0171] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0172] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0173] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0174] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0175] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0176] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0177] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A method for determining a battery pack thermal runaway risk index, characterized in that: include: Acquire operating data corresponding to a target battery pack, wherein the target battery pack includes a plurality of sub-batteries, and the operating data includes a plurality of operating time parameters; determining arrangement parameters corresponding to the plurality of sub-batteries respectively; Determining a heat transfer path parameter corresponding to the target battery group based on the plurality of sub-batteries and the arrangement parameters corresponding to the plurality of sub-batteries; determining heat propagation characteristic parameters corresponding to the plurality of operating time parameters respectively based on the operating data and the heat propagation path parameters; A thermal runaway risk index corresponding to the target battery pack is determined according to the heat propagation characteristic parameters corresponding to the plurality of operating time parameters.

2. The method according to claim 1, characterized in that Determining the heat propagation characteristic parameters corresponding to the plurality of operation time parameters respectively based on the operation data and the heat propagation path parameters includes: In a case where the heat propagation path parameter includes a heat propagation path graph, determining an adjacency matrix and a degree matrix corresponding to the heat propagation path graph, wherein the heat propagation path graph includes a plurality of nodes obtained based on a plurality of sub-batteries, the adjacency matrix is ​​a matrix indicating whether a corresponding node is connected to other nodes, and the degree matrix is ​​a matrix indicating the number of nodes connected to the corresponding node; Determining a spatial feature matrix corresponding to the heat propagation path graph based on the adjacency matrix and the degree matrix, wherein the diagonal elements of the spatial feature matrix are used to represent node features corresponding to a plurality of nodes in the heat propagation path graph, and the off-diagonal elements of the spatial feature matrix are used to represent adjacency features corresponding to the plurality of nodes in the heat propagation path graph; Heat propagation characteristic parameters corresponding to the plurality of operating time parameters are determined according to the operating data and the spatial characteristic matrix.

3. The method according to claim 2, characterized in that Determining the heat propagation characteristic parameters corresponding to the plurality of operation time parameters respectively based on the operation data and the spatial characteristic matrix includes: Determining spatial feature parameters corresponding to the plurality of runtime parameters respectively according to the operation data and the spatial feature matrix; Determining time characteristic parameters corresponding to the plurality of running time parameters respectively according to the spatial characteristic parameters corresponding to the plurality of running time parameters respectively; The heat propagation characteristic parameters respectively corresponding to the plurality of operating time parameters are determined according to the spatial characteristic parameters and the temporal characteristic parameters respectively corresponding to the plurality of operating time parameters.

4. The method according to claim 3, characterized in that The determining, based on the spatial characteristic parameters respectively corresponding to the multiple running time parameters, the time characteristic parameters respectively corresponding to the multiple running time parameters includes: determining initial time characteristic parameters corresponding to a heat propagation characteristic sequence, wherein the heat propagation characteristic sequence includes spatial characteristic parameters corresponding to the plurality of operating time parameters respectively; Determining a first time characteristic parameter corresponding to the first runtime parameter according to the time sequence of the plurality of runtime parameters, the initial time characteristic parameter, and the first spatial characteristic parameter corresponding to the first runtime parameter; According to the first time characteristic parameter and the next spatial characteristic parameter corresponding to the next running time parameter, the next time characteristic parameter corresponding to the next running time parameter is determined, until the multiple running time parameters are processed, and the time characteristic parameters corresponding to the multiple running time parameters are obtained.

5. The method according to claim 2, characterized in that Before determining the adjacency matrix corresponding to the heat propagation path graph, the method further includes: When the heat transfer path parameter includes a heat transfer path diagram and the arrangement parameter includes an arrangement position relationship, determining voltage change parameters corresponding to each of the plurality of sub-batteries; Determining a plurality of nodes based on the plurality of sub-batteries, wherein the plurality of nodes correspond one-to-one to the plurality of sub-batteries; Determining a plurality of edges according to the arrangement position relationships corresponding to the plurality of sub-batteries, wherein the plurality of edges correspond to the plurality of arrangement position relationships in a one-to-one manner; Determining edge weights corresponding to the plurality of edges respectively according to voltage change parameters respectively corresponding to the plurality of sub-batteries; A heat propagation path graph corresponding to the target battery pack is determined based on the multiple nodes, the multiple edges, and the edge weights corresponding to the multiple edges.

6. The method according to claim 1, characterized in that The determining, based on the heat propagation characteristic parameters corresponding to the plurality of operating time parameters, a thermal runaway risk index corresponding to the target battery pack includes: determining a heat propagation characteristic distribution parameter corresponding to the target battery pack according to the heat propagation characteristic parameters corresponding to the plurality of operating time parameters; determining a heat propagation fluctuation index and a heat propagation trend index corresponding to the target battery pack based on the heat propagation characteristic distribution parameters; A thermal runaway risk index corresponding to the target battery pack is determined based on the heat propagation fluctuation index and the heat propagation trend index.

7. The method according to any one of claims 1 to 6, characterized in that The determining, based on the heat propagation characteristic parameters corresponding to the plurality of operating time parameters, a thermal runaway risk index corresponding to the target battery pack includes: Retrieving a target model, wherein the target model is obtained by training an initial model based on sample data, the sample data including thermal runaway sample data and non-thermal runaway sample data, and a thermal runaway risk index corresponding to the thermal runaway sample data is greater than or equal to a risk threshold; A thermal runaway risk index corresponding to the target battery pack is determined based on the heat propagation characteristic parameters corresponding to the plurality of operating time parameters and the target model.

8. A device for determining a battery pack thermal runaway risk index, characterized in that: include: an acquisition module, configured to acquire operating data corresponding to a target battery pack, wherein the target battery pack includes a plurality of sub-batteries, and the operating data includes a plurality of operating time parameters; A first determining module, configured to determine arrangement parameters corresponding to the plurality of sub-batteries respectively; a second determining module, configured to determine a heat propagation path parameter corresponding to the target battery pack based on the plurality of sub-batteries and the arrangement parameters corresponding to the plurality of sub-batteries; a third determining module, configured to determine heat propagation characteristic parameters corresponding to the plurality of operating time parameters respectively based on the operating data and the heat propagation path parameters; The fourth determination module is configured to determine a thermal runaway risk index corresponding to the target battery pack based on the heat propagation characteristic parameters corresponding to the plurality of operating time parameters.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method for determining a thermal runaway risk index of a battery pack according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method for determining a thermal runaway risk index of a battery pack according to any one of claims 1 to 7.

Images