Lithium ion battery thermal runaway risk prediction device and method

Through the combination of data acquisition, processing and early warning models, the forward-backward algorithm and Viterbi algorithm are used to solve the problem of insufficient variable-long data processing capability in the prediction of thermal runaway risk of lithium-ion batteries, and the thermal runaway state of lithium-ion batteries is realized Accurate prediction and real-time early warning improve battery safety.

CN118940490AInactive Publication Date: 2024-11-12四川吉利学院

Patent Information

Application Number
CN202410980600.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The prior art relies heavily on historical data in the prediction of thermal runaway risk of lithium-ion batteries, and cannot process variable-length data, resulting in poor applicability and inability to effectively predict the thermal runaway risk of battery systems.

Method used

The data acquisition module is used to obtain battery parameter data, and the SOC and temperature calculation is performed through the data processing module, and it is transferred to a pre-trained early warning model for processing. The forward-backward algorithm and Viterbi algorithm are used to solve the model parameters and decode hidden state sequences. , realize the prediction and real-time early warning of thermal runaway state.

Benefits of technology

Overcoming the defect that the prior art cannot process variable-length data, the accurate prediction and real-time early warning of the thermal runaway state of lithium-ion batteries are achieved, and the battery safety is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940490A_ABST
    Figure CN118940490A_ABST
Patent Text Reader

Abstract

The invention discloses a lithium ion battery thermal runaway risk prediction device and method, and the device comprises a data collection module which is used for obtaining the parameter data of a battery; the data processing module is used for performing calculation processing according to the parameter data to obtain input parameters; the calculation processing comprises SOC calculation and temperature calculation; the prediction module is used for transmitting the input parameters to a pre-trained early warning model for processing so as to obtain a corresponding prediction result; the early warning model comprises a statistical learning model; judging whether early warning information is generated or not according to the prediction result; the method has the beneficial effects that after a model is established, a hidden state sequence is solved from acquired data through a Viterbi algorithm, and whether the current thermal runaway state exists or not is calculated; according to the method, migration from non-time-series data to time-series data is achieved, data with any variable length can be processed, and therefore the defects that in the prior art, variable-length data cannot be processed, and applicability is poor are overcome.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of battery safety technology, and in particular to a device and method for predicting thermal runaway risk of a lithium-ion battery. Background Art

[0002] Lithium-ion batteries have been widely used in new energy electric vehicles due to their high energy density, long life and small size. However, in actual applications, polymer lithium battery products will accumulate a lot of heat during daily operation and storage. When the battery temperature fluctuates too high, it will rapidly intensify the side decomposition reaction in the polymer battery system and even cause thermal runaway of the system, which will directly cause serious system overheating safety and reliability problems, thus bringing safety risks.

[0003] At present, there are also some solutions that use machine learning for prediction. Although machine learning has high accuracy, it relies heavily on historical data training and cannot process variable-length data, which leads to poor applicability. Summary of the invention

[0004] In view of the technical defects mentioned in the background technology, an object of the embodiments of the present invention is to provide a device and method for predicting the thermal runaway risk of a lithium-ion battery.

[0005] To achieve the above objectives, in a first aspect, an embodiment of the present invention provides a device for predicting thermal runaway risk of a lithium-ion battery, comprising:

[0006] Data acquisition module, used to obtain battery parameter data;

[0007] A data processing module, used for performing calculation processing according to the parameter data to obtain input parameters; wherein the calculation processing includes SOC calculation and temperature calculation;

[0008] Prediction module for:

[0009] The input parameters are transmitted to a pre-trained early warning model for processing to obtain corresponding prediction results; wherein the early warning model includes a statistical learning model;

[0010] Determine whether to generate warning information based on the prediction result.

[0011] As a preferred implementation of the present application, the parameter data of the battery includes voltage data, current data and temperature data; the data processing module estimates the battery SOC and the internal temperature of the battery based on the voltage data, current data and temperature data.

[0012] As a preferred implementation of the present application, when training the early warning model, the battery thermal runaway data set is used for training, and the model parameters are solved by a forward-backward algorithm;

[0013] During prediction, a new observation sequence is obtained based on the model parameters, and then the Viterbi algorithm is used to solve the hidden state sequence, thereby achieving the purpose of thermal runaway state prediction.

[0014] As a preferred implementation of the present application, the data processing module is also used to perform extended analysis on each variable data.

[0015] As a preferred implementation of the present application, the data processing module is also used to correct the SOC calculation to reduce errors; specifically including:

[0016] Based on the initial value, the corresponding current integral value is subtracted; wherein the current integral value is calculated by the correction coefficient, the nominal capacity of the battery, the charge and discharge current and the charge and discharge efficiency;

[0017] The correction coefficient is determined according to the preset influencing factors, and then the nominal capacity of the battery is updated; the nominal capacity is the capacity value obtained by completely discharging the current to the cut-off voltage at a preset rate in a fully charged state.

[0018] In a second aspect, an embodiment of the present invention further provides a method for predicting thermal runaway risk of a lithium-ion battery, the method comprising:

[0019] Get the battery parameter data;

[0020] Performing calculation processing according to the parameter data to obtain input parameters; wherein the calculation processing includes SOC calculation and temperature calculation;

[0021] The input parameters are transmitted to a pre-trained early warning model for processing to obtain corresponding prediction results; wherein the early warning model includes a statistical learning model;

[0022] Determine whether to generate warning information based on the prediction result.

[0023] As a preferred implementation of the present application, when training the early warning model, the battery thermal runaway data set is used for training, and the model parameters are solved by a forward-backward algorithm;

[0024] During prediction, a new observation sequence is obtained based on the model parameters, and then the Viterbi algorithm is used to solve the hidden state sequence, thereby achieving the purpose of thermal runaway state prediction.

[0025] As a preferred implementation of the present application, the method further includes:

[0026] Extended analysis was performed on the data of each variable.

[0027] The technical solution provided by the embodiment of the present invention calculates and processes the acquired parameter data to obtain input parameters, and transmits the input parameters to a pre-trained early warning model for processing to obtain corresponding prediction results; the model parameters are solved by a forward-backward algorithm for modeling, and after the model is established, the currently acquired data is decoded by the Viterbi algorithm, the observation sequence is solved, the hidden state sequence is solved, and it is calculated whether it is currently in a thermal runaway state; the migration from non-time series data to time series data is realized, and any variable length data can be processed, thereby overcoming the defects of the prior art that variable length data cannot be processed and the applicability is poor. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the specific implementation of the present invention or the technical solution in the prior art, the drawings required for use in the specific implementation or the description of the prior art are briefly introduced below.

[0029] Figure 1 This is a principle block diagram of a device for predicting thermal runaway risk of a lithium-ion battery provided by an embodiment of the present invention;

[0030] Figure 2 It is a flow chart of a method for predicting thermal runaway risk of a lithium-ion battery provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application 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 as to describe the embodiments of the present application described herein.

[0033] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0034] Throughout the specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment of the present invention. Therefore, the phrases "in one embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily all refer to the same embodiment or example. Furthermore, particular features, structures, or characteristics may be combined in one or more embodiments or examples in any appropriate combinations and / or subcombinations.

[0035] It should be noted that, unless otherwise specified, the technical terms in this embodiment have the common meanings understood in the relevant technical field.

[0036] Please refer to Figure 1 , a lithium-ion battery thermal runaway risk prediction device provided by an embodiment of the present invention comprises:

[0037] Data acquisition module, used to obtain battery parameter data;

[0038] A data processing module, used for performing calculation processing according to the parameter data to obtain input parameters; wherein the calculation processing includes SOC calculation and temperature calculation;

[0039] Prediction module for:

[0040] The input parameters are transmitted to a pre-trained early warning model for processing to obtain corresponding prediction results; wherein the early warning model includes a statistical learning model;

[0041] Determine whether to generate warning information based on the prediction result.

[0042] During implementation, the parameter data of the battery includes voltage data, current data and temperature data; the data processing module estimates the battery SOC and the internal temperature of the battery according to the voltage data, current data and temperature data.

[0043] In this embodiment, relevant preprocessing is first performed. On the basis of conventional data conversion and deletion, it also includes extracting fast and slow charging data fragments and sorting the overall data after time data processing according to the time column for data integration.

[0044] When the calculation and processing is performed according to the parameter data, it includes corresponding SOC estimation and temperature calculation; wherein the temperature calculation includes two parts: the internal temperature of the battery and the surface temperature.

[0045] The thermal runaway process can be regarded as a Gaussian mixture random process, and three Gaussian distributions represent three states: safe state, risky state, and thermal runaway state.

[0046] The statistical learning model adopts a hidden Markov model, which includes a state transfer process and an observation process; the state transfer process cannot be observed and can only be inferred through the observable sequence of the output.

[0047] When training the early warning model, the battery thermal runaway data set is used for training, and the model parameters are solved by a forward-backward algorithm; the forward-backward algorithm of this embodiment adopts the Baum-Welch algorithm, which is an algorithm for estimating hidden Markov model (HMM) parameters, and the HMM model parameters are estimated according to the observed data;

[0048] At the same time, a mixed Gaussian model is used to optimize the features of the data in the thermal runaway dataset;

[0049] By adding the Markov state transition process to the hidden state of the mixed Gaussian model, a hidden Markov model applied to time series analysis is constructed;

[0050] During prediction, a new observation sequence is obtained based on the model parameters, and then the Viterbi algorithm is used to solve the hidden state sequence, thereby achieving the purpose of thermal runaway state prediction;

[0051] It should be noted that the time series data to be predicted is processed simultaneously by combining statistical features and electrochemical features to combine more new features, thereby realizing feature extraction of data during prediction.

[0052] That is, in the model prediction stage, the real-time collected data is processed and input into the trained early warning model, and the current hidden state is solved through the Viterbi algorithm to achieve the purpose of real-time early warning.

[0053] Furthermore, in another embodiment, factors such as the external environment and internal aging of the battery may also affect the maximum capacity of the battery, thereby generating an estimation error, and the error becomes larger as time accumulates; in order to reduce the error, on the basis of the above scheme, the data processing module is also used to correct the SOC calculation to reduce the error; specifically, it includes:

[0054] Based on the initial value, the corresponding current integral value is subtracted; wherein the current integral value is calculated by the correction coefficient, the nominal capacity of the battery, the charge and discharge current and the charge and discharge efficiency;

[0055] The correction coefficient is determined according to the preset influencing factors, and then the nominal capacity of the battery is updated; the nominal capacity is the capacity value obtained by fully discharging the current to the cut-off voltage at a preset rate in a fully charged state;

[0056] The initial SOC value is estimated by the open circuit voltage method; the correction coefficient Ko=Ks×KT, where Ks is the cycle life influence factor and KT is the temperature influence factor.

[0057] The above scheme calculates and processes the acquired parameter data to obtain input parameters, and transmits the input parameters to a pre-trained early warning model for processing to obtain corresponding prediction results; the model parameters are solved by a forward-backward algorithm for modeling, and after the model is established, the currently acquired data is decoded by the Viterbi algorithm, the observation sequence is solved, the hidden state sequence is solved, and it is calculated whether it is currently in a thermal runaway state; the migration from non-time series data to time series data is realized, and any variable length data can be processed, thereby overcoming the defects of the prior art that it cannot process variable length data and has poor applicability.

[0058] Furthermore, the data processing module is also used to perform extended analysis on each variable data.

[0059] It should be noted that since the variables involved, such as temperature, current, and SOC, are closely related to thermal runaway, in order to enrich the data, each variable is also analyzed in multiple dimensions. For example, for voltage and temperature variables, we not only focus on their own data values, but also study their changes for expansion; for single cell voltage and temperature at the measuring point, their consistency is measured by information entropy; for high-precision data, appropriate distribution is used to determine outliers.

[0060] Reference Figure 2 Based on the same inventive concept, an embodiment of the present invention further provides a method for predicting thermal runaway risk of a lithium-ion battery, the method comprising the following steps:

[0061] S101, obtaining parameter data of the battery;

[0062] S102, performing calculation processing according to the parameter data to obtain input parameters; wherein the calculation processing includes SOC calculation and temperature calculation;

[0063] S103, transmitting the input parameters to a pre-trained early warning model for processing to obtain corresponding prediction results; wherein the early warning model includes a statistical learning model;

[0064] S104: Determine whether to generate warning information based on the prediction result.

[0065] Furthermore, when the early warning model is trained, the battery thermal runaway data set is used for training, and the model parameters are solved by a forward-backward algorithm;

[0066] During prediction, a new observation sequence is obtained based on the model parameters, and then the Viterbi algorithm is used to solve the hidden state sequence, thereby achieving the purpose of thermal runaway state prediction.

[0067] The method also includes: performing extended analysis on each variable data.

[0068] It should be noted that because the variables involved, such as temperature, current, and SOC, are closely related to thermal runaway;

[0069] In order to enrich the data, each variable is also analyzed in multiple dimensions. For example, for voltage and temperature variables, we not only focus on their data values, but also study their changes for expansion; for single cell voltage and temperature at the measuring point, we measure their consistency through information entropy; for high-precision data, we use appropriate distribution to determine outliers.

[0070] Furthermore, in another embodiment, factors such as the external environment and internal aging of the battery may also affect the maximum capacity of the battery, thereby generating an estimation error, and the error becomes larger as time accumulates; in order to reduce the error, based on the above solution, the method further includes:

[0071] Correct the SOC calculation to reduce the error; specifically include:

[0072] Based on the initial value, the corresponding current integral value is subtracted; wherein the current integral value is calculated by the correction coefficient, the nominal capacity of the battery, the charge and discharge current and the charge and discharge efficiency;

[0073] The correction coefficient is determined according to the preset influencing factors, and then the nominal capacity of the battery is updated; the nominal capacity is the capacity value obtained by fully discharging the current to the cut-off voltage at a preset rate in a fully charged state;

[0074] The initial SOC value is estimated by the open circuit voltage method.

[0075] It should be noted that for a more specific description of the workflow of the method embodiment, please refer to the aforementioned device embodiment part, which will not be repeated here.

[0076] The entire scheme calculates and processes the acquired parameter data to obtain input parameters, and transmits the input parameters to a pre-trained early warning model for processing to obtain corresponding prediction results; the model parameters are solved by a forward-backward algorithm for modeling, and after the model is established, the currently acquired data is decoded by the Viterbi algorithm, the observation sequence is solved, the hidden state sequence is solved, and it is calculated whether it is currently in a thermal runaway state; the migration from non-time series data to time series data is realized, and data of any variable length can be processed, thereby overcoming the defects of the prior art that it cannot process variable-length data and has poor applicability.

[0077] In several embodiments provided in the present application, it should be understood that the disclosed device and method can also be implemented in other ways. The device embodiment described above is only schematic, for example, each box in the flow chart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0078] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0079] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. It should be noted that, in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0080] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A device for predicting thermal runaway risk of a lithium-ion battery, characterized in that: include: Data acquisition module, used to obtain battery parameter data; A data processing module, used for performing calculation processing according to the parameter data to obtain input parameters; wherein the calculation processing includes SOC calculation and temperature calculation; Prediction module for: The input parameters are transmitted to a pre-trained early warning model for processing to obtain corresponding prediction results; wherein the early warning model includes a statistical learning model; Determine whether to generate warning information based on the prediction result.

2. A lithium-ion battery thermal runaway risk prediction device as claimed in claim 1, characterized in that: The parameter data of the battery includes voltage data, current data and temperature data; the data processing module estimates the battery SOC and the internal temperature of the battery according to the voltage data, current data and temperature data.

3. A lithium-ion battery thermal runaway risk prediction device as claimed in claim 2, characterized in that: When training the early warning model, the battery thermal runaway data set is used for training, and the model parameters are solved by a forward-backward algorithm; During prediction, a new observation sequence is obtained based on the model parameters, and then the Viterbi algorithm is used to solve the hidden state sequence, thereby achieving the purpose of thermal runaway state prediction.

4. A lithium-ion battery thermal runaway risk prediction device as claimed in claim 2, characterized in that: The data processing module is also used to perform extended analysis on each variable data.

5. A lithium-ion battery thermal runaway risk prediction device as claimed in claim 2, characterized in that: The data processing module is also used to correct the SOC calculation to reduce errors; specifically includes: Based on the initial value, the corresponding current integral value is subtracted; wherein the current integral value is calculated by the correction coefficient, the nominal capacity of the battery, the charge and discharge current and the charge and discharge efficiency; The correction coefficient is determined according to the preset influencing factors, and then the nominal capacity of the battery is updated; the nominal capacity is the capacity value obtained by completely discharging the current to the cut-off voltage at a preset rate in a fully charged state.

6. A method for predicting thermal runaway risk of a lithium-ion battery, characterized in that: The method comprises: Get the battery parameter data; Performing calculation processing according to the parameter data to obtain input parameters; wherein the calculation processing includes SOC calculation and temperature calculation; The input parameters are transmitted to a pre-trained early warning model for processing to obtain corresponding prediction results; wherein the early warning model includes a statistical learning model; Determine whether to generate warning information based on the prediction result.

7. A method for predicting thermal runaway risk of a lithium-ion battery according to claim 6, characterized in that: When training the early warning model, the battery thermal runaway data set is used for training, and the model parameters are solved by a forward-backward algorithm; During prediction, a new observation sequence is obtained based on the model parameters, and then the Viterbi algorithm is used to solve the hidden state sequence, thereby achieving the purpose of thermal runaway state prediction.

8. A method for predicting thermal runaway risk of a lithium-ion battery according to claim 6 or 7, characterized in that: The method also includes: performing extended analysis on each variable data.

Citation Information

Patent Citations

  • Temperature and aging degree-considered battery ampere-hour integral SOC estimation method

    CN107991623A

  • Battery SOC estimation method and device

    CN111220922A

  • Improved single-particle electrochemical model modeling method based on historical data verification

    CN115331745A

  • Lithium battery thermal runaway early warning method and medium

    CN118151017A

Cited By

  • Battery extreme high temperature thermal runaway temperature prediction method, system, medium and equipment

    CN120688209A