Vehicle thermal runaway prediction method, device, equipment and storage medium

Abstract

This invention discloses a method, apparatus, device, and storage medium for predicting vehicle thermal runaway, relating to the field of vehicle batteries. The method includes: collecting data on historical thermal runaway vehicles to obtain historical runaway data; performing voltage deviation analysis on the historical runaway vehicles based on the historical runaway data; determining the runaway threshold of the historical thermal runaway vehicles based on the voltage deviation analysis results; and predicting thermal runaway of a target vehicle to be analyzed based on the runaway threshold. Because this invention determines the runaway threshold of historical thermal runaway vehicles through voltage deviation analysis and predicts thermal runaway of the target vehicle to be analyzed based on the runaway threshold, it achieves early prediction of thermal runaway of vehicle power batteries, improving the accuracy of thermal runaway prediction and effectively enhancing vehicle safety.

Description

Technical Field

[0001] This invention relates to the field of vehicle battery technology, and in particular to a method, apparatus, device, and storage medium for predicting vehicle thermal runaway. Background Technology

[0002] With the development of information technology, the application of vehicle-to-everything (V2X) technology in automobiles is becoming increasingly widespread, and more and more vehicles are implementing V2X functionality. As V2X applications become more prevalent, the collection of real-time vehicle data is becoming increasingly easier. This is especially true for new energy vehicles, where all vehicles collect, transmit, and store data according to specific requirements, laying a solid foundation for subsequent vehicle data analysis.

[0003] With the increasing market share of new energy vehicles in recent years, thermal runaway has become an unavoidable issue. Current power batteries in new energy vehicles are prone to thermal runaway, and existing technology cannot accurately predict this problem.

[0004] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this invention is to provide a method, apparatus, device, and storage medium for predicting thermal runaway in vehicles, aiming to solve the technical problem that existing technologies cannot accurately predict the thermal runaway of power batteries.

[0006] To achieve the above objectives, the present invention provides a method for predicting vehicle thermal runaway, the method comprising the following steps:

[0007] Data was collected from historical thermal runaway vehicles to obtain historical runaway data;

[0008] Voltage deviation analysis was performed on the historical thermal runaway vehicles based on the historical runaway data.

[0009] The runaway threshold of the historical thermal runaway vehicles was determined based on the voltage deviation analysis results;

[0010] Thermal runaway prediction is performed on the target vehicle to be analyzed based on the runaway threshold.

[0011] Optionally, the voltage deviation analysis of the historical thermal runaway vehicle based on the historical runaway data includes:

[0012] Extract the voltage data of each individual cell in the battery pack of the historical thermal runaway vehicle from the historical runaway data;

[0013] Voltage deviation analysis is performed on each individual cell based on the voltage data.

[0014] Optionally, the voltage deviation analysis of each individual cell based on the voltage data includes:

[0015] The voltage outlier of each individual cell is determined based on the voltage data;

[0016] The voltage acquisition time data of each individual battery cell is obtained based on the historical runaway data;

[0017] A voltage deviation analysis graph is constructed based on the voltage outlier and the voltage time data;

[0018] Voltage deviation analysis is performed on each individual cell based on the voltage deviation analysis diagram.

[0019] Optionally, determining the voltage outlier of each individual cell based on the voltage data includes:

[0020] The voltage acquisition time data of each individual battery cell is obtained based on the historical runaway data;

[0021] Associate the voltage data with the voltage acquisition time data;

[0022] The voltage-time matrix of the battery pack is constructed based on the correlation results;

[0023] The voltage reference value of the battery pack is determined based on the voltage-time matrix;

[0024] The voltage outlier of each individual cell is determined based on the voltage reference value and the voltage data.

[0025] Optionally, the step of predicting thermal runaway of the target vehicle to be analyzed based on the runaway threshold includes:

[0026] Obtain the battery pack model of the historical thermal runaway vehicle;

[0027] The battery pack model is associated with the runaway threshold to obtain the runaway threshold mapping relationship;

[0028] Construct a thermal runaway prediction model based on at least one set of runaway threshold mapping relationships;

[0029] The battery pack signal of the target vehicle to be analyzed is input into the thermal runaway prediction model to predict thermal runaway of the target vehicle.

[0030] Optionally, the step of collecting data on historical thermal runaway vehicles to obtain historical runaway data includes:

[0031] Send a data acquisition request to the on-board terminal of a vehicle with a history of thermal runaway, so that the on-board terminal can collect data from the vehicle with a history of thermal runaway based on the data acquisition frequency in the data acquisition request;

[0032] Obtain the raw data of the historical thermal runaway vehicles collected by the vehicle terminal;

[0033] The raw data is processed to obtain historical out-of-control data.

[0034] Optionally, the step of processing the original data to obtain historical out-of-control data includes:

[0035] The original data is parsed to obtain the data fields contained in the original data;

[0036] Based on the data fields, the original data is classified to obtain candidate data;

[0037] The candidate data is cleaned based on preset cleaning rules to obtain historical out-of-control data.

[0038] Furthermore, to achieve the above objectives, the present invention also proposes a vehicle thermal runaway prediction device, the vehicle thermal runaway prediction device comprising:

[0039] Furthermore, to achieve the above objectives, the present invention also proposes a vehicle thermal runaway prediction device, which includes: a memory, a processor, and a vehicle thermal runaway prediction program stored in the memory and executable on the processor. The vehicle thermal runaway prediction program is configured to implement the steps of the vehicle thermal runaway prediction method as described above.

[0040] Furthermore, to achieve the above objectives, the present invention also proposes a storage medium storing a vehicle thermal runaway prediction program, wherein when the vehicle thermal runaway prediction program is executed by a processor, it implements the steps of the vehicle thermal runaway prediction method described above.

[0041] This invention collects data on historical thermal runaway vehicles to obtain historical runaway data. Based on this data, it performs voltage deviation analysis on the historical thermal runaway vehicles, determines the runaway threshold based on the analysis results, and then predicts thermal runaway of the target vehicle to be analyzed based on the runaway threshold. Because this invention uses voltage deviation analysis on historical thermal runaway vehicles to identify abnormal outlier batteries, determines the runaway threshold based on the analysis results, and predicts thermal runaway of the target vehicle to be analyzed based on the runaway threshold, it achieves early prediction of thermal runaway of vehicle power batteries, improves the accuracy of thermal runaway prediction, and effectively enhances vehicle safety. Attached Figure Description

[0042] Figure 1 This is a schematic diagram of the structure of a vehicle thermal runaway prediction device in the hardware operating environment involved in the embodiments of the present invention;

[0043] Figure 2 This is a flowchart illustrating the first embodiment of the vehicle thermal runaway prediction method of the present invention;

[0044] Figure 3 This is a flowchart illustrating the second embodiment of the vehicle thermal runaway prediction method of the present invention;

[0045] Figure 4 This is a schematic diagram of the voltage deviation curve of the second embodiment of the vehicle thermal runaway prediction method of the present invention;

[0046] Figure 5 This is a schematic diagram of the voltage-time matrix of the second embodiment of the vehicle thermal runaway prediction method of the present invention;

[0047] Figure 6 This is a flowchart illustrating the third embodiment of the vehicle thermal runaway prediction method of the present invention;

[0048] Figure 7 This is a structural block diagram of the first embodiment of the vehicle thermal runaway prediction device of the present invention.

[0049] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0050] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0051] Reference Figure 1 , Figure 1 This is a schematic diagram of the vehicle thermal runaway prediction device structure in the hardware operating environment involved in the embodiments of the present invention.

[0052] like Figure 1As shown, the vehicle thermal runaway prediction device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to establish communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk storage device. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0053] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the vehicle thermal runaway prediction device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0054] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a vehicle thermal runaway prediction program.

[0055] exist Figure 1 In the vehicle thermal runaway prediction device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the vehicle thermal runaway prediction device of the present invention can be set in the vehicle thermal runaway prediction device. The vehicle thermal runaway prediction device calls the vehicle thermal runaway prediction program stored in the memory 1005 through the processor 1001 and executes the vehicle thermal runaway prediction method provided in the embodiment of the present invention.

[0056] This invention provides a method for predicting vehicle thermal runaway, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of a vehicle thermal runaway prediction method according to the present invention.

[0057] In this embodiment, the vehicle thermal runaway prediction method includes the following steps:

[0058] Step S10: Collect data on historical thermal runaway vehicles to obtain historical runaway data.

[0059] It's important to note that current vehicle thermal runaway prediction methods primarily monitor and predict from a temperature perspective. Temperature, as the most direct indicator of thermal runaway, allows for rapid problem detection and decision-making. However, a significant drawback is that changes in battery temperature are often only detectable shortly before thermal runaway occurs, leaving very little time for prevention and intervention. Often, thermal runaway has already occurred before anyone can react. This is the main reason why thermal runaway is difficult to predict.

[0060] It is understood that this embodiment collects historical runaway data of historical thermal runaway vehicles and performs voltage deviation analysis on these vehicles to determine the battery outlier characteristics and trends. It then accurately calculates the runaway threshold for processing these vehicles and predicts thermal runaway based on the threshold. This allows for early prediction of vehicle thermal runaway and ensures vehicle safety.

[0061] It should be understood that the subject executing the method in this embodiment may be a vehicle thermal runaway prediction device with data processing, network communication and program running functions, such as a computer or monitoring platform, or other devices or equipment that can achieve the same or similar functions. Here, the above-mentioned vehicle thermal runaway prediction device (hereinafter referred to as prediction device) is used as an example for explanation.

[0062] It should be noted that vehicles with a history of thermal runaway can be those that have previously experienced power battery thermal runaway faults. The predictive device collects historical runaway data of the power battery of these vehicles by sending data acquisition requests to them. This historical runaway data can include relevant data about the power battery and vehicle operation, such as data acquisition time, vehicle VIN, vehicle operating status, total mileage, and individual battery cell voltage values.

[0063] In practice, the predictive equipment processes the raw data of historical thermal runaway vehicles to obtain historical runaway data, thereby cleaning up invalid data and improving the efficiency and accuracy of subsequent data analysis.

[0064] Step S20: Perform voltage deviation analysis on the historical thermal runaway vehicles based on the historical runaway data.

[0065] It should be noted that voltage deviation analysis can be used to analyze the voltage outlier trends of battery packs in vehicles with historical thermal runaway, thereby extracting the battery outlier characteristics of these vehicles. Voltage deviation refers to the voltage difference between individual cells in a battery pack. By measuring the voltage of each individual cell and calculating the difference between it and other individual cells, the voltage deviation within the battery pack can be obtained.

[0066] Understandably, predictive devices extract battery data and time data from historical runaway data, and based on this data, perform outlier analysis on the voltage of each individual cell in the battery pack of historical thermal runaway vehicles to identify abnormal individual cells in the battery pack and extract the outlier characteristics of the cells.

[0067] Step S30: Determine the runaway threshold of the historical thermal runaway vehicle based on the voltage deviation analysis results.

[0068] It should be noted that the runaway threshold can be the critical threshold at which the power battery of a vehicle with a history of thermal runaway has a risk of thermal runaway. The runaway threshold is different for different battery models. Therefore, in some embodiments, the prediction device obtains the runaway threshold corresponding to multiple battery models by performing voltage deviation analysis on multiple battery models, and establishes a mapping relationship between each power battery model and the corresponding runaway threshold.

[0069] It is understood that in some embodiments, the prediction device trains a model based on the mapping relationship between each type of power battery and the corresponding runaway threshold obtained through pre-analysis, constructs a thermal runaway prediction model, and performs thermal runaway prediction through the thermal runaway prediction model.

[0070] Step S40: Perform thermal runaway prediction on the target vehicle to be analyzed based on the runaway threshold.

[0071] It is understandable that this embodiment analyzes the voltage deviation of the battery in a vehicle that has experienced a thermal runaway failure, identifies outlier trends in battery voltage, and optimizes and adjusts the critical threshold for predicting thermal runaway characteristics through the analysis of a large amount of real data, thereby enabling early warning and early intervention to prevent problems before they occur.

[0072] Furthermore, to improve the efficiency of thermal runaway prediction, step S40 above may include:

[0073] Step S401: Obtain the battery pack model of the historical thermal runaway vehicle;

[0074] Step S402: Associate the battery pack model with the runaway threshold to obtain the runaway threshold mapping relationship;

[0075] Step S403: Construct a thermal runaway prediction model based on at least one set of runaway threshold mapping relationships;

[0076] Step S404: Input the battery pack signal of the target vehicle to be analyzed into the thermal runaway prediction model to perform thermal runaway prediction on the target vehicle to be analyzed.

[0077] It should be noted that the battery pack model can be the model of the power battery from a vehicle with a history of thermal runaway. The aforementioned thermal runaway prediction model can be a data analysis model built based on a training set constructed from at least one set of runaway threshold mapping relationships.

[0078] Understandably, predictive devices obtain runaway thresholds for multiple battery models by performing voltage deviation analysis on one or more battery models, and establish a mapping relationship between each power battery model and its corresponding runaway threshold.

[0079] It should be understood that, in some embodiments, the prediction device trains a model based on the mapping relationship between each type of power battery and the corresponding runaway threshold obtained through pre-analysis, constructs a thermal runaway prediction model, and performs thermal runaway prediction through the thermal runaway prediction model.

[0080] This embodiment collects data on historical thermal runaway vehicles to obtain historical runaway data. Based on this data, voltage deviation analysis is performed on the historical thermal runaway vehicles. The runaway threshold of the historical thermal runaway vehicles is determined based on the voltage deviation analysis results. Based on the runaway threshold, thermal runaway prediction is performed on the target vehicle to be analyzed. Because this embodiment uses voltage deviation analysis on historical thermal runaway vehicles to identify the presence of abnormal outlier batteries in these vehicles, and determines the runaway threshold based on the analysis results, thermal runaway prediction is performed on the target vehicle to be analyzed based on the runaway threshold. This enables early prediction of thermal runaway of vehicle power batteries, improves the accuracy of thermal runaway prediction, and effectively enhances vehicle safety.

[0081] refer to Figure 3 , Figure 3 This is a flowchart illustrating a second embodiment of a vehicle thermal runaway prediction method according to the present invention.

[0082] Based on the first embodiment described above, in this embodiment, step S20 includes:

[0083] Step S21: Extract the voltage data of each individual cell in the battery pack of the historical thermal runaway vehicle from the historical runaway data.

[0084] It should be noted that the voltage data can be the voltage values ​​of each individual cell in the battery pack of a historical thermal runaway vehicle collected at different time points.

[0085] It is understood that in this embodiment, the prediction device sorts the collected historical runaway data according to the data collection time, and summarizes the voltage data of each individual cell in the battery pack based on the sorting results.

[0086] Step S22: Perform voltage deviation analysis on each individual cell based on the voltage data.

[0087] It is understood that the prediction device in this embodiment performs outlier analysis on voltage data to obtain the voltage outlier characteristic trend of a single cell.

[0088] Furthermore, in order to accurately perform voltage deviation analysis, step S22 above may include:

[0089] Step S221: Determine the voltage outlier of each individual cell based on the voltage data;

[0090] Step S222: Obtain the voltage acquisition time data of each individual battery cell based on the historical runaway data;

[0091] Step S223: Construct a voltage deviation analysis graph based on the voltage outlier and the voltage time data;

[0092] Step S224: Perform voltage deviation analysis on each individual cell based on the voltage deviation analysis diagram.

[0093] It should be noted that the voltage outlier can be the difference between a single cell voltage and a historical thermal runaway vehicle's single cell voltage reference value. The voltage outlier analysis chart mentioned above can be an analysis chart constructed based on voltage-time data, with the calculated voltage outliers arranged in chronological order. For example, the voltage outlier analysis chart can be a voltage outlier curve, as shown in the reference... Figure 4 , Figure 4 This is a schematic diagram of the voltage deviation curve, where the horizontal axis represents the voltage acquisition time and the vertical axis represents the battery voltage. The voltage-time data mentioned above can be the battery data acquisition time data.

[0094] It is understood that the prediction device in this embodiment extracts the voltage data of each individual battery cell based on historical runaway data, as well as the voltage acquisition time data of each individual battery cell. Based on the voltage data, it calculates the voltage outlier value of each individual battery cell, correlates the voltage outlier value with the voltage acquisition time data, generates a voltage deviation analysis chart based on the correlation correspondence of the voltage outlier value according to the time sequence, and performs voltage deviation analysis based on the voltage deviation analysis chart to obtain the trend of battery voltage outlier characteristics.

[0095] Furthermore, in order to accurately calculate the voltage outlier of each individual cell, step S221 above may include:

[0096] Step S2211: Obtain the voltage acquisition time data of each individual battery cell based on the historical runaway data;

[0097] Step S2212: Associate the voltage data with the voltage acquisition time data;

[0098] Step S2213: Construct the voltage-time matrix of the battery pack based on the correlation results;

[0099] Step S2214: Determine the voltage reference value of the battery pack based on the voltage-time matrix;

[0100] Step S2215: Determine the voltage outlier of each individual cell based on the voltage reference value and the voltage data.

[0101] It is understandable that the voltage-time matrix can be a data matrix constructed from the voltage of a single battery cell and the data acquisition time, as shown in the reference. Figure 5 , Figure 5 This is a schematic diagram of the voltage-time matrix.

[0102] It should be understood that the prediction device sorts the collected voltage data by acquisition time, and then sorts the individual battery cell voltages sequentially, forming a matrix of individual battery cell voltages and acquisition time. The corresponding individual battery cell voltages for the same day are then extracted and averaged to form a longitudinal average. This method can be used to obtain the daily longitudinal average for all batteries of that vehicle model. Figure 5 As shown, first calculate the average voltage of each cell within the rectangular area.

[0103] Understandably, the prediction device will recalculate the average daily voltage of each individual cell in the battery pack to obtain the baseline voltage A for that vehicle on that day. Then, it will compare the voltage of all individual cells with the baseline value A to calculate the voltage outlier, referring to Formula 1 below, where ΔVi is the voltage outlier and Vi is the voltage of the individual cell.

[0104] AVi = Vi - A Formula 1

[0105] This embodiment extracts the voltage data of each individual cell in the battery pack of the historical thermal runaway vehicle from the historical runaway data, and performs voltage deviation analysis on each individual cell based on the voltage data. Since this embodiment extracts the voltage data of each individual cell in the battery pack of the historical thermal runaway vehicle and performs voltage deviation analysis on each individual cell based on the voltage data, it can accurately analyze the voltage outlier trend of the vehicle battery.

[0106] refer to Figure 6 , Figure 6 This is a flowchart illustrating the third embodiment of a vehicle thermal runaway prediction method according to the present invention.

[0107] Based on the first embodiment described above, in this embodiment, step S10 includes:

[0108] Step S101: Send a data acquisition request to the on-board terminal of the historical thermal runaway vehicle, so that the on-board terminal can collect data from the historical thermal runaway vehicle based on the data acquisition frequency in the data acquisition request;

[0109] Step S102: Obtain the original data of the historical thermal runaway vehicles collected by the vehicle terminal;

[0110] Step S103: Process the raw data to obtain historical out-of-control data.

[0111] It should be noted that vehicles with a history of thermal runaway can be those that have previously experienced power battery thermal runaway faults. The predictive device collects historical runaway data of the power battery of these vehicles by sending data acquisition requests to them. The aforementioned raw data can include the power battery data and relevant vehicle operation data of the vehicles with historical thermal runaway, such as data acquisition time, vehicle VIN, vehicle operating status, total mileage, and voltage values ​​of individual power battery cells.

[0112] It is understood that the prediction device in this embodiment can identify vehicles that have previously experienced thermal runaway of the power battery (i.e., vehicles with historical thermal runaway) and send data acquisition requests to these vehicles. This allows the vehicles with historical thermal runaway to acquire data at the data acquisition frequency carried in the data acquisition request, for example, 0.1Hz. After acquiring the data, the vehicles with historical thermal runaway transmit the acquired real-time data to the prediction device via a preset method (e.g., HTTP). The prediction device receives the raw data and stores it in a storage medium.

[0113] Furthermore, in order to effectively process the raw data, step S103 above may include:

[0114] Step S1031: Parse the original data to obtain the data fields contained in the original data;

[0115] Step S1032: Classify the original data based on the data fields to obtain candidate data;

[0116] Step S1033: Perform data cleaning processing on the candidate data based on preset cleaning rules to obtain historical out-of-control data.

[0117] It is understandable that the data received by the prediction device from historical thermal runaway vehicles can be message data. Therefore, when the prediction device receives message data, it can store the message data and parse it when data analysis is needed, classifying and storing the parsed data fields. These mainly include data acquisition time, vehicle VIN, vehicle operating status, total mileage, and individual battery cell voltage values. The parsed and stored data is then cleaned using certain rules. The main rules include: removing invalid values, removing zero values, removing abnormal data (such as unequal sums of total voltage and individual cell voltages), and removing duplicate data.

[0118] This embodiment sends a data acquisition request to the onboard terminal of a vehicle with a history of thermal runaway. The onboard terminal then collects data from the vehicle based on the data acquisition frequency specified in the request, obtaining raw data from the vehicle. This raw data is then processed to obtain historical runaway data. Because this embodiment collects a large amount of raw vehicle battery data by sending data acquisition requests to the onboard terminal of the vehicle with a history of thermal runaway, and processes this raw data to obtain historical runaway data, data analysis efficiency is improved, and the influence of invalid and duplicate data is avoided.

[0119] Furthermore, this embodiment of the invention also proposes a storage medium storing a vehicle thermal runaway prediction program, which, when executed by a processor, implements the steps of the vehicle thermal runaway prediction method described above.

[0120] Since this storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought about by the technical solutions of the above embodiments, which will not be repeated here.

[0121] Reference Figure 7 , Figure 7 This is a structural block diagram of the first embodiment of the vehicle thermal runaway prediction device of the present invention.

[0122] like Figure 7 As shown, the vehicle thermal runaway prediction device proposed in this embodiment of the invention includes:

[0123] Data acquisition module 10 is used to collect data on historical thermal runaway vehicles and obtain historical runaway data;

[0124] The deviation analysis module 20 is used to perform voltage deviation analysis on the historical thermal runaway vehicle based on the historical runaway data;

[0125] The threshold acquisition module 30 is used to determine the runaway threshold of the historical thermal runaway vehicle based on the voltage deviation analysis results.

[0126] The runaway prediction module 40 is used to predict thermal runaway of the target vehicle to be analyzed based on the runaway threshold.

[0127] Furthermore, the deviation analysis module 20 is also used to extract the voltage data of each individual cell in the battery pack of the historical thermal runaway vehicle from the historical runaway data; and to perform voltage deviation analysis on each individual cell based on the voltage data.

[0128] Furthermore, the deviation analysis module 20 is also used to determine the voltage outlier of each individual cell based on the voltage data; obtain the voltage acquisition time data of each individual cell based on the historical runaway data; construct a voltage deviation analysis graph based on the voltage outlier and the voltage time data; and perform voltage deviation analysis on each individual cell based on the voltage deviation analysis graph.

[0129] Furthermore, the deviation analysis module 20 is also used to obtain the voltage acquisition time data of each individual battery cell based on the historical runaway data; correlate the voltage data with the voltage acquisition time data; construct the voltage-time matrix of the battery pack based on the correlation result; determine the voltage reference value of the battery pack based on the voltage-time matrix; and determine the voltage outlier value of each individual battery cell based on the voltage reference value and the voltage data.

[0130] Furthermore, the runaway prediction module 40 is also used to obtain the battery pack model of the historical thermal runaway vehicle; associate the battery pack model with the runaway threshold to obtain a runaway threshold mapping relationship; construct a thermal runaway prediction model based on at least one set of runaway threshold mapping relationships; and input the battery pack signal of the target vehicle to be analyzed into the thermal runaway prediction model to perform thermal runaway prediction on the target vehicle to be analyzed.

[0131] Furthermore, the data acquisition module 10 is also used to send a data acquisition request to the vehicle terminal of the historical thermal runaway vehicle, so that the vehicle terminal can collect data from the historical thermal runaway vehicle based on the data acquisition frequency in the data acquisition request; obtain the raw data of the historical thermal runaway vehicle collected by the vehicle terminal; and process the raw data to obtain historical runaway data.

[0132] Furthermore, the vehicle thermal runaway prediction device also includes:

[0133] The data processing module 50 is used to parse the raw data to obtain the data fields contained in the raw data; classify the raw data based on the data fields to obtain candidate data; and perform data cleaning processing on the candidate data based on preset cleaning rules to obtain historical out-of-control data.

[0134] This embodiment collects data on historical thermal runaway vehicles to obtain historical runaway data. Based on this data, voltage deviation analysis is performed on the historical thermal runaway vehicles. The runaway threshold of the historical thermal runaway vehicles is determined based on the voltage deviation analysis results. Based on the runaway threshold, thermal runaway prediction is performed on the target vehicle to be analyzed. Because this embodiment uses voltage deviation analysis on historical thermal runaway vehicles to identify the presence of abnormal outlier batteries in these vehicles, and determines the runaway threshold based on the analysis results, thermal runaway prediction is performed on the target vehicle to be analyzed based on the runaway threshold. This enables early prediction of thermal runaway of vehicle power batteries, improves the accuracy of thermal runaway prediction, and effectively enhances vehicle safety.

[0135] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0136] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0137] In addition, for technical details not described in detail in this embodiment, please refer to the vehicle thermal runaway prediction method provided in any embodiment of the present invention, which will not be repeated here.

[0138] Furthermore, it should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0139] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0140] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they 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. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0141] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for predicting vehicle thermal runaway, characterized in that, The vehicle thermal runaway prediction method includes: Data is collected from vehicles with historical thermal runaway to obtain historical runaway data, which includes data collection time, vehicle VIN, vehicle operating status, total mileage, and voltage value of individual power battery cells. Extract the voltage data of each individual cell in the battery pack of the historical thermal runaway vehicle from the historical runaway data; obtain the voltage acquisition time data of each individual cell based on the historical runaway data; The voltage data is correlated with the voltage acquisition time data; a voltage-time matrix of the battery pack is constructed based on the correlation result; and a voltage reference value of the battery pack is determined based on the voltage-time matrix. The voltage outlier of each individual cell is determined based on the voltage reference value and the voltage data; the voltage acquisition time data of each individual cell is obtained based on the historical runaway data; a voltage deviation analysis chart is constructed based on the voltage outlier and voltage time data; and voltage deviation analysis is performed on each individual cell based on the voltage deviation analysis chart. The runaway threshold of the historical thermal runaway vehicles was determined based on the voltage deviation analysis results. Thermal runaway prediction is performed on the target vehicle to be analyzed based on the runaway threshold.

2. The vehicle thermal runaway prediction method as described in claim 1, characterized in that, The process of predicting thermal runaway of the target vehicle to be analyzed based on the runaway threshold includes: Obtain the battery pack model of the historical thermal runaway vehicle; The battery pack model is associated with the runaway threshold to obtain the runaway threshold mapping relationship; Construct a thermal runaway prediction model based on at least one set of runaway threshold mapping relationships; The battery pack signal of the target vehicle to be analyzed is input into the thermal runaway prediction model to predict thermal runaway of the target vehicle.

3. The vehicle thermal runaway prediction method as described in claim 1, characterized in that, The process of collecting data on historical thermal runaway vehicles to obtain historical runaway data includes: Send a data acquisition request to the on-board terminal of a vehicle with a history of thermal runaway, so that the on-board terminal can collect data from the vehicle with a history of thermal runaway based on the data acquisition frequency in the data acquisition request; Obtain the raw data of the historical thermal runaway vehicles collected by the vehicle terminal; The raw data is processed to obtain historical out-of-control data.

4. The vehicle thermal runaway prediction method as described in claim 3, characterized in that, The process of processing the raw data to obtain historical out-of-control data includes: The original data is parsed to obtain the data fields contained in the original data; Based on the data fields, the original data is classified to obtain candidate data; The candidate data is cleaned based on preset cleaning rules to obtain historical out-of-control data.

5. A vehicle thermal runaway prediction device, characterized in that, The vehicle thermal runaway prediction device includes: The data acquisition module is used to collect data on historical thermal runaway vehicles and obtain historical runaway data, including data acquisition time, vehicle VIN, vehicle operating status, total mileage, and voltage value of individual power battery cells. The deviation analysis module is used to perform voltage deviation analysis on the historical thermal runaway vehicle based on the historical runaway data. Specifically, the deviation analysis module is used to extract the voltage data of each individual cell in the battery pack of the historical thermal runaway vehicle from the historical runaway data; and to obtain the voltage acquisition time data of each individual cell based on the historical runaway data. The voltage data is correlated with the voltage acquisition time data; a voltage-time matrix of the battery pack is constructed based on the correlation result; and a voltage reference value of the battery pack is determined based on the voltage-time matrix. The voltage outlier of each individual cell is determined based on the voltage reference value and the voltage data; the voltage acquisition time data of each individual cell is obtained based on the historical runaway data; a voltage deviation analysis chart is constructed based on the voltage outlier and voltage time data; and voltage deviation analysis is performed on each individual cell based on the voltage deviation analysis chart. The threshold acquisition module is used to determine the runaway threshold of the historical thermal runaway vehicle based on the voltage deviation analysis results. The runaway prediction module is used to predict thermal runaway of the target vehicle to be analyzed based on the runaway threshold.

6. A vehicle thermal runaway prediction device, characterized in that, The vehicle thermal runaway prediction device includes: a memory, a processor, and a vehicle thermal runaway prediction program stored in the memory and executable on the processor, the vehicle thermal runaway prediction program being configured to implement the vehicle thermal runaway prediction method as described in any one of claims 1 to 4.

7. A storage medium, characterized in that, The storage medium stores a vehicle thermal runaway prediction program, which, when executed by a processor, implements the vehicle thermal runaway prediction method as described in any one of claims 1 to 4.

Images