CN114779085A - Real-time battery thermal runaway detection method, system, device and medium - Google Patents
Real-time battery thermal runaway detection method, system, device and medium Download PDFInfo
- Publication number
- CN114779085A CN114779085A CN202210389094.0A CN202210389094A CN114779085A CN 114779085 A CN114779085 A CN 114779085A CN 202210389094 A CN202210389094 A CN 202210389094A CN 114779085 A CN114779085 A CN 114779085A
- Authority
- CN
- China
- Prior art keywords
- battery
- thermal runaway
- real
- data
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
Abstract
The invention discloses a real-time battery thermal runaway detection method, a system, a device and a storage medium, wherein the method comprises the following steps: collecting real-time data and historical data of a battery; processing the collected real-time data and historical data to obtain the thermal runaway characteristic of the battery; and processing the thermal runaway characteristics through a thermal runaway model to obtain thermal runaway early warning information. The method, the system, the device and the storage medium of the invention mainly combine the real-time data information and the historical data information of the battery, rely on the basic data of the battery, completely describe the working condition of the battery under the current state and the parameter change related to the internal thermal runaway, and achieve the effect of timely and accurately preventing the thermal runaway of the battery, thereby effectively ensuring the safety of the user in riding and storing the electric vehicle to a certain extent, simultaneously establishing a key characteristic image for the battery in time sequence and providing data guarantee for the follow-up research of other aspects of the battery.
Description
Technical Field
The application relates to the field of battery fault detection, in particular to real-time battery thermal runaway detection.
Background
As is well known, the lead-acid battery has gradually replaced the leading position in the field of electric vehicles by virtue of the advantages of high energy density, low self-discharge rate, high cost performance, quick charge, environmental protection and the like of the lithium battery. More and more users tend to select light and convenient lithium battery electric vehicles. Lithium batteries, while superior in many respects to lead acid batteries, are subject to improved safety monitoring. In recent years, lithium battery spontaneous combustion events have become commonplace. The popularization of new lithium battery energy is greatly influenced.
Aiming at the problems, the real-time identification of the thermal runaway risk of the battery is a very meaningful matter, so that the early warning information can be generated for the user in a targeted manner, the user can stop using the battery, and the battery is isolated in a safe place to wait for the related technical personnel to process, so as to prevent the occurrence of the following major fire accidents. At present, few methods are used for detecting the thermal runaway of the battery in real time, and related technologies and data layer information are less, but with the development of two-wheeled electric vehicles, under the support of a large amount of battery data, a plurality of intelligent technologies can be applied to the real-time monitoring of the thermal runaway of the battery.
Disclosure of Invention
In view of the above-mentioned drawbacks of the prior art, the technical problem to be solved by the present invention is how to actively and real-timely identify a thermal runaway risk battery. In order to reduce the probability of thermal runaway of a lithium battery of an electric vehicle, improve the safety of the electric vehicle and eliminate fire hazard, the invention aims to actively and real-timely identify a thermal runaway risk battery. Through the battery information reported in real time, whether the battery has the risk of thermal runaway or not is identified through an algorithm model, a user of the electric vehicle is reminded to realize accurate prevention and control of the thermal runaway through modes of taking out the battery in time or isolating the battery and the like, and therefore the probability of further occurrence of the battery spontaneous combustion is reduced; on the other hand, the property and personal safety of the user are also protected.
In order to achieve the purpose, the invention provides a real-time battery thermal runaway detection method, which comprises the following steps: collecting real-time data and historical data of a battery; processing the acquired real-time data and historical data to obtain the thermal runaway characteristic of the battery; and processing the thermal runaway characteristics through a thermal runaway model to obtain thermal runaway early warning information.
In a preferred embodiment of the present invention, the method further comprises: processing the thermal runaway characteristics through a thermal runaway model to obtain current characteristic data capable of reflecting the current state of the battery; updating the historical data using the current feature data; and periodically acquiring real-time data of the battery, and processing the data by combining with historical data updated in the last period to obtain the real-time thermal runaway characteristic of the battery.
In another preferred embodiment of the present invention, the method further comprises: according to the type of the battery, the thermal runaway characteristics are input into a thermal runaway model corresponding to the battery to be processed.
In another preferred embodiment of the present invention, the method further comprises: collecting a thermal runaway battery sample and a normal battery sample; and establishing a thermal runaway model based on the thermal runaway battery sample and the normal battery sample.
In another preferred embodiment of the present invention, the method further comprises: and performing corresponding operation according to the thermal runaway early warning information, wherein the thermal runaway early warning information comprises mark information capable of indicating whether the battery has a thermal runaway risk.
In another preferred embodiment of the present invention, the method further comprises: and if the thermal runaway early warning information indicates that the battery has a thermal runaway risk, sending an early warning notice to the terminal equipment using the battery.
In another preferred embodiment of the present invention, the real-time data includes external data reflecting an external environment of the battery.
In another preferred embodiment of the present invention, the electric vehicle is used for a two-wheeled electric vehicle or a four-wheeled electric vehicle.
The invention also provides a real-time battery thermal runaway detection system, which comprises: the data acquisition module is configured to be capable of acquiring real-time data and historical data of the battery; the data processing module is configured to process the acquired real-time data and historical data to obtain the thermal runaway characteristics of the battery; and the data processing module is configured to process the thermal runaway characteristics through the thermal runaway model to obtain the thermal runaway early warning information.
The invention also provides a real-time battery thermal runaway detection device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor is configured to be capable of implementing the steps of the real-time battery thermal runaway detection method when executing the computer program.
The invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, is capable of implementing the steps of the real-time battery thermal runaway detection method.
The invention relates to the fields of data mining, battery fault detection, real-time IOT equipment detection and the like, in particular to a method for establishing a data set mainly through real-time performance and historical states of a battery and early warning thermal runaway of the battery by utilizing an algorithm model.
The method, the system, the device and the storage medium provided by the invention at least have the following beneficial technical effects: the invention mainly combines the real-time data information and the historical data information of the battery, depends on the basic data of the battery, completely describes the working condition of the battery under the current state and the parameter change related to the internal thermal runaway, effectively improves the effect of timely and accurately preventing the thermal runaway of the battery, thereby effectively ensuring the safety of a user in riding and storing an electric vehicle to a certain extent, simultaneously establishing a key characteristic image for the battery on a time sequence and providing data guarantee for the subsequent study of other aspects of the battery.
The conception, the specific structure and the technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, the features and the effects of the present invention.
Drawings
Fig. 1 is a flowchart illustrating steps of a real-time battery thermal runaway detection method according to a preferred embodiment of the invention.
FIG. 2 is a flow chart of the algorithm for building a thermal runaway model according to a preferred embodiment of the invention.
Fig. 3 is an algorithm engineering link diagram of a preferred embodiment of the real-time battery thermal runaway detection method of the present invention.
FIG. 4 is a schematic diagram of a computer device, equipment or terminal according to a preferred embodiment of the present invention.
Detailed Description
The following embodiments of the present invention are provided by way of specific examples, and other advantages and effects of the present invention will be readily apparent to those skilled in the art from the disclosure herein. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
Some exemplary embodiments of the invention have been described for illustrative purposes, and it is to be understood that the invention may be practiced otherwise than as specifically described.
FIG. 1 is a flowchart illustrating the steps of a method for detecting thermal runaway of a real-time battery according to a preferred embodiment of the invention. Fig. 2 is an algorithm engineering link diagram of a preferred embodiment of the real-time battery thermal runaway detection method of the present invention.
As shown in fig. 1, a real-time battery thermal runaway detection method of the present invention may include the following steps:
and step S111 and step S112, collecting real-time data and historical data of the battery. In some embodiments, the terminal device using the battery (for example, an on-board system or a battery control module of the electric vehicle) periodically sends the data of the battery to the server at the sampling frequency of the heartbeat of the electric vehicle, the current last frame data of the battery can be used as real-time data, and the data smaller than the current time can be aggregated as historical data. In some embodiments, a terminal device using a battery transmits only real-time data of the battery to a server, and the server stores the received data as historical data of the battery in time series.
The real-time data may include internal data that can reflect the internal condition of the battery and external data that can reflect the external environment in which the battery is located. The internal data may include battery temperature, cell voltage, fault location, and the like, and the external data may include vehicle temperature, vehicle speed, and the like.
For one embodiment, the battery temperature may include a plurality of temperature values, such as a top temperature t1, a bottom temperature t2, a MOS transistor temperature t3, etc., which are sensed and collected by temperature sensors at different positions, respectively, and may be represented by [ t1, t2, t3 ]. The thermal runaway battery generally involves an increase in temperature, and in the case of 20 degrees celsius, there is a possibility of an increase to 80 degrees celsius. Excessive temperature can affect the stability of battery operation and increase the risk of thermal runaway of the battery.
A battery for an electric vehicle may include one or more cells, each cell having a respective voltage. Depending on the number of cells, the cell voltage may be represented by [ v1, v2, v3, v4, v5, … ]. The voltage of the cell may fluctuate within a certain range according to the battery material, and in some embodiments, the rated voltage of the lithium iron phosphate battery cell is 3.2v, while the cell voltage of the thermal runaway battery may decrease to 1.6 v. The stability of battery work can be influenced by the excessively high or excessively low voltage of the battery core, and the thermal runaway risk of the battery is increased.
As an example, the sampling frequency of the electric vehicle heartbeat sends data to the server periodically once every five minutes, i.e. every 5 minutes. Those skilled in the art will appreciate that different electric vehicles or batteries may be provided with a sampling frequency of less than or greater than 5 minutes depending on the situation. However, this way of uploading data periodically causes some information to be lost in the upload, and the failure bit can better record part of the lost information. For example: if one or more jumps or other temporary anomalies occur in the real-time current information during a sampling period and are recovered during sampling, such anomalies are not detected at the sampling frequency. In some embodiments, one or more fault bits may be set to record the abnormal conditions, for example, a certain fault bit may reflect whether the current value exceeds the rated current, the fault bit may record the abnormal conditions once the current value exceeds the rated current, and the corresponding abnormal conditions may be reflected according to the fault bit information. The fault bit can be represented using [ e1, e2, e3, e4, … ].
The vehicle temperature tc refers to the current real-time temperature of the electric vehicle using the battery, can reflect the temperature condition of the external environment where the battery is located, and can be sensed and acquired by using a temperature sensor installed on the electric vehicle. The difference between the vehicle temperature and the battery temperature can be detected by the vehicle temperature, and whether the change in the battery temperature is caused by the internal reaction of the battery can be analyzed or judged.
The vehicle speed v refers to the current real-time movement speed of the electric vehicle using the battery, and can be sensed and acquired by using a speed sensor installed in the electric vehicle. The change of the internal voltage of the battery under the condition of vehicle motion can be reflected by the vehicle speed.
As described above, in some embodiments, real-time data of a battery may be represented using [ t1, t2, t3, …, v1, v2, v3, …, e1, e2, e3, …, tc, v ].
In some embodiments, the history data of the battery may include data of a last frame of the battery history and flag bit data capable of reflecting a condition of the battery history over a period of time.
The data of the last frame of the history, i.e. the data of the last cycle of the acquired real-time data, may be represented in the following manner as an example:
historical last frame battery temperature: [ t _1, t _2, t _3 ];
cell voltage of the last frame of history: [ v _1, v _2, v _3, v _4, v _5, … ];
historical last frame failure bit: [ e _1, e _2, e _3, e _4, … ];
historical last frame vehicle temperature: t _ h;
historical last frame vehicle speed: v _ h.
In some embodiments, the condition of the battery over a historical period of time may be recorded by one or more flag bits. As an example, one or more of the following flag bits may be set:
battery temperature flag bit: [ tflag1, tflag2, tflag3], wherein the tflag1 is a variation characteristic corresponding to the battery temperature t1, and includes three values respectively corresponding to temperature abnormality, temperature variation abnormality, and temperature and outside abnormality. Similarly, tflag2 and tflag3 are variation characteristics corresponding to the battery temperatures t2 and t3, respectively.
Cell voltage flag bit: [ vflag1, vflag2, vflag3, … ], wherein the vflag1 is a variation characteristic corresponding to the voltage v1, and includes two values respectively corresponding to the cell voltage abnormality and the voltage variation abnormality. Similarly, the vflag2 and the vflag3 are corresponding variation characteristics of the cell voltages v2 and v3, respectively.
A fault flag bit: [ eflag1, eflag2, eflag3, … ], wherein the eflag1 is a change characteristic corresponding to the fault bit e1, and includes 1 number of values corresponding to the historical fault jump times. Similarly, the eflag2 and the eflag3 are respectively the corresponding change characteristics of the fault bits e2 and e 3.
Vehicle temperature flag: cflag, wherein cflag is the difference between the vehicle temperature tc and the previous temperature (i.e., the last frame of historical vehicle temperature t _ h).
Vehicle speed flag: and vflag, wherein vflag is a difference between the vehicle speed v and a previous vehicle speed (i.e., a historical last frame vehicle speed v _ h).
And step S120, processing the collected real-time data and historical data to obtain the thermal runaway characteristic of the battery. In some embodiments, data processing may be performed as follows:
under the condition of cold start of the battery, the flag bits of all historical data are 0, and the historical state bit is the current state bit. When the battery works for a period of time, aiming at a battery data packet uploaded in real time (which can comprise current time, cell voltage, battery temperature, fault codes, zone bits, vehicle temperature, vehicle speed and the like in real-time data and/or historical data), the cell voltage, the battery temperature and the fault codes in the battery real-time data are firstly combined with corresponding zone bits in the historical data so as to highlight main characteristics related to thermal runaway. Then, the real-time data of the battery is judged, and redundant, wrong or irregular data are removed, such as: data that is repeatedly uploaded due to faulty bits that do not correspond to temperature, voltage, and battery hardware being affected by the device or environment.
As an example, a specific way of operation is provided below:
for the battery temperature, taking t1 as an example, the value of the corresponding battery temperature flag bit tflag1 is:
wherein, TzIs the battery temperature threshold, TdThreshold value, T, for the variation of the battery temperature in a cyclesIs a threshold value for the difference between the battery temperature and the vehicle temperature. The thresholds are distinguished according to the 3sigma criterion (3 sigma criterion) of the battery material and the corresponding temperature change of the battery, and the data is obtained by detecting, analyzing and calculating a large number of thermal runaway battery samples.
If the battery temperature t1> Tz, the battery temperature is too high, an abnormal condition occurs, the first value tflag1[0] of the tflag1 is recorded as 1, otherwise, the tflag1[0] is recorded as 0, i.e., 1 represents abnormal, and 0 represents normal.
If the battery temperature changes abs (t1-t _1)>Td(abs represents absolute value), the battery temperature changes excessively and an abnormal situation occurs, the second value tflag1 of tflag1[1 ]]1 is added on the basis of the original value; otherwise normal, tflag1[1 ]]A is reduced on the basis of the original value by means of the pair tflag [1 ]]The decay of the value updates the history of the flag bit. And a, taking the reciprocal of the quotient of the average value of the difference value between the thermal runaway time of the thermal runaway battery and the corresponding temperature change time of the latest occurrence and the time interval of each frame of battery data (namely, the thermal runaway occurs after the time of how many frames passes after the corresponding temperature change). When the historical data is updated for one frame, if an abnormal condition occurs, the number of the frames is increased by 1; if it does not occurThe abnormal condition is attenuated to a, and the attenuation is up to 0.
If the difference abs (t1-tc) > Ts (abs represents an absolute value) between the battery temperature and the vehicle temperature is too large, the difference between the battery internal temperature and the external environment temperature becomes abnormal, and the third value tflag1[2] of the tflag1 is increased by 1 on the basis of the original value; otherwise, it is normal, the tflag1[2] reduces b based on the original value, and updates the historical data of the flag bit by attenuating the tflag [2] value. And b, taking the reciprocal of the quotient of the average value of the difference value between the thermal runaway time of the thermal runaway battery and the corresponding time with the excessive temperature difference of the last occurrence and the time interval of each frame of battery data (namely, the time of how many frames of thermal runaway occurs after the corresponding temperature difference is excessive). If the historical data is updated by one frame, increasing 1 if an abnormal condition occurs; if no abnormal condition occurs, the signal is attenuated by b until 0.
The 3sigma criterion is also called Laudea criterion, and is that a group of detection data is assumed to only contain random errors, the detection data is calculated to obtain standard deviation, an interval is determined according to a certain probability, the error exceeding the interval is considered not to belong to the random errors but to be coarse errors, and the data containing the errors are removed. In a normal distribution, σ represents a standard deviation, μ represents a mean value, and x ═ μ is a symmetry axis of an image. The 3 σ rule is that the probability of the numerical distribution in (μ - σ, μ + σ) is 0.6826, the probability of the numerical distribution in (μ -2 σ, μ +2 σ) is 0.9544, and the probability of the numerical distribution in (μ -3 σ, μ +3 σ) is 0.9974. It is considered that the values of Y are almost entirely concentrated in the (μ -3 σ, μ +3 σ) ] range, and the possibility of exceeding this range is less than 0.3%. The 3sigma criterion is based on the equal-precision repeated measurement of normal distribution, so that the interference or noise of singular data is difficult to meet the normal distribution. If the absolute value nui of the residual error of a certain measured value in a group of measured data is larger than 3sigma, the measured value is a bad value and should be removed. The 3sigma criterion exists because the probability of falling outside 3sigma is only 0.27% for a normally distributed random error, which is usually taken as the limit error, and it is less likely to occur in a limited number of measurements. The 3sigma criterion is the most common and simplest gross error criterion and is generally applied when the number of measurements is sufficiently large (n ≧ 30) or when n > 10 is used for coarse discrimination.
Other battery temperature flag bits tflag2, tflag3, etc. are adjusted in a similar manner as tflag 1.
For the cell voltage, taking v1 as an example, the value of the corresponding cell voltage flag vflag1 is:
wherein, VsIs a high threshold value of cell voltage, VdIs a low threshold value of cell voltage, VaIs a threshold value at which the cell voltage changes within one cycle. The thresholds are distinguished according to the 3sigma criterion (3 sigma criterion) of the battery material and the corresponding voltage variation of the battery, and the data is derived from the detection, analysis and calculation of a large number of thermal runaway battery samples.
If the cell voltage v1>VsOr v1<VdIf the cell voltage is too high or too low, an abnormal condition occurs, and a first value vflag1[ 0] of the vflag1]Recorded as 1, otherwise vflag1[0]A record of 0, i.e. 1 indicates abnormal, 0 indicates normal.
If the change abs of the cell voltage (v1-v _1)>Va(abs represents an absolute value), the cell voltage changes too much, an abnormal condition occurs, and the second value vflag1[1 ] of vflag1]1 is added on the basis of the original value; otherwise, it is the normal case, vflag1[1 ]]C is reduced on the basis of the original value by means of the value of vflag [1 ]]The decay of the value updates the history of the flag bit. And c, taking the reciprocal of the quotient of the average value of the difference value between the thermal runaway time of the thermal runaway battery and the corresponding voltage change time of the latest occurrence and the time interval of each frame of battery data (namely, the thermal runaway occurs after the time of how many frames passes after the corresponding voltage change occurs). Each history dataUpdating a frame, increasing by 1 if an abnormal condition occurs, and attenuating by c if no abnormal condition occurs.
Other cell voltage flag bits vflag2, vflag3, etc. are adjusted in a similar manner as vflag 1.
And (4) adding 1 to the fault flag bit according to the difference between the last fault bit and the current fault bit, and subtracting the parameter d on the original basis if the fault flag bit is the same as the last fault bit. Similarly, d is the reciprocal of the quotient of the average value of the difference between the time of thermal runaway of all thermal runaway batteries and the change time of the corresponding fault code occurring at the last time and the time interval of each frame of battery data.
Through the data processing, the thermal runaway characteristic can be further generated. In some embodiments, the flag bits of the battery temperature, the battery cell voltage, and the fault code corresponding to the battery temperature, the battery cell voltage, and the fault code in the historical data may be updated in real time according to data of the battery temperature, the battery cell voltage, and the fault code in the real-time data, so as to generate the flag bits of the battery cell voltage, the battery temperature, and the fault code in the real-time data, and then form a group of data capable of reflecting the thermal runaway characteristic together with the vehicle temperature, the vehicle speed, and the like, so as to facilitate subsequent input of the algorithm model for processing.
By comparing with the data of the thermal runaway battery characteristics in the previous period, the data of the thermal runaway battery characteristics in different situations can be found to have large differences, such as: the cell voltage differs by 2V, the temperatures of the upper top cover and the lower top cover differ by 8 ℃, and the like, and the risk-free or low-risk battery has relatively stable performance in the characteristics.
As an example, a specific way of operation is provided below:
analyzing the cell voltage, the battery temperature, the fault location, the vehicle temperature, the vehicle speed in the real-time data and the battery temperature zone bit, the cell voltage zone bit, the fault zone bit, the vehicle temperature zone bit and the vehicle speed zone bit in the historical data into the following characteristic forms so as to facilitate the input of an algorithm model:
feature＝[t1,t2,t3,…,v1,v2,v3,…,e1,e2,e3,…,tflag1_1,tflag2_2,…]
and S130, processing the thermal runaway characteristics through a thermal runaway model to obtain thermal runaway early warning information. And inputting the obtained thermal runaway characteristics into a thermal runaway model, performing calculation analysis on the input thermal runaway characteristics by the thermal runaway model, and further judging whether the battery has a risk of thermal runaway or not according to information output by the thermal runaway model.
In some embodiments, the thermal runaway signature may also be input to a thermal runaway model corresponding to the battery for processing, depending on the type of battery. Different types of battery discrimination data may be added before the thermal runaway signature is input into the thermal runaway model. That is, when the battery is processed, the types of the battery are firstly distinguished by the battery material, and the batteries of different materials may have large differences in the input characteristics, such as: the lithium iron phosphate battery and the ternary lithium battery have great difference in cell voltage, and the number and the rated voltage of the cells are obviously different.
As an embodiment, different thermal runaway models can be established according to different types of batteries, so that battery materials can be distinguished according to the codes of the batteries, and the processed thermal runaway characteristics feature is input into the corresponding thermal runaway model for processing.
The thermal runaway model processes the input thermal runaway characteristics, and can output corresponding thermal runaway early warning information for indicating whether the battery has a thermal runaway risk. In some embodiments, the thermal runaway warning message may be a binary flag bit to respectively mark whether the battery has a thermal runaway risk.
And step S140, performing corresponding operation on the battery according to the thermal runaway early warning information, wherein the thermal runaway early warning information comprises mark information capable of indicating whether the battery has a thermal runaway risk. If the battery is judged to have the risk of thermal runaway according to the thermal runaway early warning information output by the thermal runaway model, corresponding operations on the battery can be further triggered, for example: if the thermal runaway early warning information indicates that the battery has a thermal runaway risk, an early warning notice can be sent to the terminal equipment using the battery; sending a message to remind the user of paying attention; stopping the discharge of the battery in time; immediately or after a delay, turning off a battery switch or stopping the use of the electric vehicle; notifying the user of risks, processing methods and the like, wherein notification modes include but are not limited to APP message notification, telephone notification, short message notification, WeChat notification, APP state display and the like.
In some embodiments, the thermal runaway signature may be processed by a thermal runaway model to obtain current signature data that may reflect a current state of the battery; updating the historical data using the current feature data; and periodically acquiring real-time data of the battery, and processing the real-time data by combining with historical data updated in the last period to obtain the real-time thermal runaway characteristic of the battery.
The thermal runaway model processes the input thermal runaway characteristics, can output corresponding current characteristic data, and then further updates historical data by using the current characteristic data output this time so as to process and process data in the next period. In some embodiments, the current signature data may include all or a portion of the thermal runaway signature.
In some embodiments, new historical data of the current battery may be generated based on the input thermal runaway characteristics and the historical data, and stored in the hbase database, when the battery uploads real-time data in the next cycle, the updated historical data and the real-time data are combined into a current data packet to be uploaded, and the above operation steps are repeated to perform thermal runaway detection in the next cycle.
Specifically, the flag bits of the history data in feature may be combined with the cell voltage, the battery temperature, the fault bit, the vehicle temperature, and the vehicle speed in the real-time data to be used as new history data, and then stored as a main key according to the battery code to be used as the history data of the next input.
In some embodiments, a thermal runaway cell sample and a normal cell sample may be collected; and establishing a thermal runaway model based on the thermal runaway battery sample and the normal battery sample. A thermal runaway model can be established based on a thermal runaway battery sample and a normal battery sample by collecting and analyzing a case of thermal runaway of the electric vehicle. As an embodiment, a thermal runaway model may be established based on an RF classification algorithm by analyzing changes in cell voltage, battery temperature, battery fault code, electric vehicle external temperature, electric vehicle speed, etc., when a thermal runaway occurs in a sample case as characteristic data, wherein a time interval of historical data may be set to extend one month from a thermal runaway time onward.
In some embodiments, the last frame of data of the sample battery may be used as real-time data, and the data with time less than the real-time data may be aggregated as historical data, and the real-time data and the historical data of the sample battery may be processed in a similar manner as in step S120, so as to obtain the thermal runaway characteristic of the sample battery. Then, different marks are marked on the thermal runaway characteristics of the thermal runaway battery and the normal battery respectively, and the thermal runaway characteristics are used as training data to establish a thermal runaway model on the basis of an RF (radio frequency) classification algorithm.
The RF two-class algorithm (Random Forest algorithm) is a classifier that trains and predicts a sample by using a plurality of decision trees. It contains classifiers of multiple decision trees and the categories of its output are dependent on the mode of the categories output by the individual trees. The random forest is a flexible and easy-to-use machine learning algorithm, and even if no hyper-parameter tuning exists, a good result can be obtained under most conditions, so that the random forest can be used for classification and regression. And integrating all classification voting results in the random forest, and designating the category with the maximum voting times as final output.
The basic RF construction algorithm proceeds as follows:
(1) the number of training cases (samples) is represented by N, and the number of features is represented by M.
(2) Inputting a feature number m for determining a decision result of a node on a decision tree; where M should be much smaller than M.
(3) Sampling N times from N training cases (samples) in a mode of repeated sampling to form a training set (namely, bootstrap sampling), and using the cases (samples) which are not extracted as prediction to evaluate the error of the cases (samples).
(4) For each node, m features are randomly selected, and the decision for each node on the decision tree is determined based on these features. Based on the m features, the optimal splitting mode is calculated.
(5) Each tree will grow completely without pruning, which may be employed after a normal tree classifier is built).
FIG. 3 is a flow chart of the algorithm for building a thermal runaway model according to a preferred embodiment of the invention. As shown in fig. 3, in some embodiments, after the battery is labeled with the thermal runaway model, the battery labeled as having the thermal runaway risk may be recovered and added as a sample to the training data after the manual review to update the thermal runaway model.
In order to realize real-time monitoring of thermal runaway of the battery, the invention provides a prediction method based on the thermal runaway of the lithium battery based on understanding of real-time data of the lithium battery, namely, an algorithm model is established by collecting relevant characteristics such as voltage, temperature and fault codes uploaded by the lithium battery on an electric vehicle and the temperature and speed of the electric vehicle, and the monitoring is carried out in real time.
The invention mainly combines the real-time information and the historical information of the battery, depends on the basic data of the battery, completely describes the working condition of the battery under the current state and the parameter change related to the internal thermal runaway, and effectively improves the effect of timely and accurately preventing the thermal runaway of the battery, thereby effectively ensuring the safety of a user in riding and storing an electric vehicle to a certain extent, simultaneously establishing a key characteristic image for the battery on a time sequence, and providing data guarantee for the subsequent study of other aspects of the battery.
The battery thermal runaway detection method mainly uses the temperature, the voltage, the fault code and the vehicle related data of the battery as the original bottom layer characteristics of the battery, abstracts the characteristics reported by the battery in real time and a convergence of historical characteristics on the original bottom layer characteristics, and enables the battery to keep the long-time data characteristics by continuously updating the historical characteristics of the battery so that an algorithm model can more accurately predict the risk of the battery thermal runaway.
The technical scheme of the invention utilizes the real-time data and the historical characteristics of the battery to establish a battery related data set, and finishes real-time prevention on the safety of the battery in time sequence by continuously updating the historical state information of the battery; and combine some vehicle information, the supplementary battery state of judging can effectively promote the accuracy degree that detects.
The thermal runaway detection scheme of the four-wheel electric vehicle usually stores the related data of the battery in a storage module of the battery, has higher detection frequency and shorter detection period, can detect the thermal runaway in every second or several seconds, has larger communication data volume and has higher requirements on the hardware configuration of the battery and a server. Compared with a four-wheel electric vehicle, the battery of the two-wheel electric vehicle is lighter and is difficult to match with the battery with high configuration requirements, so that the detection scheme of the four-wheel electric vehicle is difficult to be applied to the two-wheel electric vehicle.
The thermal runaway detection scheme is generalized, does not depend on the historical information stored in the battery, and can be suitable for the thermal runaway detection of various batteries including two-wheel electric vehicles and four-wheel electric vehicles.
The technical solutions provided in the present application may be systems, methods, apparatuses, and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied therewith for causing a processor to implement various aspects of the present application.
In some embodiments, the present application further provides a computer apparatus, device or terminal, an internal structure of an embodiment of which may be as shown in fig. 4. The computer device, apparatus or terminal includes a processor, memory, network interface, display screen and input device connected by a system bus. The processor is used for providing calculation and control capability, and the memory comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program to run in the non-volatile storage medium. The network interface is used for communicating with an external terminal through network connection. The computer program is executed by a processor to implement the various methods, procedures, steps disclosed in the present application, or the processor executes the computer program to implement the functions of the respective modules or units in the embodiments disclosed in the present application. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell, an external keyboard, a touch pad or a mouse and the like.
Illustratively, a computer program may be partitioned into one or more modules or units that are stored in a memory and executable by a processor to implement aspects of the present application. These modules or units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of a computer program in an apparatus, device or terminal.
The device, apparatus or terminal may be a desktop computer, a notebook, a mobile electronic device, a palm computer, a cloud server or other computing devices. It will be appreciated by those skilled in the art that the configurations shown in the figures are block diagrams of only some of the configurations relevant to the present disclosure, and do not constitute limitations on the apparatus, devices or terminals to which the present disclosure may be applied, and that a particular apparatus, device or terminal may include more or less components than shown in the figures, or may combine certain components, or have a different arrangement of components.
The Processor may be a Central Processing Unit (CPU), other general-purpose or special-purpose Processor, a microprocessor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The processor is the control center of the above-mentioned apparatus, device or terminal, and connects the respective parts of the apparatus, device or terminal by using various interfaces and lines.
The memory may be used to store computer programs, modules and data, and the processor may implement various functions of the apparatus, device or terminal by executing or executing the computer programs and/or modules stored in the memory and calling the data stored in the memory. The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the data storage area may store various types of data (such as multimedia data, documents, operation histories, etc.) created according to the application, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), a magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the above method. It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The above-described apparatus or terminal device integrated modules and units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer-readable storage medium. Based on such understanding, the present application can realize all or part of the flow of the disclosed methods, and can also be realized by a computer program for instructing relevant hardware to complete, the computer program can be stored in a computer readable storage medium, and the computer program can realize the steps of the above methods when being executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic diskette, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signal, telecommunications signal, software distribution medium, etc. It should be noted that the computer readable medium may contain content that is appropriately increased or decreased as required by legislation and patent practice in the jurisdiction.
In some embodiments, the various methods, procedures, modules, apparatuses, devices, or systems disclosed herein may be implemented or performed in one or more processing devices (e.g., digital processors, analog processors, digital circuits designed to process information, analog circuits designed to process information, state machines, computing devices, computers, and/or other mechanisms for electronically processing information). The one or more processing devices may include one or more devices that perform some or all of the operations of a method in response to instructions stored electronically on an electronic storage medium. The one or more processing devices may include one or more devices configured through hardware, firmware, and/or software to be specifically designed for performing one or more operations of a method. The above description is only for the preferred embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art should be considered as the technical solutions and the inventive concepts of the present application in the scope of the present application.
Embodiments of the present application may be implemented in hardware, firmware, software, or various combinations thereof, and may also be implemented as instructions stored on a machine-readable medium, which may be read and executed using one or more processing devices. In some implementations, a machine-readable medium may include various mechanisms for storing and/or transmitting information in a form readable by a machine (e.g., a computing device). For example, a machine-readable storage medium may include read-only memory, random-access memory, magnetic disk storage media, optical storage media, flash-memory devices, and other media for storing information, and a machine-readable transmission medium may include various forms of propagated signals (including carrier waves, infrared signals, digital signals), and other media for transmitting information. While firmware, software, routines, or instructions may be described in the above disclosure in terms of performing certain exemplary aspects and embodiments of certain actions, it will be apparent that such descriptions are merely for convenience and that such actions in fact result from a machine device, computing device, processing device, processor, controller, or other device or machine executing the firmware, software, routines, or instructions.
In the claims and specification of the present application, a module for performing a specified function or a module described using a functional feature is intended to cover any means capable of performing the function, for example: combinations of circuit elements performing the functions, software, hardware, and combinations of software and hardware to perform or implement the functions, or any form of software, firmware, code or combination thereof with appropriate circuitry or other means. The functions provided by the various modules are combined together in the manner claimed and it should thus be considered that any module, component, element which may provide such functions is equivalent or equivalent to the module defined in the claims. According to the principle of equivalent transformation of the circuit, the circuit structure of some embodiments in the present application may also be changed or modified, for example: the current source is converted to a voltage source, the series structure is converted to a parallel structure, and the like, thereby obtaining more diversified embodiments, but all of the changes and modifications belong to the scope disclosed in the present application.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Those skilled in the art can modify or change the above-described embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which may be made by those skilled in the art without departing from the spirit and scope of the present invention as defined in the appended claims.
Claims (11)
1. A real-time battery thermal runaway detection method is characterized by comprising the following steps:
collecting real-time data and historical data of a battery;
processing the collected real-time data and the historical data to obtain the thermal runaway characteristic of the battery; and
and processing the thermal runaway characteristics through a thermal runaway model to obtain thermal runaway early warning information.
2. The real-time battery thermal runaway detection method of claim 1, further comprising:
processing the thermal runaway characteristics through the thermal runaway model to obtain current characteristic data capable of reflecting the current state of the battery;
updating the historical data using the current feature data; and
and periodically collecting the real-time data of the battery, and processing the real-time data by combining with the historical data updated in the last period to obtain the real-time thermal runaway characteristic of the battery.
3. The real-time battery thermal runaway detection method of claim 1, further comprising:
and inputting the thermal runaway characteristics into the thermal runaway model corresponding to the battery for processing according to the type of the battery.
4. The real-time battery thermal runaway detection method of claim 1, further comprising:
collecting a thermal runaway battery sample and a normal battery sample; and
and establishing the thermal runaway model based on the thermal runaway battery sample and the normal battery sample.
5. The real-time battery thermal runaway detection method of claim 1, further comprising:
and performing corresponding operation according to the thermal runaway early warning information, wherein the thermal runaway early warning information comprises mark information capable of indicating whether the battery has a thermal runaway risk.
6. The real-time battery thermal runaway detection method of claim 5, further comprising:
and if the thermal runaway early warning information indicates that the battery has a thermal runaway risk, sending an early warning notice to the terminal equipment using the battery.
7. The real-time battery thermal runaway detection method according to claim 1, wherein:
the real-time data includes external data that reflects an external environment in which the battery is located.
8. The real-time battery thermal runaway detection method of claim 1, wherein:
the electric vehicle is used for two-wheeled electric vehicles or four-wheeled electric vehicles.
9. A real-time battery thermal runaway detection system, comprising:
a data acquisition module configured to enable acquisition of real-time data and historical data of a battery;
a data processing module configured to process the collected real-time data and the historical data to obtain a thermal runaway characteristic of the battery; and
a data processing module configured to process the thermal runaway features through a thermal runaway model to derive thermal runaway warning information.
10. A real-time battery thermal runaway detection apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the steps of the real-time battery thermal runaway detection method according to any one of claims 1 to 8 when the computer program is executed.
11. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, is able to carry out the steps of the method for real-time thermal runaway detection for a battery according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210389094.0A CN114779085A (en) | 2022-04-13 | 2022-04-13 | Real-time battery thermal runaway detection method, system, device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210389094.0A CN114779085A (en) | 2022-04-13 | 2022-04-13 | Real-time battery thermal runaway detection method, system, device and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114779085A true CN114779085A (en) | 2022-07-22 |
Family
ID=82429533
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210389094.0A Pending CN114779085A (en) | 2022-04-13 | 2022-04-13 | Real-time battery thermal runaway detection method, system, device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114779085A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115015768A (en) * | 2022-08-10 | 2022-09-06 | 力高(山东)新能源技术有限公司 | Method for predicting abnormal battery cell of battery pack |
| CN115782584A (en) * | 2022-11-22 | 2023-03-14 | 重庆长安新能源汽车科技有限公司 | New energy vehicle safety state determination method, system, equipment and medium |
| CN115817177A (en) * | 2022-10-11 | 2023-03-21 | 宁德时代新能源科技股份有限公司 | Battery thermal runaway prediction method and device, computer equipment and storage medium |
-
2022
- 2022-04-13 CN CN202210389094.0A patent/CN114779085A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115015768A (en) * | 2022-08-10 | 2022-09-06 | 力高(山东)新能源技术有限公司 | Method for predicting abnormal battery cell of battery pack |
| CN115015768B (en) * | 2022-08-10 | 2022-11-11 | 力高(山东)新能源技术股份有限公司 | Method for predicting abnormal battery cell of battery pack |
| CN115817177A (en) * | 2022-10-11 | 2023-03-21 | 宁德时代新能源科技股份有限公司 | Battery thermal runaway prediction method and device, computer equipment and storage medium |
| CN115782584A (en) * | 2022-11-22 | 2023-03-14 | 重庆长安新能源汽车科技有限公司 | New energy vehicle safety state determination method, system, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114779085A (en) | Real-time battery thermal runaway detection method, system, device and medium | |
| Wang et al. | A data-driven method for battery charging capacity abnormality diagnosis in electric vehicle applications | |
| Wang et al. | Voltage fault diagnosis and prognosis of battery systems based on entropy and Z-score for electric vehicles | |
| CN108198408B (en) | Self-adaptive anti-electricity-stealing monitoring method and system based on electricity information acquisition system | |
| EP3648433B1 (en) | System and method of training behavior labeling model | |
| CN111832974A (en) | Vehicle fault early warning method and storage medium | |
| CN112883645A (en) | Single battery voltage inconsistency fault prediction method and device and server | |
| CN113310647A (en) | Method and device for detecting leakage of battery pack, electronic equipment and storage medium | |
| CN115796708B (en) | Big data intelligent quality inspection method, system and medium for engineering construction | |
| CN114487856A (en) | Thermal runaway early warning method and system for battery replacement station | |
| CN115186502A (en) | Vehicle abnormal data identification method and device, electronic device and storage medium | |
| Hong et al. | Voltage fault precaution and safety management of lithium-ion batteries based on entropy for electric vehicles | |
| CN112149908A (en) | Vehicle driving prediction method, system, computer device and readable storage medium | |
| CN117067920B (en) | Fault detection method and device of power battery, electronic equipment and electric automobile | |
| CN117067921B (en) | Fault detection method of electric automobile and electric automobile | |
| CN113705074A (en) | Chemical accident risk prediction method and device | |
| CN117035563A (en) | Product quality safety risk monitoring method, device, monitoring system and medium | |
| CN112530049A (en) | Battery state monitoring method and device, electronic equipment and storage medium | |
| Li et al. | Multi-dimension statistical analysis and selection of safety-representing features for battery pack in real-world electric vehicles | |
| CN115980585A (en) | Battery fault detection method and device, computer equipment and storage medium | |
| Zhang et al. | Battery leakage fault diagnosis based on multi-modality multi-classifier fusion decision algorithm | |
| Wang et al. | A double-layer fault diagnosis strategy for electric vehicle batteries based on Gaussian mixture model | |
| CN115508713A (en) | Battery system safety early warning method and device, storage medium and equipment | |
| CN115184808A (en) | Battery thermal runaway risk detection method, device, equipment and computer storage medium | |
| CN114839554A (en) | Battery alarm method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |