CN113013514A - Thermal runaway gas-sensitive alarm device of vehicle-mounted lithium ion power battery and detection method thereof - Google Patents
Thermal runaway gas-sensitive alarm device of vehicle-mounted lithium ion power battery and detection method thereof Download PDFInfo
- Publication number
- CN113013514A CN113013514A CN202110208652.4A CN202110208652A CN113013514A CN 113013514 A CN113013514 A CN 113013514A CN 202110208652 A CN202110208652 A CN 202110208652A CN 113013514 A CN113013514 A CN 113013514A
- Authority
- CN
- China
- Prior art keywords
- battery
- thermal runaway
- state
- gas
- vehicle
- 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.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/48—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/425—Structural combination with electronic components, e.g. electronic circuits integrated to the outside of the casing
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/48—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte
- H01M10/486—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte for measuring temperature
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Abstract
The invention discloses a thermal runaway gas-sensitive alarm device of a vehicle-mounted lithium ion power battery, which comprises: a box body; the battery pack modules are arranged in the box body at intervals, the battery monomers are uniformly arranged in the battery pack modules, and cooling flow field channels are formed among the battery pack modules; the gas sensor is arranged at the outlet position of the cooling flow field channel; the thermocouple temperature sensors are uniformly arranged inside the battery pack modules; the mass sensors are correspondingly arranged at the lower parts of the battery monomers one by one; the management device is connected with the gas sensor, the thermocouple temperature sensors and the mass sensors. The invention also discloses a detection method of the thermal runaway gas-sensitive alarm device of the vehicle-mounted lithium ion power battery, which judges the probability of thermal runaway of the battery by establishing a Markov chain prediction model, and adopts cooling measures for the battery and reminds drivers and passengers.
Description
Technical Field
The invention relates to the technical field of lithium ion battery safety, in particular to a thermal runaway gas-sensitive alarm device of a vehicle-mounted lithium ion power battery and a detection method thereof.
Background
Lithium ion batteries have become the mainstream choice for automotive power batteries due to their advantages of high capacity, high output voltage, high charging rate, high energy density, low self-discharge, and excellent cycle characteristics. However, the high activity of the electrode material and the flammability of the electrolyte material determine that the lithium ion battery always has the risk of thermal runaway. In recent years, with the increase of the market reserves of electric vehicles and the improvement of the power performance of the electric vehicles, severe safety accidents caused by thermal runaway of vehicle-mounted lithium ion power batteries are frequent, and the confidence of consumers on the electric vehicles is seriously struck.
In the case of a cell formed of a laminated wound material, even when the lithium ion battery is used in a completely normal state, the cell is structurally damaged by residual stress generated at the interface by carriers with every charge and discharge. Structural damage at the interface can cause uneven deposition of carriers, resulting in dendrite generation. The SEI passivation film covering the electrode surface is an important measure to prevent dendrite-induced destructive side reactions. Studies have shown that SEI passivation films decompose under thermal abuse, resulting in side reactions that continue to move in the positive direction. The generated gas and heat effect can aggravate the thermal damage degree of the battery structure, so that the scale of the side reaction exceeds a threshold value, and a bistable system of the battery is guided to irreversible thermal runaway. Research shows that during normal operation of the battery, the battery has no substance exchange with the outside and no gas is generated. Therefore, the gas generated by these side reactions can be used as a measurable physical characteristic for measuring the degree of thermal damage of the cell, so as to evaluate the risk of thermal runaway of the monomer.
The thermal damage of the battery can be classified into reversible and irreversible. Studies have shown that the occurrence of thermal runaway is highly correlated with internal short circuits caused by the battery, and irreversible damage to the internal structure of the battery becomes a direct cause of the occurrence of internal short circuits. In the practical use of the electric vehicle, the process from the occurrence of thermal damage to the occurrence of thermal runaway of the battery cell is a gradual process. In the initial stage of the occurrence of thermal damage, due to the structural characteristics of the battery itself, as the main output external parameters of the battery, the temperature and the voltage are not changed obviously, and the length of the period of time is greatly related to the triggering mode of the thermal damage, but the lag in the period of time is ubiquitous. This provides a time window for the intervention of engineering means, making active protection against thermal runaway possible. And enlarging the time window as much as possible becomes the key to success of the engineering means intervention.
The thermal runaway is a severe side reaction of an electrolyte essentially, the concentration of free radicals in the battery has a decisive influence on the final trend of the side reaction, if the concentration of the free radicals in the battery can be quickly reduced, namely, the electrolyte is quickly inactivated, the spread of the side reaction in the battery can be effectively blocked, the reaction scale of the battery is controlled, the system is prevented from leading to a thermal runaway state due to the breakthrough of a threshold value, and the active safety intervention on the thermal runaway is realized. Meanwhile, since the thermal effect and the voltage floating are the most remarkable characteristics of the battery side reaction, the voltage fluctuation or the thermal signal is the main triggering means of the existing thermal runaway alarm system. However, the thermal runaway early warning method based on the single external parameter representation has high false alarm and missing report probability and early warning time lag, so that the intervention window of subsequent active safety measures is too small, and the effect is weak.
And as the working substance of the forced fire extinguishing system, the thermal runaway blocking agent represented by the chlorofluoroalkane can quickly exhaust the free radicals of the thermal runaway monomers and simultaneously can also scrap other intact battery monomers in the same module due to the loss of chemical activity.
Disclosure of Invention
The invention aims to design and develop a thermal runaway gas-sensitive alarm device of a vehicle-mounted lithium ion power battery, which can monitor whether the power battery is damaged and the damage degree thereof in real time under the working state by acquiring the changes of gas concentration, battery monomer temperature and battery monomer quality in a battery pack module and sending the changes to a BMS upper computer, thereby improving the early warning and intervention time of thermal runaway.
The invention also aims to design and develop a detection method of the thermal runaway gas-sensitive alarm device of the vehicle-mounted lithium ion power battery, which judges the probability of thermal runaway of the battery by establishing a Markov chain prediction model, adopts cooling measures for the battery and reminds drivers and passengers, thereby realizing quantitative prediction of the risk of thermal runaway.
The technical scheme provided by the invention is as follows:
a thermal runaway gas-sensitive alarm device of a vehicle-mounted lithium ion power battery comprises:
a box body; and
the battery pack modules are arranged inside the box body at intervals, the battery cells are uniformly arranged inside the battery pack modules, and cooling flow field channels are formed among the battery pack modules;
the gas sensor is arranged at the outlet position of the cooling flow field channel;
a plurality of thermocouple temperature sensors uniformly arranged inside the plurality of battery pack modules;
the mass sensors are arranged at the lower parts of the battery cells in a one-to-one correspondence manner;
and the management device is connected with the gas sensor, the thermocouple temperature sensors and the mass sensors and is used for receiving signals and transmitting commands.
Preferably, the management device includes:
a signal transmission assembly connected with the gas sensor, the plurality of thermocouple temperature sensors and the plurality of mass sensors;
the single chip microcomputer is connected with the signal transmission assembly;
and the BMS upper computer is connected with the singlechip and is used for receiving signals and transmitting commands.
Preferably, the method further comprises the following steps:
the current/voltage signal collectors are connected with the single batteries in a one-to-one correspondence mode and used for monitoring the output current and the output voltage of the single batteries;
a solid state particle detector disposed on one side of the gas sensor;
wherein the plurality of current/voltage signal collectors and the solid state particle detector are both connected to the signal transmission assembly.
A detection method of a thermal runaway gas-sensitive alarm device of a vehicle-mounted lithium ion power battery comprises the following steps:
step one, according to a sampling period, collecting the concentration of carbon monoxide characteristic gas in a box body, the temperature in a plurality of battery pack modules and the mass loss percentage of a battery monomer, and constructing a battery state characterization matrix:
Ω＝(Q,T,Δm)T；
in the formula, Q is a concentration vector of carbon monoxide characteristic gas in the box body, T is a temperature vector of each monitoring point in the battery pack module, and Δ m is mass loss percentage of each battery monomer;
step two, the battery state data is processed according to the following steps of 1: 1, randomly dividing the proportion into a training set and a testing set, carrying out statistics on the appeared battery state representation matrix on the training set according to a time sequence principle to obtain a state space of the battery, establishing a Markov chain prediction model, and obtaining a state transition matrix:
in the formula (II)
For the battery from state omegaiTransition to state ΩjAm (a)Rate, i ═ 1,2, … N, j ═ 1,2, … N, N is the unique number of states of the battery;
step three, predicting the battery state [ omega ] of each battery state in the test set in the next three sampling periods by means of the established effective Markov chain modelt+T,Ωt+2T,Ωt+3T]T is the current time tag, and T is the sampling period;
inputting the battery states, the Markov chain validity and the SOC value of the battery in the next three sampling periods into a BP neural network model to obtain the stage grade of the thermal runaway of the battery;
and step five, judging the probability of the thermal runaway of the battery according to the stage grade of the thermal runaway of the battery, and adopting a cooling measure for the battery and reminding drivers and passengers.
Preferably, the battery is driven from state ΩiTransition to state ΩjThe probability of (c) satisfies:
in the formula (I), the compound is shown in the specification,
for the state transition omega of the battery under the actual measurement experimentiTo state omegajThe number of times that this occurs is,
for the battery state omega under the actual measurement experimentiTotal number of occurrences.
Preferably, the process of determining whether the markov chain model is valid is as follows:
and predicting the battery state of each battery state in the test set in a future sampling period according to the state transition matrix, comparing a prediction result with a real state, if the effectiveness of the Markov chain is more than 90%, proving that the Markov chain prediction model is effective, and otherwise, reestablishing the Markov chain prediction model.
Preferably, the markov chain validity satisfies:
in the formula, K is the accurate number of the prediction results, and K is the number of the states of all the test sets.
Preferably, the SOC value of the battery is obtained through real-time current/voltage signal query after acquiring a battery SOC-OCV curve based on an offline bench test.
Preferably, the calculation process of the BP neural network model is as follows:
step 1, determining an input layer neuron vector x ═ x of a three-layer BP neural network1,x2,x3,x4,x5}; wherein x is1Is in a battery state omegat+T，x2Is in a battery state omegat+2T，x3Is in a battery state omegat+3T，x4For Markov chain validity f, x5Is the SOC value of the battery;
step 2, the vector of the input layer is mapped to a hidden layer, the number of hidden layer neurons is h, and
in the formula, m is the number of input nodes, n is the number of output nodes, and a is an adjusting factor;
step 3, obtaining an output layer neuron vector o ═ o1,o2}；o1Is a battery thermal runaway risk level, o2Is o1The reliability of the prediction result;
wherein the content of the first and second substances,
0 is zero-order risk which indicates that the battery is normal, 1 is first-order risk which indicates that the single battery possibly has thermal runaway and needs to continuously monitor the battery, 2 is second-order risk which indicates that the single battery has thermal runaway and needs to be cooled, and 3 is third-order risk which indicates that the thermal runaway of the battery pack module occurs。
Preferably, the step five specifically includes:
when o 10 and o2When the temperature is more than or equal to 90 percent, the battery has no probability of thermal runaway;
when o11 and o2When the temperature of the battery is more than or equal to 80%, the probability of thermal runaway of the battery is less than 50%, and the monomer of the battery needs to be cooled;
when o12 and o2When the temperature of the battery pack is more than or equal to 70%, the probability of thermal runaway of the battery is more than 50%, and the battery pack module needs to be cooled;
when o13 and o2And when the temperature is more than or equal to 60 percent, the battery pack module generates thermal runaway and needs to remind drivers and passengers to avoid danger in time and send out an alarm sound.
The invention has the following beneficial effects:
(1) the gas-sensitive sensor adopted by the thermal runaway gas-sensitive alarm device for the vehicle-mounted lithium ion power battery is a patch type electric signal sensor, has small volume and low cost, does not depend on an external power supply, can be directly integrated into a battery pack module in the packaging process, does not depend on the output of an external signal of a battery pack, and is slightly influenced by external factors; different from the traditional photosensitive detection equipment, the battery pack module does not depend on upper computer detection equipment, and can realize real-time monitoring of gas components in the battery pack module.
(2) The thermal runaway gas-sensitive alarm device for the vehicle-mounted lithium ion power battery, which is designed and developed by the invention, can carry out cooperative measurement on various thermal runaway precursor characterization physical quantities, can effectively avoid misinformation and missing report of a BMS (battery management system), can remarkably advance early warning time by introducing a gas-sensitive signal, and improves the overall safety performance of an electric vehicle;
(3) the invention designs and develops a detection method of a thermal runaway gas-sensitive alarm device of a vehicle-mounted lithium ion power battery, which solves the technical problem of accurately evaluating the thermal runaway risk of a vehicle-mounted lithium ion power battery monomer under a dynamic working condition, so that the thermal runaway risk can be predicted by undetected quantification, and timely early warning for a driver is realized on the basis of the prediction; risk of thermal runaway occurrence is quantified through the system, so that the BMS can more accurately identify potential threats and evaluate the degree of the potential threats, and the effectiveness of intervention measures is greatly improved.
(4) The invention relates to a detection method of a thermal runaway gas-sensitive alarm device of a vehicle-mounted lithium ion power battery, which is matched with a safety solution of a vehicle-mounted BMS system, is a safety submodule specially developed based on the safety requirements of an electric vehicle, is different from the existing safety measures developed for an energy storage power station, emphasizes the compatibility with the existing control software of the electric vehicle, and gives consideration to the internal structure layout and the dynamic requirements of the electric vehicle.
Drawings
Fig. 1 is a schematic view of an assembly structure of a battery pack module in a system according to the present invention.
Fig. 2 is a schematic diagram of the safe working range and thermal runaway characterization of the lithium battery of the present invention.
FIG. 3 is a schematic diagram of the variation of the mass of the monomer under different SOC conditions at each thermal runaway stage according to the present invention.
Fig. 4 is a schematic diagram of the relationship between the overall heat release of the battery and the number of cells in different pressure environments according to the present invention.
Fig. 5 is a schematic diagram of the variation of the pressure inside the battery according to the present invention as the temperature of the cell surface increases.
Fig. 6 is a schematic diagram of the arrangement of various sensors in a battery according to the present invention.
Fig. 7 is an architecture diagram of an evaluation model of the battery thermal runaway early warning system according to the invention.
Fig. 8 is a schematic diagram of a physical architecture of a mechanism layer of the battery thermal runaway early warning system according to the invention.
Detailed Description
The present invention is described in further detail below in order to enable those skilled in the art to practice the invention with reference to the description.
The invention aims to design a vehicle-mounted lithium ion power battery thermal runaway early warning device and a detection method thereof based on a gas sensor passage (gas signal, gas pressure and gas concentration), a temperature sensor (temperature signal) and a mass sensor (mass change signal) and a thermal runaway probability evaluation model combining machine learning and big data analysis, so that the technical problem of accurately evaluating the thermal runaway risk of a vehicle-mounted lithium ion power battery monomer under a dynamic working condition is solved, the thermal runaway risk is predicted by an undetected quantity, and timely early warning for a driver is realized on the basis of the thermal runaway risk.
As shown in fig. 1, the thermal runaway gas sensitive alarm device for a vehicle-mounted lithium ion power battery provided by the invention comprises: the battery pack structure comprises a box body 100, a first battery pack module 111, a second battery pack module 112, a third battery pack module 113 and a fourth battery pack module 114, wherein the first battery pack module 111, the second battery pack module 112, the third battery pack module 113 and the fourth battery pack module 114 are arranged inside the box body 100 at intervals, battery monomers 120 which are uniformly arranged are arranged inside the first battery pack module 111, the second battery pack module 112, the third battery pack module 113 and the fourth battery pack module 114, and a cooling flow field channel is arranged among the first battery pack module 111, the second battery pack module 112, the third battery pack module 113 and the fourth battery pack module 114; the cooling flow field channel includes a cooling inlet channel 131 and a heat dissipation outlet channel 132.
As shown in fig. 2, before thermal runaway occurs, internal structural damage of the battery must reach a certain degree. With the approach of thermal runaway, internal damage is continuously enlarged, and then a larger-scale side reaction is triggered, and finally the thermal runaway is developed to an irreversible degree. For a lithium ion battery with a perfect structure, the electrolyte in the battery core does not participate in chemical reaction, and no matter exchange occurs with the outside of the system under the working state. When the lithium ion battery is damaged, no matter how small the damage is, the electrolyte in the core is subjected to oxidation reaction, and the oxidation product of the oxidation reaction exchanges substances and energy with the outside in the form of gas and heat. As shown in fig. 3-5, when the pressure relief valve located at the top cover of the battery communicates the environment inside and outside the battery due to the increase in the internal pressure of the battery, three direct consequences result: the method comprises the following steps of increasing the pressure in a battery pack, changing the gas components, reducing the mass of a battery monomer, releasing the heat of the battery monomer and increasing the surface temperature, wherein the main components of the gas comprise water, carbon monoxide, carbon dioxide and a small amount of organic vapor, wherein the carbon dioxide is the main component of the gas product, and the characteristic components are carbon monoxide and hydrofluoric acid vapor.
In view of the above, through to above three physical quantity, characteristic gas abundance, battery monomer mass loss proportion and battery surface temperature, monitor the disturbance of battery module internal environment state, and then under the condition that does not rely on the external parameter output of battery, judge whether there is the emergence and the emergence degree of electrolyte decomposition condition, realize carrying out real-time supervision to damage and damage degree whether appear in power battery under operating condition.
As shown in fig. 1 and 6, the present invention relates to a method for arranging sensors in units of independently packaged battery pack modules that are cooled by air cooling, including: the gas sensor 140 is arranged at the outlet of the heat dissipation gas outlet channel 132, and the air flow in the air cooling channel is used as a carrier gas for the gas generated by the battery, so that the generated gas is conveyed to the gas sensor 140; the thermocouple temperature sensors 150 are uniformly arranged inside the first battery pack module 111, the second battery pack module 112, the third battery pack module 113 and the fourth battery pack module 114, and are used for detecting temperature field distribution inside the first battery pack module 111, the second battery pack module 112, the third battery pack module 113 and the fourth battery pack module 114; the mass sensors 160 are arranged at the lower parts of the battery cells 120 in a one-to-one correspondence manner, and are used for detecting the mass loss condition of the battery cells 120 and using the mass loss condition as a supplementary signal of a signal of the gas sensor 140 so as to determine the position of a specific damaged battery cell 120; the plurality of current/voltage signal collectors are connected to the battery cells 120 in a one-to-one correspondence manner, and are configured to monitor output currents and output voltages of the battery cells 120; a solid state particle detector 170 is disposed on one side of the gas sensor 140; management devices are connected to the gas sensor 140, the plurality of thermocouple temperature sensors 150, the plurality of mass sensors 160, the plurality of current/voltage signal collectors, and the solid particle detector 170 for signal reception and command transmission.
The management device includes: the system comprises a signal transmission assembly, a single chip microcomputer and a BMS upper computer, wherein the signal transmission assembly is connected with the gas sensor 140, a plurality of thermocouple temperature sensors 150, a plurality of mass sensors 160, a plurality of current/voltage signal collectors and a solid particle detector 170; the single chip microcomputer is connected with the signal transmission assembly; and the BMS upper computer is connected with the singlechip and is used for receiving signals and transmitting commands.
Different from the existing photosensitive gas detection method based on Fourier infrared spectroscopy, the invention adopts a patch type gas sensor based on electric signals to detect the abundance change of characteristic gas in a module in real time, the monitoring principle is based on the resistance change caused by the characteristic gas molecules captured by a coating, the secondary detection of a purified sample by optical detection equipment is not relied on, additional accessories do not need to be additionally arranged in a battery pack module or a box body, and the concentration change of the characteristic gas at different positions in the module can be sensed by an upper computer in real time by arranging a gas sensor array in the module according to the flow field distribution of the cooling gas in the module. The real-time temperature field distribution returned by the coupling thermocouples can preliminarily judge the position of the problem monomer in the module. The high accuracy mass sensor who arranges in the monomer bottom is cooperated, can make the accurate damage monomer that locks in the module of host computer, compares in the technical scheme who arranges pressure sensor in relief valve department, adopts mass sensor's method can avoid pressure sensor signal noise big, receive the obvious shortcoming of environmental factor influence.
In the present embodiment, 16 thermocouple temperature sensors 150 are arranged in the form of 4 × 4 inside the housings of the first, second, third, and fourth battery pack modules 111, 112, 113, and 114.
Compared with the current method for carrying out thermal runaway early warning by using single external parameter of voltage or temperature, the introduction of the combustible gas sensor and the quality sensor can not only reduce the probability of false alarm and false alarm, but also more directly reflect the internal state of the battery, and can remarkably advance the early warning time of thermal runaway, so that the intervention time window is widened to the minute level, and conditions are created for the subsequent active safety measures to play roles.
The thermal runaway gas-sensitive alarm device for the vehicle-mounted lithium ion power battery is designed and developed, disturbance of the internal environment state of the battery pack module is monitored through the characteristic gas abundance, the mass loss proportion of the battery monomer and the surface temperature of the battery, and then whether the decomposition of electrolyte occurs and the occurrence degree of the electrolyte is judged under the condition of not depending on the output of external parameters of the battery, so that whether the power battery is damaged and the damage degree of the power battery is monitored in real time under the working state. Compared with the current method for carrying out thermal runaway early warning by using single external parameter of voltage or temperature, the introduction of the combustible gas sensor and the quality sensor can not only reduce the probability of false alarm and false alarm, but also more directly reflect the internal state of the battery, and can remarkably advance the early warning time of thermal runaway, so that the intervention time window is widened to the minute level, and conditions are created for the subsequent active safety measures to play roles.
Although the system can be considered to enter an irreversible state once thermal runaway occurs, thermal damage of the battery does not necessarily lead to the occurrence of thermal runaway due to differences in specific working conditions triggering the thermal runaway, and therefore, the battery state data obtained by the sensor must be evaluated by a probability analysis model to evaluate the risk of the occurrence of the thermal runaway.
According to the requirement of the electric vehicle, the model takes the change rate of the physical quantity as input and takes the thermal runaway occurrence probability under the working condition as output, so that the quantitative evaluation of the thermal runaway occurrence risk is realized. Therefore, the thermal runaway risk assessment model located on the upper computer should be composed of a mechanism simulation model for describing the battery state and a probability model for assessing the occurrence risk of thermal runaway. After a physical quantity fluctuation signal of the sensor is obtained, firstly, a mechanism simulation model judges the scale of a side reaction of the monomer according to an input signal peak value, and then a probability analysis model based on a machine learning algorithm evaluates the thermal damage stage and the size of an available safety intervention window according to the scale of the side reaction. Based on the evaluation result of the model, the BMS automatically selects the corresponding safety strategy while early warning the driver of the thermal runaway risk, thereby achieving the purpose of improving the safety of the electric vehicle.
As shown in fig. 7, the probability evaluation model based on the physical model is used as the evaluation model in the present invention, wherein the reaction kinetics model, the thermal diffusion model, the thermal strain model and the dynamic strain model form the physical model, the physical model is converted into a mathematical model, and the mathematical model and the measured data are input into the machine learning algorithm together, which is a mechanism layer; obtaining an experience model/a virtual measured object through a machine learning algorithm, and combining the experience model/the virtual measured object with dynamic bench data to obtain a control intervention model, wherein the control intervention model is an inference layer; and finally, the output intervention result and the data of the electric appliance model are jointly transmitted to a BMS upper computer to form an operation layer.
The task of the mechanism layer is mainly to form a virtual prototype used as a model kernel, the task of the reasoning layer is to perform data analysis on a database formed by the virtual prototype and an actual measurement experiment through a machine learning method to obtain a probability distribution model of the thermal runaway risk, the task of the operation layer is to make a decision on the subsequent operation according to the risk evaluation result of the probability layer, wherein the mechanism layer is used as the basis of the whole evaluation model and provides theoretical support for the model, and is used as the reasoning layer and the operation layer of the subsequent upper-layer building, the support and the restriction of a big data technology and a hardware implementation method are needed, and the operation layer makes reasonable suggestions on the basis of the judgment of corresponding results given by the reasoning layer in combination with actual conditions, such as performing corresponding cooling measures on a battery pack or reminding a driver to perform safe escape.
The core of the mechanism layer lies in the accurate reproduction of the thermal runaway physical scene by a physical model. The basis of this goal is the physical decoupling of critical features of thermal runaway and the manner in which the relevant physical fields are coupled. The physical architecture adopted by the physical model and the coupling mode and the judgment condition of each main module are shown in fig. 8. As a concentration cell, diffusion behavior is considered by the present model as the first driving force for cell function, while thermal triggering is used as an intrinsic condition for cell thermal runaway triggering.
The method for controlling the thermal runaway gas-sensitive alarm device of the vehicle-mounted lithium ion power battery in the inference layer comprises the steps of using the thermal runaway gas-sensitive alarm device of the vehicle-mounted lithium ion power battery as claimed in any one of claims 1 to 3, collecting gas characteristic distribution, temperature distribution and monomer quality loss of the battery through a plurality of arranged sensors, making confidence prediction on the battery state within a future period of time by utilizing a Markov chain-Monte Carlo algorithm, and taking battery characteristic parameters represented by the established battery equivalent circuit model as input signals of a neural network model to correspondingly evaluate the thermal runaway risk of the battery. The method specifically comprises the following steps:
the method comprises the following steps: according to the sampling period, the concentration of carbon monoxide characteristic gas in the collection box body, the temperature in the plurality of battery pack modules and the mass loss percentage of the battery monomer are measured through the sensor, and a state characterization matrix of a group of batteries is constructed:
Ω＝(Q,T,Δm)T；
in the formula, Q is a concentration vector of carbon monoxide characteristic gas in the box body, T is a temperature vector of each monitoring point in the battery pack module, and Δ m is mass loss percentage of each battery monomer;
step two, according to the database of the actual measurement experiment journey, the battery state data is calculated according to the following steps of 1: 1, randomly dividing the ratio into a training set and a testing set, and carrying out corresponding statistics on the appeared battery state representation matrix on the training set according to a time sequence principle to obtain the state space of the battery:
[S1,S2,......Sn]；
in the formula, n is the number of sampling time segments;
establishing a Markov chain prediction model to obtain a state transition matrix:
in the formula (II)
In the shape of a batteryState omegaiTransition to state ΩjI 1,2, … N, j 1,2, … N, N being the unique number of states of the battery;
wherein the battery is driven from state ΩiTransition to state ΩjThe probability of (c) satisfies:
in the formula (I), the compound is shown in the specification,
for the state transition omega of the battery under the actual measurement experimentiTo state omegajThe number of times that this occurs is,
for the battery state omega under the actual measurement experimentiThe total number of occurrences;
step three: predicting the battery state of each battery state of the test set in a future sampling period by utilizing the established Markov chain state transfer matrix, wherein the prediction process comprises the following steps:
assume that the current battery state is ΩiI ═ 1,2, … N, max probability:
Pmax＝Pij＝max(Pi1,Pi2,......PiN)，
wherein j is the maximum probability state number, ΩjPredicting a state for the next battery;
and comparing the model prediction result with the real state, testing the accuracy of the Markov chain, and calculating the effectiveness of the Markov chain:
in the formula, K is the accurate number of the prediction results, and K is the number of states of all test sets;
if f is larger than 90%, the Markov chain prediction model is proved to be effective, otherwise, the Markov chain prediction model is reestablished;
predicting the battery state [ omega ] of each battery state in the test set in the next three sampling periods by means of the established effective Markov chain modelt+T,Ωt+2T,Ωt+3T]T is the current time tag, and T is the sampling period;
inputting the battery states, the Markov chain validity and the SOC value of the battery in the next three sampling periods into a BP neural network model to obtain the stage grade of the thermal runaway of the battery;
after a battery SOC-OCV curve is obtained based on an off-line bench test, a physical characterization model of the battery is established, on the basis, a real-time output current/voltage signal of the battery is obtained through a CAN bus, then the SOC of the battery is accurately characterized through the established physical characterization model of the battery, and the characteristic state of the SOC is determined to be SSOC；
The calculation process of the BP neural network model comprises the following steps:
step 1, determining an input layer neuron vector x ═ x of a three-layer BP neural network1,x2,x3,x4,x5}; wherein x is1Is a battery state S1，x2Is a battery state S2，x3Is a battery state S3，x4For Markov chain validity, x5Is the SOC value of the battery;
step 2, the vector of the input layer is mapped to a hidden layer, the number of hidden layer neurons is h, and
in the formula, m is the number of input nodes, n is the number of output nodes, a is a regulating factor, and the value range of the regulating factor is 1-10, so that 5 hidden layer neurons are selected;
step 3, obtaining an output layer neuron vector o ═ o1,o2}；o1Is a battery thermal runaway risk level, o2Is o1The reliability of the prediction result;
wherein the content of the first and second substances,
the zero-level risk is 0, which indicates that the battery is normal, the first-level risk is 1, which indicates that the battery monomer is likely to generate thermal runaway and needs to continuously monitor the battery, the second-level risk is 2, which indicates that the battery monomer is thermally runaway and needs to be cooled, and the third-level risk is 3, which indicates that the battery pack module is thermally runaway.
The excitation functions of the hidden layer and the output layer adopt S-shaped functions fj(x)＝1/(1+e-x)；
Step five, judging the probability of the thermal runaway of the battery according to the stage grade of the thermal runaway of the battery, adopting a cooling measure to the battery and reminding drivers and passengers, and specifically comprising the following steps:
when o 10 and o2When the temperature is more than or equal to 90 percent, the battery has no probability of thermal runaway;
when o11 and o2When the temperature of the battery is more than or equal to 80%, the probability of thermal runaway of the battery is less than 50%, and the monomer of the battery needs to be cooled;
when o12 and o2When the temperature of the battery pack is more than or equal to 70%, the probability of thermal runaway of the battery is more than 50%, and the battery pack module needs to be cooled;
when o13 and o2And when the temperature is more than or equal to 60 percent, the battery pack module generates thermal runaway and needs to remind drivers and passengers to avoid danger in time and send out an alarm sound.
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable to various fields of endeavor for which the invention may be embodied with additional modifications as would be readily apparent to those skilled in the art, and the invention is therefore not limited to the details given herein and to the embodiments shown and described without departing from the generic concept as defined by the claims and their equivalents.
Claims (10)
1. A thermal runaway gas-sensitive alarm device and method for a vehicle-mounted lithium ion power battery are characterized by comprising the following steps:
a box body; and
the battery pack modules are arranged inside the box body at intervals, the battery cells are uniformly arranged inside the battery pack modules, and cooling flow field channels are formed among the battery pack modules;
the gas sensor is arranged at the outlet position of the cooling flow field channel;
a plurality of thermocouple temperature sensors uniformly arranged inside the plurality of battery pack modules;
the mass sensors are arranged at the lower parts of the battery cells in a one-to-one correspondence manner;
and the management device is connected with the gas sensor, the thermocouple temperature sensors and the mass sensors and is used for receiving signals and transmitting commands.
2. The thermal runaway gas sensitive alarm device for the vehicle-mounted lithium ion power battery and the method thereof as claimed in claim 1, wherein the management device comprises:
a signal transmission assembly connected with the gas sensor, the plurality of thermocouple temperature sensors and the plurality of mass sensors;
the single chip microcomputer is connected with the signal transmission assembly;
and the BMS upper computer is connected with the singlechip and is used for receiving signals and transmitting commands.
3. The thermal runaway gas-sensitive alarm device for the vehicle-mounted lithium ion power battery and the method thereof as claimed in claim 2, further comprising:
the current/voltage signal collectors are connected with the single batteries in a one-to-one correspondence mode and used for monitoring the output current and the output voltage of the single batteries;
a solid state particle detector disposed on one side of the gas sensor;
wherein the plurality of current/voltage signal collectors and the solid state particle detector are both connected to the signal transmission assembly.
4. A detection method of a thermal runaway gas-sensitive alarm device of a vehicle-mounted lithium ion power battery, which uses the thermal runaway gas-sensitive alarm device of the vehicle-mounted lithium ion power battery as claimed in any one of claims 1 to 3, and is characterized by comprising the following steps:
step one, according to a sampling period, collecting the concentration of carbon monoxide characteristic gas in a box body, the temperature in a plurality of battery pack modules and the mass loss percentage of a battery monomer, and constructing a battery state characterization matrix:
Ω＝(Q,T,Δm)T；
in the formula, Q is a concentration vector of carbon monoxide characteristic gas in the box body, T is a temperature vector of each monitoring point in the battery pack module, and Δ m is mass loss percentage of each battery monomer;
step two, the battery state data is processed according to the following steps of 1: 1, randomly dividing the proportion into a training set and a testing set, carrying out statistics on the appeared battery state representation matrix on the training set according to a time sequence principle to obtain a state space of the battery, establishing a Markov chain prediction model, and obtaining a state transition matrix:
in the formula (II)
For the battery from state omegaiTransition to state ΩjI 1,2, … N, j 1,2, … N, N being the unique number of states of the battery;
step three, predicting the battery state [ omega ] of each battery state in the test set in the next three sampling periods by means of the established effective Markov chain modelt+T,Ωt+2T,Ωt+3T]T is the current time tag, and T is the sampling period;
inputting the battery states, the Markov chain validity and the SOC value of the battery in the next three sampling periods into a BP neural network model to obtain the stage grade of the thermal runaway of the battery;
and step five, judging the probability of the thermal runaway of the battery according to the stage grade of the thermal runaway of the battery, and adopting a cooling measure for the battery and reminding drivers and passengers.
5. The detection method of the thermal runaway gas-sensitive alarm device of the vehicle-mounted lithium ion power battery as claimed in claim 4, characterized in that the battery is in a state omegaiTransition to state ΩjThe probability of (c) satisfies:
in the formula (I), the compound is shown in the specification,
for the state transition omega of the battery under the actual measurement experimentiTo state omegajThe number of times that this occurs is,
for the battery state omega under the actual measurement experimentiTotal number of occurrences.
6. The detection method of the thermal runaway gas-sensitive alarm device of the vehicle-mounted lithium-ion power battery as claimed in claim 5, wherein the process of judging whether the Markov chain model is valid is as follows:
and predicting the battery state of each battery state in the test set in a future sampling period according to the state transition matrix, comparing a prediction result with a real state, if the effectiveness of the Markov chain is more than 90%, proving that the Markov chain prediction model is effective, and otherwise, reestablishing the Markov chain prediction model.
7. The detection method of the thermal runaway gas-sensitive alarm device of the vehicle-mounted lithium-ion power battery as claimed in claim 6, wherein the Markov chain validity meets the following requirements:
in the formula, K is the accurate number of the prediction results, and K is the number of the states of all the test sets.
8. The detection method of the thermal runaway gas-sensitive alarm device of the vehicle-mounted lithium ion power battery as claimed in claim 7, wherein the SOC value of the battery is obtained by real-time current/voltage signal query after a battery SOC-OCV curve is obtained based on an offline bench test.
9. The detection method of the thermal runaway gas-sensitive alarm device of the vehicle-mounted lithium-ion power battery as claimed in claim 8, wherein the calculation process of the BP neural network model is as follows:
step 1, determining an input layer neuron vector x ═ x of a three-layer BP neural network1,x2,x3,x4,x5}; wherein x is1Is in a battery state omegat+T，x2Is in a battery state omegat+2T，x3Is in a battery state omegat+3T，x4For Markov chain validity f, x5Is the SOC value of the battery;
step 2, the vector of the input layer is mapped to a hidden layer, the number of hidden layer neurons is h, and
in the formula, m is the number of input nodes, n is the number of output nodes, and a is an adjusting factor;
step 3, obtaining an output layer neuron vector o ═ o1,o2}；o1Is a battery thermal runaway risk level, o2Is o1The reliability of the prediction result;
wherein the content of the first and second substances,
the zero-level risk is 0, which indicates that the battery is normal, the first-level risk is 1, which indicates that the battery monomer is likely to generate thermal runaway and needs to continuously monitor the battery, the second-level risk is 2, which indicates that the battery monomer is thermally runaway and needs to be cooled, and the third-level risk is 3, which indicates that the battery pack module is thermally runaway.
10. The method for detecting the thermal runaway gas-sensitive alarm device of the vehicle-mounted lithium ion power battery as claimed in claim 9, wherein the fifth step specifically comprises:
when o10 and o2When the temperature is more than or equal to 90 percent, the battery has no probability of thermal runaway;
when o11 and o2When the temperature of the battery is more than or equal to 80%, the probability of thermal runaway of the battery is less than 50%, and the monomer of the battery needs to be cooled;
when o12 and o2When the temperature of the battery pack is more than or equal to 70%, the probability of thermal runaway of the battery is more than 50%, and the battery pack module needs to be cooled;
when o13 and o2And when the temperature is more than or equal to 60 percent, the battery pack module generates thermal runaway and needs to remind drivers and passengers to avoid danger in time and send out an alarm sound.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110208652.4A CN113013514B (en) | 2021-02-25 | 2021-02-25 | Thermal runaway gas-sensitive alarm device of vehicle-mounted lithium ion power battery and detection method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110208652.4A CN113013514B (en) | 2021-02-25 | 2021-02-25 | Thermal runaway gas-sensitive alarm device of vehicle-mounted lithium ion power battery and detection method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113013514A true CN113013514A (en) | 2021-06-22 |
| CN113013514B CN113013514B (en) | 2022-08-05 |
Family
ID=76386406
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110208652.4A Active CN113013514B (en) | 2021-02-25 | 2021-02-25 | Thermal runaway gas-sensitive alarm device of vehicle-mounted lithium ion power battery and detection method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113013514B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114019398A (en) * | 2021-10-29 | 2022-02-08 | 中国第一汽车股份有限公司 | Battery system thermal runaway test device and battery system thermal runaway test method |
| WO2023071783A1 (en) * | 2021-10-29 | 2023-05-04 | 宁德时代新能源科技股份有限公司 | Method and apparatus for detecting thermal runaway of battery, and system, vehicle and storage medium |
| EP4207432A3 (en) * | 2021-12-30 | 2023-09-06 | Chongqing Changan New Energy Vehicles Technology Co., Ltd | Method and system for predicting thermal runaway of battery based on machine learning |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070212596A1 (en) * | 1999-06-25 | 2007-09-13 | Nebrigic Dragan D | Single and multiple cell lithium ion battery with built-in controller |
| US7433794B1 (en) * | 2007-07-18 | 2008-10-07 | Tesla Motors, Inc. | Mitigation of propagation of thermal runaway in a multi-cell battery pack |
| US20130207596A1 (en) * | 2012-01-26 | 2013-08-15 | Li-Tec Battery Gmbh | Electrochemical energy converter device with a cell housing, a battery with at least two of said electrochemical energy converter devices, and a method for the manufacture of an electrochemical energy converter device |
| US20130231894A1 (en) * | 2012-03-01 | 2013-09-05 | Nokia Corporation | Method and apparatus for providing battery information |
| US20140247137A1 (en) * | 2013-03-04 | 2014-09-04 | Hello Inc. | Base charging station for monitoring device |
| US20140295218A1 (en) * | 2013-03-27 | 2014-10-02 | Eva Hakansson | Method of detecting lithium-ion cell damage via vapor detection |
| CN108258338A (en) * | 2017-12-29 | 2018-07-06 | 江苏博强新能源科技股份有限公司 | The management system and method for battery |
| CN109177982A (en) * | 2018-10-31 | 2019-01-11 | 吉林大学 | Consider the vehicle driving Hazard degree assessment method of driving style |
| CN110828760A (en) * | 2018-08-08 | 2020-02-21 | 辉能科技股份有限公司 | Horizontal combined type electric energy supply unit group |
| CN111325403A (en) * | 2020-02-26 | 2020-06-23 | 长安大学 | Method for predicting remaining life of electromechanical equipment of highway tunnel |
| CN111373586A (en) * | 2017-06-02 | 2020-07-03 | 弗朗什孔岱大学 | Method and system for real-time diagnosing the operating state of an electrochemical system, and electrochemical system incorporating the same |
| US20200266405A1 (en) * | 2019-02-20 | 2020-08-20 | Rivian Ip Holdings, Llc | Battery module gas sensor for battery cell monitoring |
| US20200307413A1 (en) * | 2019-03-28 | 2020-10-01 | Honda Motor Co., Ltd. | Selection apparatus, selection method, and storage medium |
| CN112018292A (en) * | 2020-09-07 | 2020-12-01 | 上海弘特智能系统科技股份有限公司 | UPS battery cabinet safety early warning device and control method |
| CN112090006A (en) * | 2020-11-10 | 2020-12-18 | 国网江苏省电力有限公司经济技术研究院 | Fire control system and method for prefabricated cabin |
| US20210049480A1 (en) * | 2019-08-12 | 2021-02-18 | Micron Technology, Inc. | Predictive maintenance of automotive battery |
-
2021
- 2021-02-25 CN CN202110208652.4A patent/CN113013514B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070212596A1 (en) * | 1999-06-25 | 2007-09-13 | Nebrigic Dragan D | Single and multiple cell lithium ion battery with built-in controller |
| US7433794B1 (en) * | 2007-07-18 | 2008-10-07 | Tesla Motors, Inc. | Mitigation of propagation of thermal runaway in a multi-cell battery pack |
| US20130207596A1 (en) * | 2012-01-26 | 2013-08-15 | Li-Tec Battery Gmbh | Electrochemical energy converter device with a cell housing, a battery with at least two of said electrochemical energy converter devices, and a method for the manufacture of an electrochemical energy converter device |
| US20130231894A1 (en) * | 2012-03-01 | 2013-09-05 | Nokia Corporation | Method and apparatus for providing battery information |
| US20140247137A1 (en) * | 2013-03-04 | 2014-09-04 | Hello Inc. | Base charging station for monitoring device |
| US20140295218A1 (en) * | 2013-03-27 | 2014-10-02 | Eva Hakansson | Method of detecting lithium-ion cell damage via vapor detection |
| CN111373586A (en) * | 2017-06-02 | 2020-07-03 | 弗朗什孔岱大学 | Method and system for real-time diagnosing the operating state of an electrochemical system, and electrochemical system incorporating the same |
| CN108258338A (en) * | 2017-12-29 | 2018-07-06 | 江苏博强新能源科技股份有限公司 | The management system and method for battery |
| CN110828760A (en) * | 2018-08-08 | 2020-02-21 | 辉能科技股份有限公司 | Horizontal combined type electric energy supply unit group |
| CN109177982A (en) * | 2018-10-31 | 2019-01-11 | 吉林大学 | Consider the vehicle driving Hazard degree assessment method of driving style |
| US20200266405A1 (en) * | 2019-02-20 | 2020-08-20 | Rivian Ip Holdings, Llc | Battery module gas sensor for battery cell monitoring |
| US20200307413A1 (en) * | 2019-03-28 | 2020-10-01 | Honda Motor Co., Ltd. | Selection apparatus, selection method, and storage medium |
| US20210049480A1 (en) * | 2019-08-12 | 2021-02-18 | Micron Technology, Inc. | Predictive maintenance of automotive battery |
| CN111325403A (en) * | 2020-02-26 | 2020-06-23 | 长安大学 | Method for predicting remaining life of electromechanical equipment of highway tunnel |
| CN112018292A (en) * | 2020-09-07 | 2020-12-01 | 上海弘特智能系统科技股份有限公司 | UPS battery cabinet safety early warning device and control method |
| CN112090006A (en) * | 2020-11-10 | 2020-12-18 | 国网江苏省电力有限公司经济技术研究院 | Fire control system and method for prefabricated cabin |
Non-Patent Citations (4)
| Title |
|---|
| SAKUMURA,Y等: "Markov chain model approximating the Hodgkin-Huxley neuron", 《ARTIFICIAL NEURAL NETWORKS-ICANN 2001,PROCEEDINGS》 * |
| 乔玉龙等: "基于隐马尔可夫模型的锂电池退化状态识别", 《应用科技》 * |
| 张绪祥等: "基于HMM的锂电池仓火灾预测算法研究", 《汽车实用技术》 * |
| 彭凯: "增程式电动车动力电池组预热控制策略研究", 《中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑)》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114019398A (en) * | 2021-10-29 | 2022-02-08 | 中国第一汽车股份有限公司 | Battery system thermal runaway test device and battery system thermal runaway test method |
| WO2023071783A1 (en) * | 2021-10-29 | 2023-05-04 | 宁德时代新能源科技股份有限公司 | Method and apparatus for detecting thermal runaway of battery, and system, vehicle and storage medium |
| EP4207432A3 (en) * | 2021-12-30 | 2023-09-06 | Chongqing Changan New Energy Vehicles Technology Co., Ltd | Method and system for predicting thermal runaway of battery based on machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113013514B (en) | 2022-08-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113013514B (en) | Thermal runaway gas-sensitive alarm device of vehicle-mounted lithium ion power battery and detection method thereof | |
| Yang et al. | Characterization of external short circuit faults in electric vehicle Li-ion battery packs and prediction using artificial neural networks | |
| Jiang et al. | Data-driven fault diagnosis and thermal runaway warning for battery packs using real-world vehicle data | |
| Wang et al. | A data-driven method for battery charging capacity abnormality diagnosis in electric vehicle applications | |
| Chen et al. | Model-based fault diagnosis approach on external short circuit of lithium-ion battery used in electric vehicles | |
| CN111007401A (en) | Electric vehicle battery fault diagnosis method and device based on artificial intelligence | |
| CN110416644B (en) | Vehicle-mounted early warning device for hidden damage monitoring and thermal runaway of lithium ion power battery and early warning method thereof | |
| CN110398699A (en) | Power battery thermal runaway method for early warning combined of multi-sensor information | |
| Wang et al. | A fault diagnosis method for lithium-ion battery packs using improved RBF neural network | |
| CN109604186A (en) | Power battery performance flexibility assesses method for separating | |
| CN205674885U (en) | A kind of battery detecting management system of electric automobile | |
| WO2023036037A1 (en) | Intelligent battery monitoring and early warning method and system based on multiple types and quantities of sensors | |
| CN113791364A (en) | Lithium ion battery internal short circuit diagnosis method and system driven by model fusion signal | |
| Xu et al. | Safety warning analysis for power battery packs in electric vehicles with running data | |
| Ding et al. | Diagnosis of connection fault for parallel-connected lithium-ion batteries based on long short-term memory networks | |
| Li et al. | Battery safety risk assessment in real-world electric vehicles based on abnormal internal resistance using proposed robust estimation method and hybrid neural networks | |
| He et al. | Voltage abnormality-based fault diagnosis for batteries in electric buses with a self-adapting update model | |
| Cho et al. | An LSTM-PINN hybrid method to estimate lithium-ion battery pack temperature | |
| Yang et al. | Internal short circuit detection for parallel-connected battery cells using convolutional neural network | |
| Wu et al. | A fault detection method of electric vehicle battery through Hausdorff distance and modified Z-score for real-world data | |
| Liu et al. | Online diagnosis and prediction of power battery voltage comprehensive faults for electric vehicles based on multi-parameter characterization and improved K-means method | |
| Yang et al. | A review on models to prevent and control lithium-ion battery failures: From diagnostic and prognostic modeling to systematic risk analysis | |
| CN115958957B (en) | Method and system for predicting charging overheat faults of power battery of electric automobile | |
| Liu et al. | Voltage fault diagnosis and misdiagnosis analysis of battery systems using the modified Shannon entropy in real-world electric vehicles | |
| Zhang et al. | Internal short circuit warning method of parallel lithium-ion module based on loop current detection |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |