CN114889433A - Thermal runaway alarm system and method for battery of electric vehicle - Google Patents

Thermal runaway alarm system and method for battery of electric vehicle Download PDF

Info

Publication number
CN114889433A
CN114889433A CN202210466186.4A CN202210466186A CN114889433A CN 114889433 A CN114889433 A CN 114889433A CN 202210466186 A CN202210466186 A CN 202210466186A CN 114889433 A CN114889433 A CN 114889433A
Authority
CN
China
Prior art keywords
battery
thermal runaway
early warning
model
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.)
Pending
Application number
CN202210466186.4A
Other languages
Chinese (zh)
Inventor
黄芳芳
宋开通
吴亚东
赵欢欢
王恒
王延智
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chery New Energy Automobile Co Ltd
Original Assignee
Chery New Energy Automobile Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chery New Energy Automobile Co Ltd filed Critical Chery New Energy Automobile Co Ltd
Priority to CN202210466186.4A priority Critical patent/CN114889433A/en
Publication of CN114889433A publication Critical patent/CN114889433A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L3/00—Electric devices on electrically-propelled vehicles for safety purposes; Monitoring operating variables, e.g. speed, deceleration or energy consumption
    • B60L3/0023—Detecting, eliminating, remedying or compensating for drive train abnormalities, e.g. failures within the drive train
    • B60L3/0046—Detecting, eliminating, remedying or compensating for drive train abnormalities, e.g. failures within the drive train relating to electric energy storage systems, e.g. batteries or capacitors
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L58/00—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles
    • B60L58/10—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries
    • 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
    • H01M10/4285—Testing apparatus
    • 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
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/60—Other road transportation technologies with climate change mitigation effect
    • Y02T10/70—Energy storage systems for electromobility, e.g. batteries

Landscapes

  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Mechanical Engineering (AREA)
  • Sustainable Energy (AREA)
  • Sustainable Development (AREA)
  • Transportation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Manufacturing & Machinery (AREA)
  • Chemical & Material Sciences (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Electrochemistry (AREA)
  • General Chemical & Material Sciences (AREA)
  • Secondary Cells (AREA)

Abstract

The invention discloses a thermal runaway alarm system and method for an electric vehicle battery.A battery early warning system is responsible for monitoring the temperature of a battery monomer in a battery pack, the pressure in the battery pack, the bus current and the bus voltage of a finished vehicle in different working modes; the smoke sensor is used for monitoring the smoke concentration in the battery pack; the collected data are all transmitted to a battery management system; the battery management system transmits the smoke concentration data to the vehicle control unit; the vehicle control unit analyzes the smoke concentration data to determine whether a first thermal runaway early warning instruction is sent; the battery management system transmits data acquired by the battery early warning system to the vehicle-mounted terminal; the vehicle-mounted terminal transmits the data to the cloud server, and the cloud server determines whether to send out a second thermal runaway early warning instruction or not according to the data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; and the battery management system determines whether to send out a thermal runaway alarm according to the two runaway early warning instructions. Reliability of alarming and user experience are improved.

Description

Electric vehicle battery thermal runaway alarm system and method
Technical Field
The invention relates to the technical field of battery monitoring of pure electric vehicles, in particular to a thermal runaway alarm system and method for an electric vehicle battery.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
With the increasing preservation quantity of electric automobiles in the market, the safety problem of the electric automobiles is increasingly severe.
The root cause of electric vehicle fire and explosion is thermal runaway caused by battery failure. The thermal runaway problem not only restricts the popularization and the commercial application of the electric automobile, but also brings serious hidden dangers to the life, property and traffic safety of people. At present, after the battery of the electric automobile is out of control due to heat, a battery high-temperature alarm, a battery temperature difference alarm and a battery pressure difference alarm can be reported, but at present, an accurate, rapid and personalized battery out of control thermal alarm system does not exist.
Chinese utility model patent CN 215752027U-power battery thermal runaway early warning system and car, voltage and temperature through voltage sensor and temperature sensor collection battery cell realize the early warning of power battery thermal runaway, however, there is the alarm condition single, alarm data processing speed is slow, sensitivity to alarm is low, the reliability is poor, has the alert problem of wrong report.
Chinese utility model patent CN 212313296U-a battery package thermal runaway early warning system, the monomer information through smoke concentration and the battery package in gathering the battery package carries out the early warning of thermal runaway, though can solve the alert problem of battery wrong report, but there is data singleness, and the analysis result is unreliable, analysis process consumes time, gives the remaining problem of keeping away from the time of dangerous battery package too short of user.
The inventor finds that the existing battery thermal runaway early warning has the problems of single data acquisition, unreliable warning result, low warning sensitivity, overlong calculation time in the warning analysis process, short time for a user and overhigh warning sensitivity; for example, data generated by electric vehicle battery packs of different models are different, data generated by electric vehicle battery packs of the same model under the condition of different service lives are also different, if only data collected at the current time point is considered, the alarm sensitivity can be too high, and the user experience can be seriously influenced if the alarm is not given.
Disclosure of Invention
In order to solve the defects of the prior art, the invention provides an electric vehicle battery thermal runaway alarm system and method; the method comprises the steps of carrying out quick early warning on the thermal runaway fault of the battery system of the electric automobile, and sending an alarm signal in advance by the battery management system 30 minutes before the thermal runaway of a passenger compartment so as to strive for more time for a user; various data are adopted for analysis, so that the reliability of alarming is improved; meanwhile, the sensitivity of thermal runaway alarm is not too high, and the user experience is improved.
In a first aspect, the invention provides a thermal runaway alarm method for an electric vehicle battery;
a thermal runaway alarm method for an electric vehicle battery is applied to a battery management system BMS and comprises the following steps:
transmitting the smoke concentration data to a VCU (vehicle control unit); so that the VCU of the vehicle control unit analyzes the smoke concentration data to determine whether to send out a first thermal runaway early warning instruction; receiving an analysis result of a VCU of the vehicle controller;
transmitting data of different working modes acquired by the battery early warning system to a cloud server through a vehicle-mounted terminal T-BOX (telematics BOX); the cloud server determines whether to send a second thermal runaway early warning instruction or not according to the data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; receiving an analysis result of the cloud server through the vehicle-mounted terminal;
and determining whether to send out a thermal runaway alarm or not according to the two analysis results.
In a second aspect, the present invention provides a battery management system BMS;
a battery management system BMS, comprising:
a first transmission module configured to: transmitting the smoke concentration data to a Vehicle Control Unit (VCU); so that the VCU of the vehicle control unit analyzes the smoke concentration data to determine whether to send out a first thermal runaway early warning instruction; receiving an analysis result of a VCU of the vehicle controller;
a second transmission module configured to: transmitting data of different working modes acquired by the battery early warning system to a cloud server through a vehicle-mounted terminal T-BOX (telematics BOX); the cloud server determines whether to send a second thermal runaway early warning instruction or not according to the data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; receiving an analysis result of the cloud server through the vehicle-mounted terminal;
an output module configured to: and determining whether to send out a thermal runaway alarm or not according to the two analysis results.
In a third aspect, the invention provides an electric vehicle battery thermal runaway alarm method;
an electric vehicle battery thermal runaway alarm method is applied to a vehicle control unit and comprises the following steps:
acquiring smoke concentration data;
analyzing the smoke concentration data to determine whether a first thermal runaway early warning instruction is sent;
sending the first analysis result to a Battery Management System (BMS);
the auxiliary battery management system is combined with the first analysis result and the second analysis result to determine whether to send out a thermal runaway alarm or not;
the second analysis result is sent to the battery management system BMS by the cloud server through the vehicle-mounted terminal; the second analysis result is that the cloud server determines whether to send a second thermal runaway early warning instruction according to the data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; the data uploaded by the vehicle-mounted terminal are data acquired by different sensors in different working modes and acquired by the battery early warning system.
In a fourth aspect, the present disclosure provides a vehicle control unit;
vehicle control unit includes:
a first acquisition module configured to: acquiring smoke concentration data;
a first analysis module configured to: analyzing the smoke concentration data to determine whether a first thermal runaway early warning instruction is sent;
a first transmitting module configured to: sending the first analysis result to a Battery Management System (BMS);
a first determination module configured to: the auxiliary battery management system is combined with the first analysis result and the second analysis result to determine whether to send out a thermal runaway alarm;
the second analysis result is sent to the battery management system BMS by the cloud server through the vehicle-mounted terminal; the second analysis result is that the cloud server determines whether to send a second thermal runaway early warning instruction according to the data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; the data uploaded by the vehicle-mounted terminal are data acquired by different sensors in different working modes and acquired by the battery early warning system.
In a fifth aspect, the invention provides a thermal runaway alarm method for an electric vehicle battery;
an electric vehicle battery thermal runaway alarm method is applied to a cloud server and comprises the following steps:
acquiring data in different working modes and different modes;
determining a second analysis result based on data of different working modes and different modes and the trained thermal runaway early warning model; the second analysis result indicates whether a second thermal runaway early warning instruction is sent;
sending the determined second analysis result to a Battery Management System (BMS) through the vehicle-mounted terminal;
the auxiliary battery management system is combined with the first analysis result and the second analysis result to determine whether to send out a thermal runaway alarm;
the data of different working modes and different modes are collected by different sensors and are uploaded to the cloud server through the battery management system BMS and the vehicle-mounted terminal in sequence; the first analysis result is obtained by analyzing smoke concentration data by the VCU of the vehicle control unit; the first analysis result indicates whether a first thermal runaway early warning instruction is sent; the smoke concentration data are collected by the smoke sensor and uploaded to the VCU through the BMS.
In a sixth aspect, the present invention provides a cloud server;
a cloud server, comprising:
a second acquisition module configured to: acquiring data in different working modes and different modes;
a second analysis module configured to: determining a second analysis result based on data of different working modes and different modes and the trained thermal runaway early warning model; the second analysis result indicates whether a second thermal runaway early warning instruction is sent;
a second transmitting module configured to: sending the determined second analysis result to a Battery Management System (BMS) through the vehicle-mounted terminal;
a second determination module configured to: the auxiliary battery management system is combined with the first analysis result and the second analysis result to determine whether to send out a thermal runaway alarm;
the data of different working modes and different modes are collected by different sensors and are uploaded to the cloud server through the battery management system BMS and the vehicle-mounted terminal in sequence; the first analysis result is obtained by analyzing the smoke concentration data by the VCU; the first analysis result indicates whether a first thermal runaway early warning instruction is sent; the smoke concentration data are collected by the smoke sensor and uploaded to the VCU through the BMS.
In a seventh aspect, the invention further provides an electric vehicle battery thermal runaway alarm system;
an electric vehicle battery thermal runaway alarm system, comprising: the system comprises a battery management system BMS, a vehicle control unit VCU and a cloud server;
the battery management system BMS transmits the smoke concentration data to a VCU (vehicle control unit); the VCU analyzes the smoke concentration data to determine whether a first thermal runaway early warning instruction is sent out;
the battery management system BMS transmits data of different working modes acquired by the battery early warning system to a vehicle-mounted terminal T-BOX (telematics BOX); the vehicle-mounted terminal transmits the data to the cloud server, and the cloud server determines whether to send out a second thermal runaway early warning instruction or not according to the data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model;
and the battery management system BMS determines whether to send out a thermal runaway alarm or not according to the two runaway early warning instructions.
In an eighth aspect, the present invention provides an electronic device;
an electronic device, comprising:
a memory for non-transitory storage of computer readable instructions; and
a processor for executing the computer readable instructions,
wherein the computer readable instructions, when executed by the processor, perform the method of the first, third or fifth aspect.
In a ninth aspect, the present invention also provides a storage medium storing non-transitory computer readable instructions, wherein the non-transitory computer readable instructions, when executed by a computer, perform the instructions of the method of the first, third or fifth aspect.
In a tenth aspect, the invention also provides a computer program product comprising a computer program for implementing the method of the first, third or fifth aspect when run on one or more processors.
Compared with the prior art, the invention has the beneficial effects that:
(1) the battery management system sends out an alarm signal in advance 30 minutes before the thermal runaway of the passenger compartment, so that more time is won for a user;
(2) various data of temperature, pressure, current, voltage and smoke are adopted for analysis, so that the reliability and sensitivity of alarming are improved;
(3) by combining the historical data of the same type and batch of batteries with the battery mechanism model and the artificial intelligence early warning model, the sensitivity of thermal runaway alarm is not too high, and the user experience is improved.
(4) The invention combines the battery early warning system and the smoke sensor, and sends out the thermal runaway acousto-optic warning information at least 30 minutes before the thermal runaway happens, thereby solving the problem that the thermal runaway warning signal is sent out 5 minutes before the thermal runaway of the passenger compartment in the safety requirement of the power storage battery for the electric automobile, expanding the functionality of the electric automobile and improving the safety of the electric automobile;
(5) the invention replaces the conventional battery thermal runaway alarm (no special battery thermal runaway alarm system), and reports the thermal runaway of the battery after monitoring alarm information such as battery high temperature alarm, battery temperature difference alarm, battery pressure difference alarm and the like.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
Fig. 1 is a schematic diagram of internal connection of a thermal runaway alarm system for an electric vehicle battery according to a first embodiment of the application;
FIG. 2 is a schematic diagram of a thermal runaway alarm strategy according to a first embodiment of the present application;
fig. 3 is a schematic diagram of a battery warning system according to a first embodiment of the present application;
fig. 4 is a flowchart illustrating interaction with a smoke sensor in a BMS non-sleep state according to a first embodiment of the present application;
fig. 5 is a flowchart illustrating interaction with a smoke sensor in a BMS sleep state according to a first embodiment of the present application;
001 represents different vehicle modes, wherein the driving mode, the slow charging mode and the fast charging mode correspond to the non-sleep state of the BMS, and the standing power-down mode corresponds to the sleep state of the BMS;
002 indicates BMS ignition signals including K15 ignition, slow charge ignition, fast charge ignition signals;
003, the BMS is woken up and enters a working state;
004 for representing thermal runaway alarm monitoring information, including the early warning information monitored by a battery early warning system, smoke alarm and other information;
005 shows that the thermal runaway alarm system in the BMS synthesizes the monitoring information of the battery early warning system and the smoke sensing alarm information to confirm the thermal runaway alarm and uploads the thermal runaway alarm to the whole vehicle network through the whole vehicle CAN;
006 shows that after the VCU of the whole vehicle receives the thermal runaway alarm information of the battery, audible and visual alarm is carried out.
Detailed Description
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and it should be understood that the terms "comprises" and "comprising", and any variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
All data are obtained according to the embodiment and are legally applied on the data on the basis of compliance with laws and regulations and user consent.
The embodiment I provides a thermal runaway alarm method for an electric vehicle battery;
as shown in fig. 1, a method for alarming thermal runaway of a battery of an electric vehicle, applied to a battery management system BMS, includes:
transmitting the smoke concentration data to a VCU (vehicle control unit); so that the VCU of the vehicle control unit analyzes the smoke concentration data to determine whether to send out a first thermal runaway early warning instruction; receiving an analysis result of a VCU (vehicle control unit);
transmitting data of different working modes acquired by the battery early warning system to a cloud server through a vehicle-mounted terminal T-BOX (telematics BOX); the cloud server determines whether to send a second thermal runaway early warning instruction or not according to the data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; receiving an analysis result of the cloud server through the vehicle-mounted terminal;
and determining whether to send out a thermal runaway alarm or not according to the two analysis results.
Further, the battery early warning system and the smoke sensor are both arranged in the battery pack;
the battery early warning system is responsible for monitoring the temperature of a battery monomer in the battery pack, the pressure in the battery pack, the bus current and the bus voltage of the whole vehicle in different working modes;
the smoke sensor is used for monitoring the smoke concentration in the battery pack of the whole vehicle in different working modes;
the battery early warning system and the smoke sensor transmit the acquired data to a battery Management system BMS (Battery Management System).
According to the technical scheme, the technical problems that the collected data are single and the analysis result is not accurate enough in the prior art are solved by collecting various data, and the technical effect that the analysis results of various data are more reliable is achieved. Moreover, a first thermal runaway early warning instruction is given out by analyzing the smoke concentration data through the vehicle control unit; analyzing data acquired by the battery early warning system through the cloud server to give a second thermal runaway early warning instruction; the final thermal runaway alarm is given by comprehensively considering the two thermal runaway early warning instructions, the problem of thermal runaway misinformation is avoided, the reliability and the stability of the thermal runaway alarm are improved, and the sensitivity of the thermal runaway alarm is also controlled not to be too high or too low.
When the whole vehicle is in a driving mode, an alternating current charging mode, a direct current charging mode and a standing power-off mode, the battery early warning system carries out battery early warning by monitoring the temperature, the current, the voltage and the pressure of the full life cycle inside the battery system, smoke sensing concentration abnormity warning information is monitored in real time by combining a battery system assembly controller Battery Management System (BMS), a thermal runaway warning signal is sent out at least 30 minutes before the thermal runaway occurs, and sound and light warning is carried out on the whole vehicle to remind passengers, as shown in figure 2.
Further, the battery early warning system includes: temperature sensors, pressure sensors, current sensors, and voltage sensors.
Further, the VCU analyzes the smoke concentration data to determine whether to send out a first thermal runaway early warning instruction; the method specifically comprises the following steps:
(11) in the non-dormancy state (driving, alternating current charging and direct current charging) of the whole vehicle, the smoke sensor works in a continuous working mode, and monitors the smoke concentration, the Pulse Width Modulation (PWM) frequency and the duty ratio in the battery pack; the battery management system BMS reads the PWM frequency and the duty ratio monitored by the smoke sensor in real time;
(12) the smoke sensor judges whether the smoke concentration in the battery pack exceeds a set threshold value, and if the smoke concentration exceeds the set threshold value, the PWM frequency and the duty ratio of the corresponding moment when the concentration exceeds the set threshold value are uploaded to a battery management system BMS;
(13) the battery management system BMS judges whether the received frequency is equal to a first frequency threshold value, if not, the step is carried out (14); if so, entering (15);
(14) judging whether the received frequency is equal to a second frequency threshold value, if so, reporting that the smoke sensor has a fault according to the PWM frequency and the duty ratio; if not, continuously judging whether the received frequency is equal to a second frequency threshold value;
(15) judging whether the current duty ratio is larger than a first duty ratio threshold value or not, if so, judging to send a first thermal runaway early warning instruction, sending the first thermal runaway early warning instruction to a Vehicle Control Unit (VCU), and sending a high-voltage disconnection instruction to the VCU to actively stop battery charging or battery discharging; and if not, reporting that the smoke sensor has a fault according to the PWM frequency and the duty ratio.
Further, the VCU analyzes the smoke concentration data to determine whether to send out a first thermal runaway early warning instruction; the method specifically comprises the following steps:
(21) in a whole vehicle dormancy (parking) state, the smoke sensor works in a low-power-consumption working mode, and monitors the smoke concentration in the battery pack; the smoke sensor judges whether the smoke concentration in the battery pack exceeds a set threshold value, and if the smoke concentration exceeds the set threshold value, the smoke sensor outputs a high level to a Battery Management System (BMS);
(22) the battery management system BMS continuously judges whether the Wake-up signal Wake-up is at a high level; if not, judging that the battery management system BMS is in an initialization stage and the smoke sensor does not send out a wake-up signal; if yes, the battery management system BMS sends a signal Request from BMS to the smoke sensor to be in a high level, and meanwhile, the whole vehicle controller VCU is awakened through a network;
(23) the smoke sensor receives that the Request from BMS is high level, and sends PWM frequency and duty ratio to a battery management system BMS;
(24) the battery management system BMS receives the PWM frequency and the duty ratio, judges whether the frequency is a first threshold value or not, and enters (25) if the frequency is not the first threshold value; if so, entering (26);
(25) judging whether the frequency is a second threshold value, and reporting that the smoke sensor has a fault according to the PWM frequency and the duty ratio if the frequency is the second threshold value; if not, continuously judging whether the frequency is the second threshold value;
(26) judging whether the duty ratio reaches a duty ratio alarm threshold value, if so, sending a first thermal runaway early warning instruction; if not, reporting that the smoke sensor has a fault according to the PWM frequency and the duty ratio; the Request from BMS is set to a low level and the smoke sensor enters a low power mode.
Further, the cloud server determines whether to send a second thermal runaway early warning instruction according to data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; the method specifically comprises the following steps:
the cloud server uploads the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage in the battery pack, which are uploaded by the vehicle-mounted terminal;
preprocessing the temperature of a battery monomer in the battery pack, the pressure in the battery pack, the bus current and the bus voltage through a battery mechanism model to obtain an internal resistance abnormal score, a self-discharge abnormal score, an internal short circuit abnormal score and a temperature rise abnormal score; wherein the battery mechanism model comprises: an internal resistance model, a self-discharge model, an internal short circuit model and a temperature rise model;
and performing weight accumulation on the internal resistance abnormal value, the self-discharge abnormal value, the internal short circuit abnormal value and the temperature rise abnormal value in the preprocessing result, inputting the values into the trained thermal runaway early warning model, and outputting a classification result of whether thermal runaway occurs or not.
Further, the input values of the internal resistance model are bus current, battery state of charge (SOC) and battery cell voltage; the working principle of the internal resistance model is that data of a discharging working condition with SOC (state of charge) more than or equal to 30% and less than or equal to 80% are processed, if the code of the single battery with the maximum voltage change of the current frame voltage minus the last frame voltage when the bus current is maximum is the same as the code of the single battery with the maximum voltage change when the bus current is minimum, the internal resistance of the single battery is judged to be abnormal; and the output values of the internal resistance model are the code of the single battery and the abnormal value of the internal resistance.
Further, the input values of the self-discharge model are a battery state of charge (SOC) and a battery cell voltage; the working principle of the self-discharge model is that the monomer self-discharge abnormity can cause system level pressure difference abnormity, and the self-discharge characteristic is identified through the time dimension pressure difference stability; 1) a data source: extracting data segments corresponding to the SOC of more than or equal to 98 percent, the SOC of more than or equal to 50 percent and less than or equal to 60 percent and the SOC of more than or equal to 15 percent and less than or equal to 20 percent in each continuous charging process; 2) single charge difference calculation: respectively calculating the pressure difference mean value delta V after denoising of data segments with SOC more than or equal to 98%, SOC more than or equal to 50% and less than or equal to 60%, and SOC more than or equal to 15% and less than or equal to 20%; 3) calculating the daily differential pressure change rate of the corresponding time interval based on the charging SOC interval segment differential pressure corresponding to the time interval requirement (5 d-6 d, 10 d-11 d, 15 d-16 d) met by the time sequence query; 4) if the current model is not triggered by the set number of continuous charging times, judging the model to be normal, otherwise, judging the battery system to be abnormal in self-discharge; if the set times of continuous charging segments do not meet the calculation requirements, outputting is not performed; the output values of the self-discharge model are self-discharge abnormity of the battery system and self-discharge abnormity values.
Further, the input of the internal short circuit model is bus current, battery state of charge (SOC) and battery cell voltage, and the output is a cell code and an internal short circuit abnormal score.
Further, the input values of the temperature rise model are the temperature of a single battery, the state of charge (SOC) of the battery and a clock signal of the battery; the working principle of the temperature rise model is as follows: carrying out data processing on data under the charging/discharging working condition and with soc being more than or equal to 10% and less than or equal to 100%, and obtaining a temperature rise abnormal coefficient a if the temperature rise speed of the single battery is 2 ℃/S and is continuous for three times; continuously increasing the difference between the highest temperature of the single battery and the lowest temperature of the single battery and exceeding a certain threshold value to obtain a temperature rise abnormal coefficient b; if the highest temperature of the single battery continuously rises and exceeds a certain threshold value, obtaining a temperature rise abnormal coefficient c; comprehensively judging temperature rise abnormal coefficients a, b and c, and outputting the code number of the single battery with abnormal temperature rise and the abnormal temperature rise grade; and the output values of the temperature rise model are the code number of the single battery and the abnormal temperature rise value.
Further, the trained thermal runaway early warning model; the training process comprises the following steps:
constructing a convolutional neural network;
constructing a training set; the training set is battery historical monitoring data of electric vehicles of the same type and the same batch which are known to be subjected to thermal runaway labels after being taken off a production line; the battery history monitoring data comprises: the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage;
preprocessing the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage of the battery pack in the training set through a battery mechanism model to obtain an internal resistance abnormal score, a self-discharge abnormal score, an internal short circuit abnormal score and a temperature rise abnormal score; wherein the battery mechanism model comprises: an internal resistance model, a self-discharge model, an internal short circuit model and a temperature rise model;
and performing weight-based accumulation on the internal resistance abnormal value, the self-discharge abnormal value, the internal short circuit abnormal value and the temperature rise abnormal value in the preprocessing result, inputting the values into a convolutional neural network, training the network, and stopping training when the loss function value of the network is not reduced or reaches a set iteration number to obtain the trained convolutional neural network, namely the trained thermal runaway early warning model.
The technical scheme has the advantages that the historical monitoring data of the batteries of the same type and the same batch of electric vehicles after being taken off the production line are used as training data to train the model, the obtained thermal runaway early warning model has pertinence, and compared with the training data of the batteries of different types and different batches aiming at the batteries to be monitored, the model trained by the historical performance of the brother batteries can more accurately predict the performance of the current batteries of the same type and the same batch.
Further, determining whether to send out a thermal runaway alarm or not according to the two analysis results; the method specifically comprises the following steps:
if the two out-of-control early warning instructions are in early warning modes, determining to send out a thermal out-of-control alarm;
if one of the two out-of-control early warning instructions is in an early warning mode and the other one is in a non-early warning mode, a thermal out-of-control alarm is not sent out;
if the smoke sensor does not give an alarm, the battery early warning system gives an alarm, the charging and discharging power is actively reduced by half, and meanwhile, the battery pack cooling mode is started;
and if both of the two runaway early warning instructions are in a non-early warning mode, determining that a thermal runaway alarm is not sent out.
When the whole vehicle is in a driving mode, awakening the BMS through a K15 whole vehicle ignition hard wire signal, enabling the BMS to work in a non-sleep mode and interact with the smoke sensor in real time, and if the smoke concentration abnormal alarm is detected and the battery early warning system is in thermal runaway early warning, confirming the thermal runaway alarm;
when the whole vehicle is in a slow charging mode, awakening the BMS through a slow charging ignition hard wire signal, enabling the BMS to work in a non-sleep mode and interact with the smoke sensor in real time, and if the smoke concentration abnormal alarm is detected and the battery early warning system is in thermal runaway early warning, confirming the thermal runaway alarm;
when the whole vehicle is in a quick charging mode, waking up the BMS through a quick charging ignition hard wire signal, enabling the BMS to work in a non-sleep mode and interact with the smoke sensor in real time, and if the smoke concentration abnormal alarm is detected and the battery early warning system is in thermal runaway early warning, confirming the thermal runaway alarm;
when the whole vehicle is in an electricity mode under standing, the BMS works in a sleep mode, the BMS is awakened through a smoke sensor hard wire signal and interacts with the smoke sensor in real time, and if smoke concentration abnormal alarm is detected and thermal runaway early warning of a battery early warning system is detected, thermal runaway alarm is confirmed.
As shown in fig. 2, the BMS of the electric vehicle battery management system, the BMS of the battery early warning system, the smoke sensor and the VCU of the vehicle controller perform information interaction through the CAN of the vehicle and the TCP/IP network, respectively complete the warning of thermal runaway of the battery in the dormant state and the non-dormant state of the vehicle, the battery early warning module is a special battery early warning module on the enterprise data platform, based on the high temperature/temperature difference characteristic, the pressure characteristic, the power characteristic and the overvoltage/pressure difference characteristic collected by the temperature sensor, the current sensor, the voltage sensor and the pressure sensor for monitoring the whole life cycle inside the battery, and through the comprehensive processing of the battery mechanism model (internal resistance model, self-discharge model, internal short circuit model, temperature rise model, etc.) and the AI early warning model (battery high sensitivity characteristic, optimal algorithm model, etc.), the smoke concentration characteristic collected by the smoke sensor is combined, early warning and rapid warning of thermal runaway of the battery of the electric automobile are realized, and the early warning and the rapid warning are shown in an attached figure 3;
in the non-sleep state of the whole vehicle (driving, alternating current charging and direct current charging), the smoke sensor works in a continuous working mode, the smoke sensor, the battery early warning system and the BMS confirm necessary information by sending identification messages with the BMS, a thermal runaway alarm signal is sent at least 30 minutes before the thermal runaway happens, and the BMS sends identification messages on a VCU (vehicle control unit) and the BMS through both sides to complete the whole vehicle high-voltage disconnection and the whole vehicle acousto-optic alarm, which is shown in the attached figure 4;
under the whole vehicle dormancy (parking) state, the smoke sensor works in the low-power consumption working mode, the smoke sensor, the battery early warning system and the BMS confirm necessary information through sending identification messages with the BMS, a thermal runaway alarm signal is sent at least 30 minutes before the thermal runaway happens, the BMS wakes up the VCU through the network after confirming the thermal runaway fault, the VCU and the BMS send identification messages through both sides, and the whole vehicle high-voltage disconnection and the whole vehicle acousto-optic alarm are completed, see the attached figure 5.
The voltage difference represents the difference between the highest monomer voltage and the lowest monomer voltage acquired by the battery acquisition unit;
the temperature difference represents the difference between the highest monomer temperature and the lowest monomer temperature acquired by the battery acquisition unit;
the temperature rise represents an abnormal value of abnormal and rapid rise of the temperature of the single body collected by the battery collection unit;
the high temperature indicates that the temperature of the monomer collected by the battery collecting unit exceeds the upper limit value of the safe use temperature of the battery;
the overvoltage represents that the cell voltage collected by the cell collecting unit exceeds the lower limit value of the cell voltage.
Based on the high temperature/pressure difference characteristic, the pressure characteristic, the power characteristic and the overvoltage/pressure difference characteristic which are acquired by a temperature sensor, a current sensor, a voltage sensor and a pressure sensor for monitoring the full life cycle in the battery, the early warning and the quick warning of the thermal runaway of the battery of the electric automobile are realized by the comprehensive processing of a battery mechanism model (an internal resistance model, a self-discharge model, an internal short circuit model, a temperature rise model and the like) and an AI early warning model (a battery high sensitivity characteristic, an optimal algorithm model and the like) in combination with the smoke concentration characteristic acquired by the smoke sensor, and the following steps are shown in the attached drawing 3:
after the whole vehicle is off-line from the production line, the BMS monitors high-temperature/temperature difference characteristics, pressure characteristics, electric power characteristics and overvoltage/pressure difference characteristics in real time through a temperature sensor, a current sensor, a voltage sensor and a pressure sensor in a battery system, and uploads a vehicle-mounted terminal TBOX through a whole vehicle CAN, and the vehicle-mounted terminal TBOX is uploaded to an enterprise data platform through a TCP/IP network;
the battery early warning system is used as a special battery early warning module on an enterprise data platform, receives and stores high-temperature/temperature difference characteristic, pressure characteristic, power characteristic and overvoltage/pressure difference characteristic data of the full life cycle of the battery, and forms a battery full life cycle database;
based on a battery full life cycle database, a battery early warning system is formed through comprehensive processing of data cleaning, a battery mechanism model (an internal resistance model, a self-discharge model, an internal short circuit model, a temperature rise model and the like), an AI early warning model (a battery high sensitivity characteristic, an optimal algorithm model and the like), model training and model tuning, test data are added to judge whether the early warning system meets a target or not, if the requirement is not met, model optimization is continued, and if the requirement of the target is met, early warning of the battery system is carried out;
the battery early warning system starts to perform battery fault early warning, wherein the battery early warning comprises thermal runaway early warning, the battery early warning system transmits the thermal runaway early warning to TBOX through a TCP/IP network, and the TBOX is sent to the BMS through the CAN of the whole vehicle.
Electric automobile BMS, battery early warning system, smoke transducer and vehicle control unit VCU carry out the information interaction through whole car CAN and TCP/IP network, accomplish battery thermal runaway warning respectively under whole car dormancy state and whole car non-dormancy state, remind the passenger to keep away from the vehicle immediately through whole car audible-visual alarm at least 30 minutes before thermal runaway takes place:
under the state that the whole vehicle is not dormant (a driving mode, a slow charging mode and a fast charging mode), the BMS works in the non-dormant mode, the BMS, the battery early warning system and the smoke sensor carry out real-time information interaction, if smoke is not alarmed, the BMS actively limits half of charging/discharging power after receiving thermal runaway early warning information monitored by the battery early warning system, meanwhile, the cooling is requested to be started, if the smoke is alarmed and the battery early warning system reports thermal runaway early warning, the thermal runaway warning system confirms the thermal runaway warning and reports the thermal runaway warning to a VCU of the whole vehicle controller through a CAN of the whole vehicle, and the VCU carries out sound and light warning of the whole vehicle to remind passengers to immediately leave the vehicle;
under the whole vehicle dormancy (under static electricity) state, BMS work is under non-dormancy mode, and smoke sensor detects smoke and feels concentration anomaly and awakens up BMS immediately, and BMS, battery early warning system and smoke sensor carry out real-time information interaction, and thermal runaway alarm system real-time supervision and confirm the warning of thermal runaway to report whole vehicle control unit VCU warning of thermal runaway through whole vehicle CAN, VCU carries out whole vehicle acousto-optic warning and reminds the passenger to keep away from the vehicle immediately.
Under the whole car non-dormancy (driving mode, slow charge mode, fast charge mode) state, smoke transducer work is under continuous operation mode, through sending the identification message with the BMS, confirms smoke transducer, battery early warning system and BMS's necessary information, sends out thermal runaway alarm signal 30 minutes before thermal runaway takes place, and whole car controller VCU sends the identification message through both sides with the BMS, accomplishes whole car high-voltage disconnection and whole car audible-visual alarm, see figure 4:
in the non-sleep state (driving mode, slow charging mode and fast charging mode) of the whole vehicle, the BMS and the VCU work in the non-sleep mode, the BMS sends a Request from BMS to the smoke sensor to be at a high level, and then the smoke sensor works in the continuous working mode;
the monitoring period of the smoke sensor is 1S, and the frequency of the emitted PWM wave is a threshold value F 1 Hz duty cycle as threshold value D 1 ％；
BMS reads the PWM frequency and duty ratio of the smoke sensor, and continuously judges whether the PWM wave frequency is a threshold value F 1 Hz, if not, further judging whether the PWM wave frequency is a threshold value F 2 If the fault is Hz, reporting the fault of the smoke sensor according to the duty ratio of the PWM wave;
the smoke sensor monitors that the smoke concentration exceeds a threshold value C 1 μg/m 3 The frequency of the PWM wave becomes the threshold value F 1 Hz duty cycle as threshold value D 2 ％；
The frequency of PWM (pulse-width modulation) waves received by BMS (battery management system) and emitted by smoke sensor is a threshold value F 1 Hz, further judging the duty ratio of the PWM wave as a threshold value D 2 Percent, if not, reporting the self fault of the smoke sensor according to the duty ratio of the PWM wave; if so, further integrating thermal runaway early warning information in the battery early warning system, judging a thermal runaway alarm, reporting the thermal runaway alarm to a VCU (vehicle control unit) through a CAN (controller area network) of the whole vehicle, and actively disconnecting high voltage to stop charging/discharging the whole vehicle;
the VCU receives the BMS thermal runaway alarm signal, sends a whole vehicle high voltage disconnection instruction, and carries out whole vehicle sound-light alarm to remind passengers to immediately keep away from the vehicle.
Under whole car dormancy (under the static electricity) state, smoke transducer work is under low-power consumption mode, through sending the identification message with BMS, confirms smoke transducer, battery early warning system and BMS's necessary information, sends out thermal runaway alarm signal 30 minutes before the thermal runaway takes place, BMS is after confirming the thermal runaway trouble, awakens up VCU through the network, VCU and BMS send through both sides and distinguish the message, accomplish whole car high-voltage disconnection and whole car audible-visual alarm, see figure 4:
in a whole vehicle sleep (under static electricity) state, both the BMS and the VCU work in a sleep mode, and the smoke sensor works in a low power consumption mode;
the monitoring period of the smoke sensor is 12S and no PWM wave is provided;
the smoke sensor monitors that the smoke concentration exceeds the C threshold value by 1 mu g/m 3 The smoke sensor sends a Wake _ up signal to the BMS as a high level;
the BMS reads the Wake-up signal Wake _ up of the smoke sensor, whether the Wake-up signal Wake _ up is high level or not is continuously judged, if not, the BMS is judged to be in an initialization stage, and the smoke sensor does not send out the Wake-up signal Wake _ up; if yes, the BMS sends a signal Request from BMS to the smoke sensor to be in a high level, and meanwhile, the VCU of the whole vehicle controller is awakened through a network;
the smoke sensor receives that the Request from BMS is high level, and the frequency of the transmitted PWM wave becomes the threshold value F 1 Hz duty cycle as threshold value D 2 ％；
The frequency of PWM (pulse-width modulation) waves received by BMS (battery management system) and emitted by smoke sensor is a threshold value F 1 Hz, further judging the duty ratio of the PWM wave as a threshold value D 2 If not, reporting the self fault of the smoke sensor according to the duty ratio of the PWM wave, sending a Request from BMS as a high level, working in a low power consumption mode and sending Wake _ up as a low level when the smoke sensor receives the Request from BMS as the high level, and entering a sleep mode when the BMS receives the Wake _ up as the low level; if so, further integrating thermal runaway early warning information in the battery early warning system to judge the thermal runawayAlarming and reporting a VCU (vehicle control unit) thermal runaway alarm through a vehicle CAN (controller area network);
the VCU receives the BMS thermal runaway alarm signal and gives sound and light alarm to remind passengers to get away from the vehicle immediately.
Second, the present embodiment provides a battery management system BMS;
a battery management system BMS, comprising:
a first transmission module configured to: transmitting the smoke concentration data to a VCU (vehicle control unit); so that the VCU of the vehicle control unit analyzes the smoke concentration data to determine whether to send out a first thermal runaway early warning instruction; receiving an analysis result of a VCU of the vehicle controller;
a second transmission module configured to: transmitting data of different working modes acquired by the battery early warning system to a cloud server through a vehicle-mounted terminal T-BOX (telematics BOX); the cloud server determines whether to send a second thermal runaway early warning instruction or not according to the data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; receiving an analysis result of the cloud server through the vehicle-mounted terminal;
an output module configured to: and determining whether to send out a thermal runaway alarm or not according to the two analysis results.
Further, the cloud server determines whether to send a second thermal runaway early warning instruction according to data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; the method specifically comprises the following steps:
the cloud server uploads the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage in the battery pack, which are uploaded by the vehicle-mounted terminal;
preprocessing the temperature of a battery monomer in the battery pack, the pressure in the battery pack, the bus current and the bus voltage through a battery mechanism model to obtain an internal resistance abnormal score, a self-discharge abnormal score, an internal short circuit abnormal score and a temperature rise abnormal score; wherein, the battery mechanism model comprises: an internal resistance model, a self-discharge model, an internal short circuit model and a temperature rise model;
and performing weight accumulation on the internal resistance abnormal value, the self-discharge abnormal value, the internal short circuit abnormal value and the temperature rise abnormal value in the preprocessing result, inputting the values into the trained thermal runaway early warning model, and outputting a classification result of whether thermal runaway occurs or not.
Further, the input values of the internal resistance model are bus current, battery state of charge (SOC) and battery cell voltage; the working principle of the internal resistance model is that data of a discharging working condition with SOC (state of charge) more than or equal to 30% and less than or equal to 80% are processed, if the code of the single battery with the maximum voltage change of the current frame voltage minus the last frame voltage when the bus current is maximum is the same as the code of the single battery with the maximum voltage change when the bus current is minimum, the internal resistance of the single battery is judged to be abnormal; and the output values of the internal resistance model are the code of the single battery and the abnormal value of the internal resistance.
Further, the input values of the self-discharge model are the state of charge (SOC) of the battery and the voltage of the battery cell; the working principle of the self-discharge model is that the monomer self-discharge abnormity can cause system level pressure difference abnormity, and self-discharge characteristics are identified through time dimension pressure difference stability; 1) a data source: extracting data segments corresponding to the SOC of more than or equal to 98 percent, the SOC of more than or equal to 50 percent and less than or equal to 60 percent and the SOC of more than or equal to 15 percent and less than or equal to 20 percent in each continuous charging process; 2) single charge difference calculation: respectively calculating the pressure difference mean value delta V after denoising of data segments with SOC more than or equal to 98%, SOC more than or equal to 50% and less than or equal to 60%, and SOC more than or equal to 15% and less than or equal to 20%; 3) based on the time sequence query, the segment pressure difference of the corresponding charging SOC interval meeting the requirement of the set time interval is met, and the daily pressure difference change rate of the corresponding time interval is calculated; 4) if the current model is not triggered by the set number of continuous charging times, judging the model to be normal, otherwise, judging the battery system to be abnormal in self-discharge; if the set times of continuous charging segments do not meet the calculation requirements, outputting is not performed; the output values of the self-discharge model are self-discharge abnormity of the battery system and self-discharge abnormity values.
Further, the input values of the temperature rise model are the single battery temperature, the battery state of charge (SOC) and the battery clock signal; the working principle of the temperature rise model is as follows: carrying out data processing on data under the charging/discharging working condition and with soc being more than or equal to 10% and less than or equal to 100%, and obtaining a temperature rise abnormal coefficient a if the temperature rise speed of the single battery is 2 ℃/S and is continuous for three times; continuously increasing the difference between the highest temperature of the single battery and the lowest temperature of the single battery and exceeding a certain threshold value to obtain a temperature rise abnormal coefficient b; the maximum temperature of the single battery continuously rises and exceeds a certain threshold value, and then a temperature rise abnormal coefficient c is obtained; comprehensively judging temperature rise abnormal coefficients a, b and c, and outputting the code number of the single battery with abnormal temperature rise and the abnormal temperature rise grade; and the output values of the temperature rise model are the code number of the single battery and the abnormal temperature rise value.
Further, the trained thermal runaway early warning model; the training process comprises the following steps:
constructing a convolutional neural network;
constructing a training set; the training set is battery history monitoring data of electric vehicles of the same model and the same batch which are known to be subjected to the thermal runaway label or not after the electric vehicles are taken off a production line; the battery history monitoring data comprises: the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage;
preprocessing the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage of the battery pack in the training set through a battery mechanism model to obtain an internal resistance abnormal score, a self-discharge abnormal score, an internal short circuit abnormal score and a temperature rise abnormal score; wherein the battery mechanism model comprises: the device comprises an internal resistance model, a self-discharge model, an internal short circuit model and a temperature rise model;
and performing weight-based accumulation on the internal resistance abnormal value, the self-discharge abnormal value, the internal short circuit abnormal value and the temperature rise abnormal value in the preprocessing result, inputting the values into a convolutional neural network, training the network, and stopping training when the loss function value of the network is not reduced or reaches a set iteration number to obtain the trained convolutional neural network, namely the trained thermal runaway early warning model.
Further, determining whether to send out a thermal runaway alarm or not according to the two analysis results; the method specifically comprises the following steps:
if the two out-of-control early warning instructions are in early warning modes, determining to send out a thermal out-of-control alarm;
if one of the two out-of-control early warning instructions is in an early warning mode and the other one is in a non-early warning mode, a thermal out-of-control alarm is not sent out;
if the smoke sensor does not give an alarm, the battery early warning system gives an alarm, the charging and discharging power is actively halved, and a battery pack cooling mode is started;
and if both of the two runaway early warning instructions are in a non-early warning mode, determining that the thermal runaway alarm is not sent out.
Implementation details of each step in the second embodiment are correspondingly consistent with the first embodiment.
The third embodiment provides a thermal runaway alarm method for an electric vehicle battery;
an electric vehicle battery thermal runaway alarm method is applied to a vehicle control unit and comprises the following steps:
acquiring smoke concentration data;
analyzing the smoke concentration data to determine whether a first thermal runaway early warning instruction is sent out;
sending the first analysis result to a Battery Management System (BMS);
the auxiliary battery management system is combined with the first analysis result and the second analysis result to determine whether to send out a thermal runaway alarm;
the second analysis result is sent to the battery management system BMS by the cloud server through the vehicle-mounted terminal; the second analysis result is that the cloud server determines whether to send a second thermal runaway early warning instruction according to the data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; the data uploaded by the vehicle-mounted terminal are data acquired by different sensors in different working modes and acquired by the battery early warning system.
Further, the cloud server determines whether to send out a second thermal runaway early warning instruction or not according to the data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; the method specifically comprises the following steps:
the cloud server uploads the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage in the battery pack, which are uploaded by the vehicle-mounted terminal;
preprocessing the temperature of a battery monomer in the battery pack, the pressure in the battery pack, the bus current and the bus voltage through a battery mechanism model to obtain an internal resistance abnormal score, a self-discharge abnormal score, an internal short circuit abnormal score and a temperature rise abnormal score; wherein the battery mechanism model comprises: an internal resistance model, a self-discharge model, an internal short circuit model and a temperature rise model;
and performing weight accumulation on the internal resistance abnormal value, the self-discharge abnormal value, the internal short circuit abnormal value and the temperature rise abnormal value in the preprocessing result, inputting the values into the trained thermal runaway early warning model, and outputting a classification result of whether thermal runaway occurs or not.
Further, the input values of the internal resistance model are bus current, battery state of charge (SOC) and battery monomer voltage; the working principle of the internal resistance model is that data of a discharging working condition with SOC (state of charge) more than or equal to 30% and less than or equal to 80% are processed, if the code of the single battery with the maximum voltage change of the current frame voltage minus the last frame voltage when the bus current is maximum is the same as the code of the single battery with the maximum voltage change when the bus current is minimum, the internal resistance of the single battery is judged to be abnormal; and the output values of the internal resistance model are the code of the single battery and the abnormal value of the internal resistance.
Further, the input values of the self-discharge model are the state of charge (SOC) of the battery and the voltage of the battery cell; the working principle of the self-discharge model is that the monomer self-discharge abnormity can cause system level pressure difference abnormity, and the self-discharge characteristic is identified through the time dimension pressure difference stability; 1) a data source: extracting data segments corresponding to the SOC of more than or equal to 98 percent, the SOC of more than or equal to 50 percent and less than or equal to 60 percent and the SOC of more than or equal to 15 percent and less than or equal to 20 percent in each continuous charging process; 2) single charge difference calculation: respectively calculating the pressure difference mean value delta V after denoising of data segments with SOC more than or equal to 98%, SOC more than or equal to 50% and less than or equal to 60%, and SOC more than or equal to 15% and less than or equal to 20%; 3) based on the time sequence query, the segment pressure difference of the corresponding charging SOC interval meeting the requirement of the set time interval is met, and the daily pressure difference change rate of the corresponding time interval is calculated; 4) if the current model is not triggered by the set number of continuous charging, the model is judged to be normal, otherwise, the model is judged to be abnormal in self-discharge of the battery system; if the set times of continuous charging segments do not meet the calculation requirements, outputting the segments; the output values of the self-discharge model are self-discharge abnormity of the battery system and self-discharge abnormity values.
Further, the input values of the temperature rise model are the single battery temperature, the battery state of charge (SOC) and the battery clock signal; the working principle of the temperature rise model is as follows: carrying out data processing on data under the charging/discharging working condition and with soc being more than or equal to 10% and less than or equal to 100%, and obtaining a temperature rise abnormal coefficient a if the temperature rise speed of the single battery is 2 ℃/S and is continuous for three times; continuously increasing the difference between the highest temperature of the single battery and the lowest temperature of the single battery and exceeding a certain threshold value to obtain a temperature rise abnormal coefficient b; the maximum temperature of the single battery continuously rises and exceeds a certain threshold value, and then a temperature rise abnormal coefficient c is obtained; comprehensively judging temperature rise abnormal coefficients a, b and c, and outputting the code of the single battery with abnormal temperature rise and the abnormal temperature rise grade; and the output values of the temperature rise model are the code number of the single battery and the abnormal temperature rise value.
Further, the trained thermal runaway early warning model; the training process comprises the following steps:
constructing a convolutional neural network;
constructing a training set; the training set is battery historical monitoring data of electric vehicles of the same type and the same batch which are known to be subjected to thermal runaway labels after being taken off a production line; the battery history monitoring data comprises: the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage;
preprocessing the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage of the battery pack in the training set through a battery mechanism model to obtain an internal resistance abnormal score, a self-discharge abnormal score, an internal short circuit abnormal score and a temperature rise abnormal score; wherein the battery mechanism model comprises: the device comprises an internal resistance model, a self-discharge model, an internal short circuit model and a temperature rise model;
and performing weight-based accumulation on the internal resistance abnormal value, the self-discharge abnormal value, the internal short circuit abnormal value and the temperature rise abnormal value in the preprocessing result, inputting the values into a convolutional neural network, training the network, and stopping training when the loss function value of the network is not reduced or reaches a set iteration number to obtain the trained convolutional neural network, namely the trained thermal runaway early warning model.
Further, determining whether to send out a thermal runaway alarm or not according to the two analysis results; the method specifically comprises the following steps:
if the two out-of-control early warning instructions are in early warning modes, determining to send out a thermal out-of-control alarm;
if one of the two out-of-control early warning commands is in an early warning mode and the other one is in a non-early warning mode, a thermal out-of-control alarm is not sent out;
if the smoke sensor does not give an alarm, the battery early warning system gives an alarm, the charging and discharging power is actively reduced by half, and meanwhile, the battery pack cooling mode is started;
and if both of the two runaway early warning instructions are in a non-early warning mode, determining that the thermal runaway alarm is not sent out.
Implementation details of each step in the third embodiment are correspondingly consistent with the first embodiment.
In a fourth embodiment, the present embodiment provides a vehicle control unit;
vehicle control unit includes:
a first acquisition module configured to: acquiring smoke concentration data;
a first analysis module configured to: analyzing the smoke concentration data to determine whether a first thermal runaway early warning instruction is sent;
a first transmitting module configured to: sending the first analysis result to a Battery Management System (BMS);
a first determination module configured to: the auxiliary battery management system is combined with the first analysis result and the second analysis result to determine whether to send out a thermal runaway alarm;
the second analysis result is sent to the battery management system BMS by the cloud server through the vehicle-mounted terminal; the second analysis result is that the cloud server determines whether to send a second thermal runaway early warning instruction according to the data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; the data uploaded by the vehicle-mounted terminal are data acquired by different sensors in different working modes and acquired by the battery early warning system.
Further, the cloud server determines whether to send a second thermal runaway early warning instruction according to data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; the method specifically comprises the following steps:
the cloud server uploads the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage in the battery pack, which are uploaded by the vehicle-mounted terminal;
preprocessing the temperature of a battery monomer in the battery pack, the pressure in the battery pack, the bus current and the bus voltage through a battery mechanism model to obtain an internal resistance abnormal score, a self-discharge abnormal score, an internal short circuit abnormal score and a temperature rise abnormal score; wherein the battery mechanism model comprises: an internal resistance model, a self-discharge model, an internal short circuit model and a temperature rise model;
and performing weight accumulation on the internal resistance abnormal value, the self-discharge abnormal value, the internal short circuit abnormal value and the temperature rise abnormal value in the preprocessing result, inputting the values into the trained thermal runaway early warning model, and outputting a classification result of whether thermal runaway occurs or not.
Further, the input values of the internal resistance model are bus current, battery state of charge (SOC) and battery cell voltage; the working principle of the internal resistance model is that data of a discharging working condition with SOC (state of charge) more than or equal to 30% and less than or equal to 80% are processed, if the code of the single battery with the maximum voltage change of the current frame voltage minus the last frame voltage when the bus current is maximum is the same as the code of the single battery with the maximum voltage change when the bus current is minimum, the internal resistance of the single battery is judged to be abnormal; and the output values of the internal resistance model are the code of the single battery and the abnormal value of the internal resistance.
Further, the input values of the self-discharge model are the state of charge (SOC) of the battery and the voltage of the battery cell; the working principle of the self-discharge model is that the monomer self-discharge abnormity can cause system level pressure difference abnormity, and self-discharge characteristics are identified through time dimension pressure difference stability; 1) a data source: extracting data segments corresponding to the SOC of more than or equal to 98 percent, the SOC of more than or equal to 50 percent and less than or equal to 60 percent and the SOC of more than or equal to 15 percent and less than or equal to 20 percent in each continuous charging process; 2) single charge difference calculation: respectively calculating the pressure difference mean value delta V after denoising of data segments with SOC more than or equal to 98%, SOC more than or equal to 50% and less than or equal to 60%, and SOC more than or equal to 15% and less than or equal to 20%; 3) based on the time sequence query, the segment pressure difference of the corresponding charging SOC interval meeting the requirement of the set time interval is met, and the daily pressure difference change rate of the corresponding time interval is calculated; 4) if the current model is not triggered by the set number of continuous charging times, judging the model to be normal, otherwise, judging the battery system to be abnormal in self-discharge; if the set times of continuous charging segments do not meet the calculation requirements, outputting is not performed; the output values of the self-discharge model are self-discharge abnormity of the battery system and self-discharge abnormity values.
Further, the input values of the temperature rise model are the single battery temperature, the battery state of charge (SOC) and the battery clock signal; the working principle of the temperature rise model is as follows: carrying out data processing on data under the charging/discharging working condition and with soc being more than or equal to 10% and less than or equal to 100%, and obtaining a temperature rise abnormal coefficient a if the temperature rise speed of the single battery is 2 ℃/S and is continuous for three times; continuously increasing the difference between the highest temperature of the single battery and the lowest temperature of the single battery and exceeding a certain threshold value to obtain a temperature rise abnormal coefficient b; the maximum temperature of the single battery continuously rises and exceeds a certain threshold value, and then a temperature rise abnormal coefficient c is obtained; comprehensively judging temperature rise abnormal coefficients a, b and c, and outputting the code number of the single battery with abnormal temperature rise and the abnormal temperature rise grade; and the output values of the temperature rise model are the code number of the single battery and the abnormal temperature rise value.
Further, the trained thermal runaway early warning model; the training process comprises the following steps:
constructing a convolutional neural network;
constructing a training set; the training set is battery history monitoring data of electric vehicles of the same model and the same batch which are known to be subjected to the thermal runaway label or not after the electric vehicles are taken off a production line; the battery history monitoring data comprises: the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage;
preprocessing the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage of the battery pack in the training set through a battery mechanism model to obtain an internal resistance abnormal score, a self-discharge abnormal score, an internal short circuit abnormal score and a temperature rise abnormal score; wherein the battery mechanism model comprises: the device comprises an internal resistance model, a self-discharge model, an internal short circuit model and a temperature rise model;
and performing weight-based accumulation on the internal resistance abnormal value, the self-discharge abnormal value, the internal short circuit abnormal value and the temperature rise abnormal value in the preprocessing result, inputting the values into a convolutional neural network, training the network, and stopping training when the loss function value of the network is not reduced or reaches a set iteration number to obtain the trained convolutional neural network, namely the trained thermal runaway early warning model.
Further, determining whether to send out a thermal runaway alarm or not according to the two analysis results; the method specifically comprises the following steps:
if the two out-of-control early warning instructions are in early warning modes, determining to send out a thermal out-of-control alarm;
if one of the two out-of-control early warning instructions is in an early warning mode and the other one is in a non-early warning mode, a thermal out-of-control alarm is not sent out;
if the smoke sensor does not give an alarm, the battery early warning system gives an alarm, the charging and discharging power is actively reduced by half, and meanwhile, the battery pack cooling mode is started;
and if both of the two runaway early warning instructions are in a non-early warning mode, determining that a thermal runaway alarm is not sent out.
Implementation details of each step in the fourth embodiment are correspondingly consistent with the first embodiment.
Fifth, the present embodiment provides a method for alarming thermal runaway of a battery of an electric vehicle;
an electric vehicle battery thermal runaway alarm method is applied to a cloud server and comprises the following steps:
acquiring data in different working modes and different modes;
determining a second analysis result based on data of different working modes and different modes and the trained thermal runaway early warning model; the second analysis result indicates whether a second thermal runaway early warning instruction is sent;
sending the determined second analysis result to a Battery Management System (BMS) through the vehicle-mounted terminal;
the auxiliary battery management system is combined with the first analysis result and the second analysis result to determine whether to send out a thermal runaway alarm or not;
the data of different working modes and different modes are collected by different sensors and are uploaded to the cloud server through the battery management system BMS and the vehicle-mounted terminal in sequence; the first analysis result is obtained by analyzing smoke concentration data by the VCU of the vehicle control unit; the first analysis result indicates whether a first thermal runaway early warning instruction is sent; the smoke concentration data are collected by the smoke sensor and uploaded to the VCU through the BMS.
Further, the cloud server determines whether to send a second thermal runaway early warning instruction according to data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; the method specifically comprises the following steps:
the cloud server uploads the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage in the battery pack, which are uploaded by the vehicle-mounted terminal;
preprocessing the temperature of a battery monomer in the battery pack, the pressure in the battery pack, the bus current and the bus voltage through a battery mechanism model to obtain an internal resistance abnormal score, a self-discharge abnormal score, an internal short circuit abnormal score and a temperature rise abnormal score; wherein the battery mechanism model comprises: an internal resistance model, a self-discharge model, an internal short circuit model and a temperature rise model;
and performing weight accumulation on the internal resistance abnormal value, the self-discharge abnormal value, the internal short circuit abnormal value and the temperature rise abnormal value in the preprocessing result, inputting the values into the trained thermal runaway early warning model, and outputting a classification result of whether thermal runaway occurs or not.
Further, the input values of the internal resistance model are bus current, battery state of charge (SOC) and battery monomer voltage; the working principle of the internal resistance model is that data of a discharging working condition with SOC (state of charge) more than or equal to 30% and less than or equal to 80% are processed, if the code of the single battery with the maximum voltage change of the current frame voltage minus the last frame voltage when the bus current is maximum is the same as the code of the single battery with the maximum voltage change when the bus current is minimum, the internal resistance of the single battery is judged to be abnormal; and the output values of the internal resistance model are the code of the single battery and the abnormal value of the internal resistance.
Further, the input values of the self-discharge model are the state of charge (SOC) of the battery and the voltage of the battery cell; the working principle of the self-discharge model is that the monomer self-discharge abnormity can cause system level pressure difference abnormity, and self-discharge characteristics are identified through time dimension pressure difference stability; 1) a data source: extracting data segments corresponding to the SOC of more than or equal to 98 percent, the SOC of more than or equal to 50 percent and less than or equal to 60 percent and the SOC of more than or equal to 15 percent and less than or equal to 20 percent in each continuous charging process; 2) single charge difference calculation: respectively calculating the pressure difference mean value delta V after denoising of data segments with SOC more than or equal to 98%, SOC more than or equal to 50% and less than or equal to 60%, and SOC more than or equal to 15% and less than or equal to 20%; 3) based on the time sequence query, the segment pressure difference of the corresponding charging SOC interval meeting the requirement of the set time interval is met, and the daily pressure difference change rate of the corresponding time interval is calculated; 4) if the current model is not triggered by the set number of continuous charging times, judging the model to be normal, otherwise, judging the battery system to be abnormal in self-discharge; if the set times of continuous charging segments do not meet the calculation requirements, outputting is not performed; the output values of the self-discharge model are self-discharge abnormity of the battery system and self-discharge abnormity values.
Further, the input values of the temperature rise model are the single battery temperature, the battery state of charge (SOC) and the battery clock signal; the working principle of the temperature rise model is as follows: carrying out data processing on data under the charging/discharging working condition and with soc being more than or equal to 10% and less than or equal to 100%, and obtaining a temperature rise abnormal coefficient a if the temperature rise speed of the single battery is 2 ℃/S and is continuous for three times; continuously increasing the difference between the highest temperature of the single battery and the lowest temperature of the single battery and exceeding a certain threshold value to obtain a temperature rise abnormal coefficient b; the maximum temperature of the single battery continuously rises and exceeds a certain threshold value, and then a temperature rise abnormal coefficient c is obtained; comprehensively judging temperature rise abnormal coefficients a, b and c, and outputting the code number of the single battery with abnormal temperature rise and the abnormal temperature rise grade; and the output values of the temperature rise model are the code number of the single battery and the abnormal temperature rise value.
Further, the trained thermal runaway early warning model; the training process comprises the following steps:
constructing a convolutional neural network;
constructing a training set; the training set is battery history monitoring data of electric vehicles of the same model and the same batch which are known to be subjected to the thermal runaway label or not after the electric vehicles are taken off a production line; the battery history monitoring data comprises: the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage;
preprocessing the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage of the battery pack in the training set through a battery mechanism model to obtain an internal resistance abnormal score, a self-discharge abnormal score, an internal short circuit abnormal score and a temperature rise abnormal score; wherein the battery mechanism model comprises: the device comprises an internal resistance model, a self-discharge model, an internal short circuit model and a temperature rise model;
and performing weight-based accumulation on the internal resistance abnormal value, the self-discharge abnormal value, the internal short circuit abnormal value and the temperature rise abnormal value in the preprocessing result, inputting the values into a convolutional neural network, training the network, and stopping training when the loss function value of the network is not reduced or reaches a set iteration number to obtain the trained convolutional neural network, namely the trained thermal runaway early warning model.
Further, determining whether to send out a thermal runaway alarm or not according to the two analysis results; the method specifically comprises the following steps:
if the two out-of-control early warning instructions are in early warning modes, determining to send out a thermal out-of-control alarm;
if one of the two out-of-control early warning instructions is in an early warning mode and the other one is in a non-early warning mode, a thermal out-of-control alarm is not sent out;
if the smoke sensor does not give an alarm, the battery early warning system gives an alarm, the charging and discharging power is actively reduced by half, and meanwhile, the battery pack cooling mode is started;
and if both of the two runaway early warning instructions are in a non-early warning mode, determining that a thermal runaway alarm is not sent out.
Implementation details of each step in the fifth embodiment are correspondingly consistent with the first embodiment.
Sixth, the present embodiment provides a cloud server;
a cloud server, comprising:
a second acquisition module configured to: acquiring data in different working modes and different modes;
a second analysis module configured to: determining a second analysis result based on data of different working modes and different modes and the trained thermal runaway early warning model; the second analysis result indicates whether a second thermal runaway early warning instruction is sent;
a second transmitting module configured to: sending the determined second analysis result to a Battery Management System (BMS) through the vehicle-mounted terminal;
a second determination module configured to: the auxiliary battery management system is combined with the first analysis result and the second analysis result to determine whether to send out a thermal runaway alarm;
the data of different working modes and different modes are collected by different sensors and are uploaded to the cloud server through the battery management system BMS and the vehicle-mounted terminal in sequence; the first analysis result is obtained by analyzing smoke concentration data by the VCU of the vehicle control unit; the first analysis result indicates whether a first thermal runaway early warning instruction is sent; the smoke concentration data are collected by the smoke sensor and uploaded to the VCU through the BMS.
Further, the cloud server determines whether to send a second thermal runaway early warning instruction according to data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; the method specifically comprises the following steps:
the cloud server uploads the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage in the battery pack, which are uploaded by the vehicle-mounted terminal;
preprocessing the temperature of a battery monomer in the battery pack, the pressure in the battery pack, the bus current and the bus voltage through a battery mechanism model to obtain an internal resistance abnormal score, a self-discharge abnormal score, an internal short circuit abnormal score and a temperature rise abnormal score; wherein the battery mechanism model comprises: an internal resistance model, a self-discharge model, an internal short circuit model and a temperature rise model;
and performing weight accumulation on the internal resistance abnormal value, the self-discharge abnormal value, the internal short circuit abnormal value and the temperature rise abnormal value in the preprocessing result, inputting the values into the trained thermal runaway early warning model, and outputting a classification result of whether thermal runaway occurs or not.
Further, the input values of the internal resistance model are bus current, battery state of charge (SOC) and battery cell voltage; the working principle of the internal resistance model is that data of a discharging working condition with SOC (state of charge) more than or equal to 30% and less than or equal to 80% are processed, if the code of the single battery with the maximum voltage change of the current frame voltage minus the last frame voltage when the bus current is maximum is the same as the code of the single battery with the maximum voltage change when the bus current is minimum, the internal resistance of the single battery is judged to be abnormal; and the output values of the internal resistance model are the code of the single battery and the abnormal value of the internal resistance.
Further, in the self-discharge model, the input values are the state of charge (SOC) of the battery and the voltage of a single battery; the working principle of the self-discharge model is that the monomer self-discharge abnormity can cause system level pressure difference abnormity, and self-discharge characteristics are identified through time dimension pressure difference stability; 1) a data source: extracting data segments corresponding to the SOC of more than or equal to 98 percent, the SOC of more than or equal to 50 percent and less than or equal to 60 percent and the SOC of more than or equal to 15 percent and less than or equal to 20 percent in each continuous charging process; 2) single charge difference calculation: respectively calculating the pressure difference mean value delta V after denoising of data segments with SOC more than or equal to 98%, SOC more than or equal to 50% and less than or equal to 60%, and SOC more than or equal to 15% and less than or equal to 20%; 3) based on the time sequence query, the segment pressure difference of the corresponding charging SOC interval meeting the requirement of the set time interval is met, and the daily pressure difference change rate of the corresponding time interval is calculated; 4) if the current model is not triggered by the set number of continuous charging times, judging the model to be normal, otherwise, judging the battery system to be abnormal in self-discharge; if the set times of continuous charging segments do not meet the calculation requirements, outputting is not performed; the output values of the self-discharge model are self-discharge abnormity of the battery system and self-discharge abnormity values.
Further, the input values of the temperature rise model are the single battery temperature, the battery state of charge (SOC) and the battery clock signal; the working principle of the temperature rise model is as follows: carrying out data processing on data under the charging/discharging working condition and with soc being more than or equal to 10% and less than or equal to 100%, and obtaining a temperature rise abnormal coefficient a if the temperature rise speed of the single battery is 2 ℃/S and is continuous for three times; continuously increasing the difference between the highest temperature of the single battery and the lowest temperature of the single battery and exceeding a certain threshold value to obtain a temperature rise abnormal coefficient b; the maximum temperature of the single battery continuously rises and exceeds a certain threshold value, and then a temperature rise abnormal coefficient c is obtained; comprehensively judging temperature rise abnormal coefficients a, b and c, and outputting the code of the single battery with abnormal temperature rise and the abnormal temperature rise grade; and the output values of the temperature rise model are the code number of the single battery and the abnormal temperature rise value.
Further, the trained thermal runaway early warning model; the training process comprises the following steps:
constructing a convolutional neural network;
constructing a training set; the training set is battery history monitoring data of electric vehicles of the same model and the same batch which are known to be subjected to the thermal runaway label or not after the electric vehicles are taken off a production line; the battery history monitoring data comprises: the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage;
preprocessing the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage of the battery pack in the training set through a battery mechanism model to obtain an internal resistance abnormal score, a self-discharge abnormal score, an internal short circuit abnormal score and a temperature rise abnormal score; wherein the battery mechanism model comprises: the device comprises an internal resistance model, a self-discharge model, an internal short circuit model and a temperature rise model;
and performing weight-based accumulation on the internal resistance abnormal value, the self-discharge abnormal value, the internal short circuit abnormal value and the temperature rise abnormal value in the preprocessing result, inputting the values into a convolutional neural network, training the network, and stopping training when the loss function value of the network is not reduced or reaches a set iteration number to obtain the trained convolutional neural network, namely the trained thermal runaway early warning model.
Further, determining whether to send out a thermal runaway alarm or not according to the two analysis results; the method specifically comprises the following steps:
if the two out-of-control early warning instructions are in early warning modes, determining to send out a thermal out-of-control alarm;
if one of the two out-of-control early warning instructions is in an early warning mode and the other one is in a non-early warning mode, a thermal out-of-control alarm is not sent out;
if the smoke sensor does not give an alarm, the battery early warning system gives an alarm, the charging and discharging power is actively reduced by half, and meanwhile, the battery pack cooling mode is started;
and if both of the two runaway early warning instructions are in a non-early warning mode, determining that a thermal runaway alarm is not sent out.
Implementation details of each step in the sixth embodiment are correspondingly consistent with the first embodiment.
The seventh embodiment further provides a thermal runaway alarm system for an electric vehicle battery;
an electric vehicle battery thermal runaway alarm system, comprising: the system comprises a battery management system BMS, a vehicle control unit VCU and a cloud server;
the battery management system BMS transmits the smoke concentration data to a VCU (vehicle control unit); the VCU analyzes the smoke concentration data to determine whether a first thermal runaway early warning instruction is sent out;
the battery management system BMS transmits data of different working modes acquired by the battery early warning system to a vehicle-mounted terminal T-BOX (telematics BOX); the vehicle-mounted terminal transmits the data to the cloud server, and the cloud server determines whether to send out a second thermal runaway early warning instruction or not according to the data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model;
and the battery management system BMS determines whether to send out a thermal runaway alarm or not according to the two runaway early warning instructions.
Further, the cloud server determines whether to send a second thermal runaway early warning instruction according to data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; the method specifically comprises the following steps:
the cloud server uploads the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage in the battery pack, which are uploaded by the vehicle-mounted terminal;
preprocessing the temperature of a battery monomer in the battery pack, the pressure in the battery pack, the bus current and the bus voltage through a battery mechanism model to obtain an internal resistance abnormal score, a self-discharge abnormal score, an internal short circuit abnormal score and a temperature rise abnormal score; wherein the battery mechanism model comprises: an internal resistance model, a self-discharge model, an internal short circuit model and a temperature rise model;
and performing weighted accumulation on the internal resistance abnormal value, the self-discharge abnormal value, the internal short circuit abnormal value and the temperature rise abnormal value in the preprocessing result, inputting the values into the trained thermal runaway early warning model, and outputting a classification result of whether thermal runaway occurs or not.
Further, the input values of the internal resistance model are bus current, battery state of charge (SOC) and battery monomer voltage; the working principle of the internal resistance model is that data processing is carried out on data under the discharging working condition and the SOC (system on chip) of more than or equal to 30% and less than or equal to 80%, if the code of the single battery with the maximum voltage change of the voltage of the previous frame subtracted from the voltage of the current frame when the bus current is maximum is the same as the code of the single battery with the maximum voltage change when the bus current is minimum, the internal resistance of the single battery is judged to be abnormal; and the output values of the internal resistance model are the code of the single battery and the abnormal value of the internal resistance.
Further, the input values of the self-discharge model are the state of charge (SOC) of the battery and the voltage of the battery cell; the working principle of the self-discharge model is that the monomer self-discharge abnormity can cause system level pressure difference abnormity, and self-discharge characteristics are identified through time dimension pressure difference stability; 1) a data source: extracting data segments corresponding to the SOC of more than or equal to 98 percent, the SOC of more than or equal to 50 percent and less than or equal to 60 percent and the SOC of more than or equal to 15 percent and less than or equal to 20 percent in each continuous charging process; 2) single charge difference calculation: respectively calculating the pressure difference mean value delta V after denoising of data segments with SOC more than or equal to 98%, SOC more than or equal to 50% and less than or equal to 60%, and SOC more than or equal to 15% and less than or equal to 20%; 3) based on the time sequence query, the segment pressure difference of the corresponding charging SOC interval meeting the requirement of the set time interval is met, and the daily pressure difference change rate of the corresponding time interval is calculated; 4) if the current model is not triggered by the set number of continuous charging times, judging the model to be normal, otherwise, judging the battery system to be abnormal in self-discharge; if the set times of continuous charging segments do not meet the calculation requirements, outputting is not performed; the output values of the self-discharge model are self-discharge abnormity of the battery system and self-discharge abnormity values.
Further, the input values of the temperature rise model are the single battery temperature, the battery state of charge (SOC) and the battery clock signal; the working principle of the temperature rise model is as follows: carrying out data processing on data under the charging/discharging working condition, wherein the soc is more than or equal to 10% and less than or equal to 100%, and if the temperature rise speed of a single battery is 2 ℃/S and is continuously carried out for three times, obtaining a temperature rise abnormal coefficient a; continuously increasing the difference between the highest temperature of the single battery and the lowest temperature of the single battery and exceeding a certain threshold value to obtain a temperature rise abnormal coefficient b; the maximum temperature of the single battery continuously rises and exceeds a certain threshold value, and then a temperature rise abnormal coefficient c is obtained; comprehensively judging temperature rise abnormal coefficients a, b and c, and outputting the code of the single battery with abnormal temperature rise and the abnormal temperature rise grade; and the output values of the temperature rise model are the code number of the single battery and the abnormal temperature rise value.
Further, the trained thermal runaway early warning model; the training process comprises the following steps:
constructing a convolutional neural network;
constructing a training set; the training set is battery historical monitoring data of electric vehicles of the same type and the same batch which are known to be subjected to thermal runaway labels after being taken off a production line; the battery history monitoring data comprises: the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage;
preprocessing the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage of the battery pack in the training set through a battery mechanism model to obtain an internal resistance abnormal score, a self-discharge abnormal score, an internal short circuit abnormal score and a temperature rise abnormal score; wherein the battery mechanism model comprises: an internal resistance model, a self-discharge model, an internal short circuit model and a temperature rise model;
and performing weight-based accumulation on the internal resistance abnormal value, the self-discharge abnormal value, the internal short circuit abnormal value and the temperature rise abnormal value in the preprocessing result, inputting the values into a convolutional neural network, training the network, and stopping training when the loss function value of the network is not reduced or reaches a set iteration number to obtain the trained convolutional neural network, namely the trained thermal runaway early warning model.
Further, determining whether to send out a thermal runaway alarm or not according to the two analysis results; the method specifically comprises the following steps:
if the two out-of-control early warning instructions are in early warning modes, determining to send out a thermal out-of-control alarm;
if one of the two out-of-control early warning instructions is in an early warning mode and the other one is in a non-early warning mode, a thermal out-of-control alarm is not sent out;
if the smoke sensor does not give an alarm, the battery early warning system gives an alarm, the charging and discharging power is actively reduced by half, and meanwhile, the battery pack cooling mode is started;
and if both of the two runaway early warning instructions are in a non-early warning mode, determining that a thermal runaway alarm is not sent out.
Implementation details of each step in the seventh embodiment are correspondingly consistent with the first embodiment.
Eighth embodiment, this embodiment provides an electronic device;
an electronic device, comprising:
a memory for non-transitory storage of computer readable instructions; and
a processor for executing the computer readable instructions,
wherein the computer readable instructions, when executed by the processor, perform the method of embodiment one, three, or five above.
Implementation details of each step in the eighth embodiment are correspondingly consistent with the first embodiment.
The ninth embodiment further provides a storage medium that stores non-transitory computer-readable instructions, wherein the non-transitory computer-readable instructions, when executed by a computer, perform the instructions of the methods of the first, third or fifth embodiments.
Implementation details of each step in the ninth embodiment are correspondingly consistent with the first embodiment.
Tenth embodiment, the present embodiment also provides a computer program product comprising a computer program for implementing the method of the first, third or fifth embodiment when the computer program runs on one or more processors.
Implementation details of each step in the tenth embodiment are correspondingly consistent with the first embodiment.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (16)

1. A thermal runaway alarm method for an electric vehicle battery is characterized by being applied to a battery management system BMS and comprising the following steps:
transmitting the smoke concentration data to a VCU (vehicle control unit); so that the VCU of the vehicle control unit analyzes the smoke concentration data to determine whether to send out a first thermal runaway early warning instruction; receiving an analysis result of a VCU of the vehicle controller;
transmitting data of different working modes acquired by the battery early warning system to a cloud server through a vehicle-mounted terminal T-BOX; the cloud server determines whether to send a second thermal runaway early warning instruction or not according to the data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; receiving an analysis result of the cloud server through the vehicle-mounted terminal;
and determining whether to send out a thermal runaway alarm or not according to the two analysis results.
2. The electric vehicle battery thermal runaway alarm method as claimed in claim 1, wherein the cloud server determines whether to send a second thermal runaway early warning instruction according to data uploaded by the vehicle-mounted terminal and a trained thermal runaway early warning model; the method specifically comprises the following steps:
the cloud server uploads the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage in the battery pack, which are uploaded by the vehicle-mounted terminal;
preprocessing the temperature of a battery monomer in the battery pack, the pressure in the battery pack, the bus current and the bus voltage through a battery mechanism model to obtain an internal resistance abnormal score, a self-discharge abnormal score, an internal short circuit abnormal score and a temperature rise abnormal score; wherein the battery mechanism model comprises: the device comprises an internal resistance model, a self-discharge model, an internal short circuit model and a temperature rise model;
and performing weighted accumulation on the internal resistance abnormal value, the self-discharge abnormal value, the internal short circuit abnormal value and the temperature rise abnormal value in the preprocessing result, inputting the values into the trained thermal runaway early warning model, and outputting a classification result of whether thermal runaway occurs or not.
3. The method for alarming thermal runaway of an electric vehicle battery as claimed in claim 2, wherein the input values of the internal resistance model are bus current, battery state of charge (SOC) and battery cell voltage; the working principle of the internal resistance model is that data of a discharging working condition with SOC (state of charge) more than or equal to 30% and less than or equal to 80% are processed, if the code of the single battery with the maximum voltage change of the current frame voltage minus the last frame voltage when the bus current is maximum is the same as the code of the single battery with the maximum voltage change when the bus current is minimum, the internal resistance of the single battery is judged to be abnormal; and the output values of the internal resistance model are the code of the single battery and the abnormal value of the internal resistance.
4. The warning method for the thermal runaway of the battery of the electric automobile as claimed in claim 2, wherein the input values of the self-discharge model are the state of charge (SOC) of the battery and the voltage of a single battery; the working principle of the self-discharge model is that the monomer self-discharge abnormity can cause system level pressure difference abnormity, and self-discharge characteristics are identified through time dimension pressure difference stability; 1) a data source: extracting data segments corresponding to the SOC of more than or equal to 98 percent, the SOC of more than or equal to 50 percent and less than or equal to 60 percent and the SOC of more than or equal to 15 percent and less than or equal to 20 percent in each continuous charging process; 2) single charge difference calculation: respectively calculating the pressure difference mean value delta V after denoising of data segments with SOC more than or equal to 98%, SOC more than or equal to 50% and less than or equal to 60%, and SOC more than or equal to 15% and less than or equal to 20%; 3) based on the time sequence query, the segment pressure difference of the corresponding charging SOC interval meeting the requirement of the set time interval is met, and the daily pressure difference change rate of the corresponding time interval is calculated; 4) if the current model is not triggered by the set number of continuous charging times, judging the model to be normal, otherwise, judging the battery system to be abnormal in self-discharge; if the set times of continuous charging segments do not meet the calculation requirements, outputting the segments; the output values of the self-discharge model are self-discharge abnormity of the battery system and self-discharge abnormity values.
5. The warning method for the thermal runaway of the battery of the electric automobile as claimed in claim 2, wherein the input values of the temperature rise model are the temperature of the battery cell, the state of charge (SOC) of the battery and a clock signal of the battery; the working principle of the temperature rise model is as follows: carrying out data processing on data under the charging/discharging working condition and with soc being more than or equal to 10% and less than or equal to 100%, and obtaining a temperature rise abnormal coefficient a if the temperature rise speed of the single battery is 2 ℃/S and is continuous for three times; continuously increasing the difference between the highest temperature of the single battery and the lowest temperature of the single battery and exceeding a certain threshold value to obtain a temperature rise abnormal coefficient b; the maximum temperature of the single battery continuously rises and exceeds a certain threshold value, and then a temperature rise abnormal coefficient c is obtained; comprehensively judging temperature rise abnormal coefficients a, b and c, and outputting the code of the single battery with abnormal temperature rise and the abnormal temperature rise grade; and the output values of the temperature rise model are the code number of the single battery and the abnormal temperature rise value.
6. The warning method for the thermal runaway of the battery of the electric automobile as claimed in claim 1, wherein the trained thermal runaway early warning model; the training process comprises the following steps:
constructing a convolutional neural network;
constructing a training set; the training set is battery history monitoring data of electric vehicles of the same model and the same batch which are known to be subjected to the thermal runaway label or not after the electric vehicles are taken off a production line; the battery history monitoring data comprises: the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage;
preprocessing the temperature of a single battery in the battery pack, the pressure in the battery pack, the bus current and the bus voltage of the battery pack in the training set through a battery mechanism model to obtain an internal resistance abnormal score, a self-discharge abnormal score, an internal short circuit abnormal score and a temperature rise abnormal score; wherein the battery mechanism model comprises: the device comprises an internal resistance model, a self-discharge model, an internal short circuit model and a temperature rise model;
and performing weight-based accumulation on the internal resistance abnormal value, the self-discharge abnormal value, the internal short circuit abnormal value and the temperature rise abnormal value in the preprocessing result, inputting the values into a convolutional neural network, training the network, and stopping training when the loss function value of the network is not reduced or reaches a set iteration number to obtain the trained convolutional neural network, namely the trained thermal runaway early warning model.
7. The warning method for the thermal runaway of the battery of the electric automobile as claimed in claim 1, wherein whether to give a warning for the thermal runaway is determined according to the two analysis results; the method specifically comprises the following steps:
if the two out-of-control early warning instructions are in early warning modes, determining to send out a thermal out-of-control alarm;
if one of the two out-of-control early warning instructions is in an early warning mode and the other one is in a non-early warning mode, a thermal out-of-control alarm is not sent out;
if the smoke sensor does not give an alarm, the battery early warning system gives an alarm, the charging and discharging power is actively reduced by half, and meanwhile, the battery pack cooling mode is started;
and if both of the two runaway early warning instructions are in a non-early warning mode, determining that a thermal runaway alarm is not sent out.
8. A battery management system BMS, comprising:
a first transmission module configured to: transmitting the smoke concentration data to a VCU (vehicle control unit); so that the VCU of the vehicle control unit analyzes the smoke concentration data to determine whether to send out a first thermal runaway early warning instruction; receiving an analysis result of a VCU of the vehicle controller;
a second transmission module configured to: transmitting data of different working modes acquired by the battery early warning system to a cloud server through a vehicle-mounted terminal T-BOX; the cloud server determines whether to send out a second thermal runaway early warning instruction or not according to the data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; receiving an analysis result of the cloud server through the vehicle-mounted terminal;
an output module configured to: and determining whether to send out a thermal runaway alarm or not according to the two analysis results.
9. An electric vehicle battery thermal runaway alarm method is characterized by being applied to a vehicle control unit and comprising the following steps:
acquiring smoke concentration data;
analyzing the smoke concentration data to determine whether a first thermal runaway early warning instruction is sent;
sending the first analysis result to a Battery Management System (BMS);
the auxiliary battery management system is combined with the first analysis result and the second analysis result to determine whether to send out a thermal runaway alarm;
the second analysis result is sent to a battery management system BMS by the cloud server through the vehicle-mounted terminal; the second analysis result is that the cloud server determines whether to send a second thermal runaway early warning instruction according to the data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; the data uploaded by the vehicle-mounted terminal are data acquired by different sensors in different working modes and acquired by the battery early warning system.
10. Vehicle control unit, characterized by includes:
a first acquisition module configured to: acquiring smoke concentration data;
a first analysis module configured to: analyzing the smoke concentration data to determine whether a first thermal runaway early warning instruction is sent;
a first transmitting module configured to: sending the first analysis result to a Battery Management System (BMS);
a first determination module configured to: the auxiliary battery management system is combined with the first analysis result and the second analysis result to determine whether to send out a thermal runaway alarm;
the second analysis result is sent to the battery management system BMS by the cloud server through the vehicle-mounted terminal; the second analysis result is that the cloud server determines whether to send out a second thermal runaway early warning instruction according to the data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model; the data uploaded by the vehicle-mounted terminal are data acquired by different sensors in different working modes and acquired by the battery early warning system.
11. An electric vehicle battery thermal runaway alarm method is characterized by being applied to a cloud server and comprising the following steps:
acquiring data of different working modes and different modes;
determining a second analysis result based on data of different working modes and different modes and the trained thermal runaway early warning model; the second analysis result indicates whether a second thermal runaway early warning instruction is sent;
sending the determined second analysis result to a Battery Management System (BMS) through the vehicle-mounted terminal;
the auxiliary battery management system is combined with the first analysis result and the second analysis result to determine whether to send out a thermal runaway alarm;
the data of different working modes and different modes are collected by different sensors and are uploaded to the cloud server through the battery management system BMS and the vehicle-mounted terminal in sequence; the first analysis result is obtained by analyzing smoke concentration data by the VCU of the vehicle control unit; the first analysis result indicates whether a first thermal runaway early warning instruction is sent; the smoke concentration data are collected by the smoke sensor and uploaded to the VCU through the BMS.
12. A cloud server, comprising:
a second acquisition module configured to: acquiring data in different working modes and different modes;
a second analysis module configured to: determining a second analysis result based on data of different working modes and different modes and the trained thermal runaway early warning model; the second analysis result indicates whether a second thermal runaway early warning instruction is sent;
a second transmitting module configured to: sending the determined second analysis result to a Battery Management System (BMS) through the vehicle-mounted terminal;
a second determination module configured to: the auxiliary battery management system is combined with the first analysis result and the second analysis result to determine whether to send out a thermal runaway alarm;
the data of different working modes and different modes are collected by different sensors and are uploaded to the cloud server through the battery management system BMS and the vehicle-mounted terminal in sequence; the first analysis result is obtained by analyzing smoke concentration data by the VCU of the vehicle control unit; the first analysis result indicates whether a first thermal runaway early warning instruction is sent; the smoke concentration data are collected by the smoke sensor and uploaded to the VCU through the BMS.
13. The utility model provides an electric automobile battery thermal runaway alarm system which characterized by includes: the system comprises a battery management system BMS, a vehicle control unit VCU and a cloud server;
the battery management system BMS transmits the smoke concentration data to the VCU; the VCU analyzes the smoke concentration data to determine whether a first thermal runaway early warning instruction is sent out;
the battery management system BMS transmits data of different working modes acquired by the battery early warning system to the vehicle-mounted terminal T-BOX; the vehicle-mounted terminal transmits the data to the cloud server, and the cloud server determines whether to send out a second thermal runaway early warning instruction or not according to the data uploaded by the vehicle-mounted terminal and the trained thermal runaway early warning model;
and the battery management system BMS determines whether to send out a thermal runaway alarm or not according to the two runaway early warning instructions.
14. An electronic device, comprising:
a memory for non-transitory storage of computer readable instructions; and
a processor for executing the computer readable instructions,
wherein the computer readable instructions, when executed by the processor, perform the method of any of claims 1-7, 9 or 11.
15. A storage medium storing non-transitory computer readable instructions, wherein the non-transitory computer readable instructions, when executed by a computer, perform the instructions of the method of any one of claims 1-7, 9 or 11.
16. A computer program product, comprising a computer program for implementing the method of any of the preceding claims 1-7, 9 or 11 when run on one or more processors.
CN202210466186.4A 2022-04-29 2022-04-29 Thermal runaway alarm system and method for battery of electric vehicle Pending CN114889433A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210466186.4A CN114889433A (en) 2022-04-29 2022-04-29 Thermal runaway alarm system and method for battery of electric vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210466186.4A CN114889433A (en) 2022-04-29 2022-04-29 Thermal runaway alarm system and method for battery of electric vehicle

Publications (1)

Publication Number Publication Date
CN114889433A true CN114889433A (en) 2022-08-12

Family

ID=82719733

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210466186.4A Pending CN114889433A (en) 2022-04-29 2022-04-29 Thermal runaway alarm system and method for battery of electric vehicle

Country Status (1)

Country Link
CN (1) CN114889433A (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115295950A (en) * 2022-09-21 2022-11-04 天津国轩新能源科技有限公司 Power battery system of electronic commodity circulation car
CN116344975A (en) * 2023-04-18 2023-06-27 湖南麦格米特电气技术有限公司 Battery pack control method, battery management system, battery pack and electric equipment
CN116520153A (en) * 2023-04-26 2023-08-01 广东博龙能源科技有限公司 Early warning protection method and system for thermal runaway of lithium battery
CN116683061A (en) * 2023-08-03 2023-09-01 太原科技大学 Power battery thermal runaway prediction and suppression integrated system, method and storage medium
CN117110901A (en) * 2023-08-25 2023-11-24 上海邦盟成套电气有限公司 New energy test vehicle-mounted lithium battery monitoring system and method
CN117154249A (en) * 2023-08-29 2023-12-01 上海橙川储能科技有限公司 Safety management method and system for cloud system of energy storage battery
CN117783751B (en) * 2023-12-29 2024-06-07 江苏淮海新能源车辆有限公司 Comprehensive vehicle condition detection system and method for electric vehicle

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115295950A (en) * 2022-09-21 2022-11-04 天津国轩新能源科技有限公司 Power battery system of electronic commodity circulation car
CN116344975A (en) * 2023-04-18 2023-06-27 湖南麦格米特电气技术有限公司 Battery pack control method, battery management system, battery pack and electric equipment
CN116344975B (en) * 2023-04-18 2024-06-07 湖南麦格米特电气技术有限公司 Battery pack control method, battery management system, battery pack and electric equipment
CN116520153A (en) * 2023-04-26 2023-08-01 广东博龙能源科技有限公司 Early warning protection method and system for thermal runaway of lithium battery
CN116520153B (en) * 2023-04-26 2024-03-26 广东博龙能源科技有限公司 Early warning protection method and system for thermal runaway of lithium battery
CN116683061A (en) * 2023-08-03 2023-09-01 太原科技大学 Power battery thermal runaway prediction and suppression integrated system, method and storage medium
CN116683061B (en) * 2023-08-03 2023-09-29 太原科技大学 Power battery thermal runaway prediction and suppression integrated system, method and storage medium
CN117110901A (en) * 2023-08-25 2023-11-24 上海邦盟成套电气有限公司 New energy test vehicle-mounted lithium battery monitoring system and method
CN117110901B (en) * 2023-08-25 2024-02-23 上海邦盟成套电气有限公司 New energy test vehicle-mounted lithium battery monitoring system and method
CN117154249A (en) * 2023-08-29 2023-12-01 上海橙川储能科技有限公司 Safety management method and system for cloud system of energy storage battery
CN117783751B (en) * 2023-12-29 2024-06-07 江苏淮海新能源车辆有限公司 Comprehensive vehicle condition detection system and method for electric vehicle

Similar Documents

Publication Publication Date Title
CN114889433A (en) Thermal runaway alarm system and method for battery of electric vehicle
CN113506924B (en) Thermal runaway early warning method and system for battery pack
CN110838609B (en) Power battery thermal runaway protection method, device and system
CN103522909B (en) Method and the car-mounted terminal of battery data is monitored under a kind of pure electric vehicle parked state
CN112319305A (en) Safety monitoring method, monitoring system and device for vehicle
CN112356689B (en) Detection method and system for safety early warning of hydrogen fuel cell automobile and vehicle-mounted terminal
CN203948534U (en) Automobile brake sheet early warning dangerous state device
CN107528095B (en) Low tension battery failure prediction method based on new energy vehicle storing card data
CN111934332A (en) Energy storage power station system based on cloud edge cooperation
CN112977160B (en) Battery management method, battery system, vehicle, and computer storage medium
CN114069856B (en) Remote monitoring system and method for electric automobile charging facility
CN112216891B (en) Power battery system and thermal runaway monitoring method for power battery system
CN106324514B (en) Vehicular battery method for testing performance and its system
CN111823952A (en) Battery cell temperature diagnosis method, storage medium and electronic equipment
CN112114259A (en) Vehicle power-shortage state monitoring method and system, server and vehicle
CN113752843B (en) Power battery thermal runaway early warning device and method based on Saybolt physical system
CN113177646B (en) Power distribution equipment online monitoring method and system based on self-adaptive edge proxy
CN113043912A (en) Full-time battery detection device and system and automobile
US11573271B1 (en) Battery fault detection
CN110838603B (en) Intelligent management system and method for electric quantity and temperature of electric vehicle battery
CN115064787A (en) Thermal runaway monitoring mechanism of power battery
CN113030759B (en) Method for detecting health degree of vehicle-mounted low-voltage storage battery
CN113296003A (en) Power battery voltage difference early warning method and system
CN212267264U (en) Multilayer safety device for electric automobile charging
CN114559816A (en) Power battery thermal runaway early warning method and device and electric automobile

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