CN112327170B - Power battery full-period residual life estimation method based on neural network - Google Patents
Power battery full-period residual life estimation method based on neural network Download PDFInfo
- Publication number
- CN112327170B CN112327170B CN202011271609.4A CN202011271609A CN112327170B CN 112327170 B CN112327170 B CN 112327170B CN 202011271609 A CN202011271609 A CN 202011271609A CN 112327170 B CN112327170 B CN 112327170B
- Authority
- CN
- China
- Prior art keywords
- power battery
- residual life
- under
- battery
- working condition
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
-
- 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
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
- Tests Of Electric Status Of Batteries (AREA)
Abstract
The invention provides a power battery full-cycle residual life estimation method based on a neural network, which is used for establishing a power battery residual life functional relation under experimental working conditions by combining an artificial neural network model I: and combining the artificial neural network model II to establish a power battery residual life function relation under the actual vehicle working condition: and establishing a full-cycle residual life function relation of the power battery through an artificial neural network model III. The neural network-based power battery full-cycle residual life estimation method adopts the artificial neural network to correct the functional relation of the power battery under the experimental working condition and the real vehicle working condition, thereby establishing the power battery full-cycle residual life functional relation.
Description
Technical Field
The invention belongs to the technical field of power battery life estimation, and particularly relates to a power battery full-cycle residual life estimation method based on a neural network.
Background
By 7 months in 2020, the new energy automobiles in China have 417 thousands of vehicles, which is increased by 36 ten thousands of vehicles compared with the last year, and the new energy automobiles are increased by 9.45%. From the cost of the new energy vehicle, the battery driven system accounts for 30-45% of the cost of the new energy vehicle, and the power battery accounts for about 75-85% of the cost of the battery driven system. The battery performance of the electric automobile decays along with the cyclic use, and when the power or capacity performance of the power battery can not reach the use standard of the electric automobile, the electric automobile needs to retire the current power battery and replace a new power battery. The new energy automobile power storage battery is retired in a large scale, and the power battery still has 80% of residual capacity after being retired from the electric automobile, so that the new energy automobile power storage battery can be applied to occasions with lower requirements on battery performance, namely, enters a battery energy storage cascade utilization stage, and at present, a method for accurately estimating the residual life of the power battery is lacking, and whether the power battery has a reutilization value cannot be accurately judged.
Disclosure of Invention
In view of the above, the present invention aims to provide a method for estimating the full cycle remaining life of a power battery based on a neural network, so as to solve the problem that a method for accurately estimating the remaining life of the power battery is lacking.
In order to achieve the above purpose, the technical scheme of the invention is realized as follows:
a power battery full cycle residual life estimation method based on a neural network comprises the following steps:
the method comprises the steps of building a power battery testing system under experimental working conditions, carrying out charge and discharge tests under different conditions, obtaining characteristic parameter data representing the residual life of the power battery under the experimental working conditions, and building a functional relation of the residual life of the power battery under the experimental working conditions by combining with an artificial neural network model I:
setting up a power battery test system under a real vehicle working condition, acquiring characteristic parameter data representing the residual life of a power battery under the real vehicle working condition by simulating the driving of the real vehicle under the condition, and establishing a functional relation of the residual life of the power battery under the real vehicle working condition by combining with an artificial neural network model II:
and training and correcting the residual life function relation of the power battery under the experimental working condition and the residual life function relation of the battery under the real vehicle working condition through the artificial neural network model three pairs, determining the weight between the residual life function relation of the power battery under the experimental working condition and the residual life function relation of the battery under the real vehicle working condition, and establishing the full-cycle residual life function relation of the power battery.
Further, the power battery test system under the experimental working condition comprises:
a high-low temperature box for adjusting the environmental temperature of the power battery;
the charging and discharging instrument is used for realizing the charging and discharging of the power battery;
the data acquisition instrument is used for acquiring data related to the power battery, the high-low temperature box and the charging and discharging instrument and is connected with the upper computer.
Further, the power battery test system under the experimental working condition is utilized to realize the charge and discharge test of the power battery under different temperature intervals, different charge and discharge multiplying powers, different SOC intervals and different dynamic working conditions, and the characteristic parameter data representing the residual life of the power battery under the experimental working condition is obtained.
Further, the characteristic parameter data representing the residual life of the power battery under the experimental working condition comprises data of residual capacity I, battery internal resistance I, battery voltage limit I and battery self-discharge rate I, and the training, the checking and the prediction are carried out on the partial random data of the residual capacity I, the battery internal resistance I, the battery voltage limit I and the battery self-discharge rate I of the power battery under the different dynamic working conditions by utilizing an artificial neural network model I and the power battery under the different temperature intervals, the different charge-discharge multiplying powers, the different SOC intervals and the different dynamic working conditions, so that the functional relation between the residual life of the power battery under the experimental working condition and the temperature, the charge-discharge multiplying power, the battery SOC interval and the working condition influence weight of the working condition on the residual life of the power battery is obtained, and the functional relation of the residual life of the power battery under the experimental working condition is established.
Further, under the power battery test system under the actual vehicle working condition, parameters representing the residual life of the power battery under different vehicle speeds, weather conditions, vehicle driving conditions and vehicle driving mileage of the electric vehicle are obtained through the battery BMS management system, the parameters comprise a second residual capacity, a second battery voltage limit, a second battery self-discharge rate and a second battery internal resistance, and the second power battery is trained, checked and predicted by partial random data of the second residual capacity, the second battery voltage limit, the second battery self-discharge rate and the second battery internal resistance under different vehicle speeds, weather conditions, the second battery driving condition and the second battery driving mileage through the artificial neural network model, so that the functional relation between the residual life of the power battery under the actual vehicle working condition and the vehicle speeds, the weather conditions and the vehicle acceleration and the weight of the vehicle driving mileage on the residual life of the power battery is obtained, and the residual life functional relation of the actual vehicle working condition power battery is established.
Compared with the prior art, the neural network-based power battery full cycle residual life estimation method has the following advantages:
the full-cycle residual life estimation method of the power battery based on the neural network adopts the artificial neural network to establish a functional relation of the residual life of the power battery under the experimental working condition under different temperatures, charge-discharge multiplying power, battery SOC and dynamic working conditions, and provides support for the estimation of the service life of the power battery under the experimental working condition; an artificial neural network is adopted to establish a functional relation of the remaining life of the power battery under the actual vehicle condition under different vehicle speeds, weather conditions, vehicle accelerations and vehicle driving mileage, so that support is provided for the life estimation of the power battery under the actual vehicle condition; and correcting the functional relation of the power battery under the experimental working condition and the real vehicle working condition by adopting an artificial neural network, so as to establish the full-cycle residual life functional relation of the power battery.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention. In the drawings:
fig. 1 is a schematic diagram of a power battery full cycle residual life estimation method based on a neural network according to an embodiment of the present invention.
Detailed Description
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.
In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first", "a second", etc. may explicitly or implicitly include one or more such feature. In the description of the present invention, unless otherwise indicated, the meaning of "a plurality" is two or more.
In the description of the present invention, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art in a specific case.
The invention will be described in detail below with reference to the drawings in connection with embodiments.
As shown in fig. 1, a method for estimating the full cycle remaining life of a power battery based on a neural network includes:
the method comprises the steps of building a power battery testing system under experimental working conditions, carrying out charge and discharge tests under different conditions, obtaining characteristic parameter data representing the residual life of the power battery under the experimental working conditions, and building a functional relation of the residual life of the power battery under the experimental working conditions by combining with an artificial neural network model I:
setting up a power battery test system under a real vehicle working condition, acquiring characteristic parameter data representing the residual life of a power battery under the real vehicle working condition by simulating the driving of the real vehicle under the condition, and establishing a functional relation of the residual life of the power battery under the real vehicle working condition by combining with an artificial neural network model II:
and training and correcting the residual life function relation of the power battery under the experimental working condition and the residual life function relation of the battery under the real vehicle working condition through the artificial neural network model three pairs, determining the weight between the residual life function relation of the power battery under the experimental working condition and the residual life function relation of the battery under the real vehicle working condition, and establishing the full-cycle residual life function relation of the power battery.
The power battery test system under the experimental working condition comprises:
a high-low temperature box for adjusting the environmental temperature of the power battery;
the charging and discharging instrument is used for realizing the charging and discharging of the power battery;
the data acquisition instrument is used for acquiring data related to the power battery, the high-low temperature box and the charging and discharging instrument and is connected with the upper computer.
And the power battery test system under the experimental working condition is utilized to realize the charge and discharge test of the power battery under different temperature intervals, different charge and discharge multiplying powers, different SOC intervals and different dynamic working conditions, and the characteristic parameter data representing the residual life of the power battery under the experimental working condition is obtained.
The characteristic parameter data representing the residual life of the power battery under the experimental working condition comprises data of residual capacity I, battery internal resistance I, battery voltage limit I and self-discharge rate I of the battery, and the partial random data of the residual capacity I, the battery internal resistance I, the battery voltage limit I and the self-discharge rate I of the battery under the different dynamic working conditions are trained, checked and predicted by utilizing an artificial neural network model I pair of power batteries in different temperature intervals, different charge-discharge multiplying powers, different SOC intervals and different dynamic working conditions, so that the functional relation between the residual life of the power battery under the experimental working condition and the temperature, the charge-discharge multiplying power, the battery SOC interval and the weight of the influence of the working condition on the residual life of the power battery is obtained, and the functional relation of the residual life of the power battery under the experimental working condition is established.
Under a power battery test system under a real vehicle condition, acquiring parameters representing the residual life of the power battery under different vehicle speeds, weather conditions, vehicle driving conditions and vehicle driving mileage of the electric vehicle through a battery BMS management system, wherein the parameters comprise a second residual capacity, a second battery voltage limit, a second battery self-discharge rate and a second battery internal resistance, training and checking and predicting partial random data of the power battery under different vehicle speeds, weather conditions, vehicle driving mileage, the second residual capacity, the second battery voltage limit, the second battery self-discharge rate and the second battery internal resistance through an artificial neural network model, obtaining a functional relation between the residual life of the power battery under the real vehicle condition and the vehicle speeds, the weather conditions and the vehicle acceleration and the vehicle driving mileage, and obtaining weights of the vehicle speeds, the weather conditions, the vehicle acceleration and the vehicle driving mileage on the residual life of the power battery, thereby establishing a real vehicle power battery residual life functional relation.
The power battery residual life estimation method based on the neural network comprises the following working principles:
as shown in fig. 1, through the cooperation installation between the power battery and the high-low temperature box, the charge-discharge instrument and the data acquisition instrument, the charge-discharge test of the power battery in different temperature intervals, different charge-discharge multiplying power, different SOC intervals and different dynamic working conditions is tested, and after a plurality of cycles, the characteristic parameters of the power battery for representing the residual life of the power battery are obtained: a first residual capacity, a first internal resistance of the battery, a first voltage limit of the battery and a first self-discharge rate of the battery; and training, checking and predicting partial random data of the power battery in different temperature intervals, different charge and discharge multiplying powers, different SOC intervals and different dynamic working conditions, namely the battery residual capacity, the battery internal resistance, the battery voltage limit and the battery self-discharge rate, so as to obtain a functional relation between the residual life of the power battery and the temperature, the charge and discharge multiplying powers, the battery SOC interval and the working conditions under the experimental working conditions, and obtain the weights of the influences of the temperature, the charge and discharge multiplying powers, the battery SOC interval and the working conditions on the residual life of the power battery as gamma 1, gamma 2, gamma 3 and gamma 4, respectively, thereby establishing the functional relation of the residual life of the power battery under the experimental working conditions.
Training partial random data of the first battery residual capacity, the first battery internal resistance, the first battery voltage limit and the first battery self-discharge rate of the power battery in different temperature intervals, different charge and discharge multiplying power, different SOC intervals and different dynamic working conditions by the artificial neural network model to form new data, and checking the data with the data of the power battery under the same experimental condition of the power battery until the error between the two is less than 1%; if the error between the two is greater than 1%, training the random data of the power battery by using the artificial neural network model until the error between the two is less than 1%; then, predicting the service life of the power battery under different working conditions of the training data through the artificial neural network model I, and performing error analysis on the experimental result of the power battery under the experimental working conditions of the same result as the predicted data until the error of the experimental result and the predicted data is less than 1%; and the functional relation between the residual life of the power battery under the experimental working condition and the temperature, the charge-discharge multiplying power, the battery SOC interval and the working condition is obtained, so that the functional relation of the residual life of the power battery under the experimental working condition is established.
The electric automobile obtains the parameter representing the remaining life of the power battery under different automobile speeds, weather conditions, automobile driving conditions and automobile driving mileage through the battery BMS management system: training, checking and predicting partial random data of the power battery under different automobile speeds, weather conditions, automobile driving mileage, battery voltage limit, battery self-discharge rate and battery internal resistance through an artificial neural network model II; the functional relation between the residual life of the power battery under the actual vehicle condition and the vehicle speed, weather condition, vehicle acceleration and vehicle driving mileage is obtained, and the weight of the influence of the vehicle speed, weather condition, vehicle acceleration and vehicle driving mileage on the residual life of the power battery is omega 1, omega 2, omega 3 and omega 4 respectively, so that the functional relation of the residual life of the power battery under the actual vehicle condition is established; and training and correcting the residual life function relation of the power battery under the experimental working condition and the residual life function relation of the battery under the real vehicle working condition through the artificial neural network model three pairs, and determining that weights between the residual life function relation of the power battery under the experimental working condition and the residual life function relation of the battery under the real vehicle working condition are alpha and beta respectively, so as to establish the full-cycle residual life function relation of the power battery.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (5)
1. The power battery full cycle residual life estimation method based on the neural network is characterized by comprising the following steps of:
a power battery test system under the experimental working condition is built, charge and discharge tests under different conditions are carried out, characteristic parameter data representing the residual life of the power battery under the experimental working condition is obtained, and a functional relation of the residual life of the power battery under the experimental working condition is built by combining with an artificial neural network model I;
setting up a power battery test system under a real vehicle working condition, acquiring characteristic parameter data representing the residual life of a power battery under the real vehicle working condition by simulating the driving of the real vehicle under the condition, and establishing a functional relation of the residual life of the power battery under the real vehicle working condition by combining with the artificial neural network model II;
training and correcting the residual life function relationship of the power battery under the experimental working condition and the residual life function relationship of the battery under the real vehicle working condition through the artificial neural network model III, determining the weight between the residual life function relationship of the power battery under the experimental working condition and the residual life function relationship of the battery under the real vehicle working condition, and establishing the full-cycle residual life function relationship of the power battery; the weight between the power battery residual life function relation under the experimental working condition and the battery residual life function relation under the real vehicle working condition is alpha and beta respectively.
2. The neural network-based power battery full cycle remaining life estimation method of claim 1, wherein the power battery test system under the experimental conditions comprises:
a high-low temperature box for adjusting the environmental temperature of the power battery;
the charging and discharging instrument is used for realizing the charging and discharging of the power battery;
the data acquisition instrument is used for acquiring data related to the power battery, the high-low temperature box and the charging and discharging instrument and is connected with the upper computer.
3. The neural network-based power battery full cycle remaining life estimation method of claim 2, wherein: and the power battery test system under the experimental working condition is utilized to realize the charge and discharge test of the power battery under different temperature intervals, different charge and discharge multiplying powers, different SOC intervals and different dynamic working conditions, and the characteristic parameter data representing the residual life of the power battery under the experimental working condition is obtained.
4. A neural network-based power cell full cycle remaining life estimation method according to claim 1 or 3, characterized in that: the characteristic parameter data representing the residual life of the power battery under the experimental working condition comprises data of residual capacity I, battery internal resistance I, battery voltage limit I and self-discharge rate I of the battery, and the partial random data of the residual capacity I, the battery internal resistance I, the battery voltage limit I and the self-discharge rate I of the battery under the different dynamic working conditions are trained, checked and predicted by utilizing an artificial neural network model I pair of power batteries in different temperature intervals, different charge-discharge multiplying powers, different SOC intervals and different dynamic working conditions, so that the functional relation between the residual life of the power battery under the experimental working condition and the temperature, the charge-discharge multiplying power, the battery SOC interval and the weight of the influence of the working condition on the residual life of the power battery is obtained, and the functional relation of the residual life of the power battery under the experimental working condition is established.
5. The neural network-based power battery full cycle remaining life estimation method of claim 1, wherein: under a power battery test system under a real vehicle condition, acquiring parameters representing the residual life of the power battery under different vehicle speeds, weather conditions, vehicle driving conditions and vehicle driving mileage of the electric vehicle through a battery BMS management system, wherein the parameters comprise a second residual capacity, a second battery voltage limit, a second battery self-discharge rate and a second battery internal resistance, training and checking and predicting partial random data of the power battery under different vehicle speeds, weather conditions, vehicle driving mileage, the second residual capacity, the second battery voltage limit, the second battery self-discharge rate and the second battery internal resistance through an artificial neural network model, obtaining a functional relation between the residual life of the power battery under the real vehicle condition and the vehicle speeds, the weather conditions and the vehicle acceleration and the vehicle driving mileage, and obtaining weights of the vehicle speeds, the weather conditions, the vehicle acceleration and the vehicle driving mileage on the residual life of the power battery, thereby establishing a real vehicle power battery residual life functional relation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011271609.4A CN112327170B (en) | 2020-11-13 | 2020-11-13 | Power battery full-period residual life estimation method based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011271609.4A CN112327170B (en) | 2020-11-13 | 2020-11-13 | Power battery full-period residual life estimation method based on neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112327170A CN112327170A (en) | 2021-02-05 |
| CN112327170B true CN112327170B (en) | 2023-04-28 |
Family
ID=74319171
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011271609.4A Active CN112327170B (en) | 2020-11-13 | 2020-11-13 | Power battery full-period residual life estimation method based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112327170B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113159435B (en) * | 2021-04-29 | 2022-11-22 | 浙江吉利控股集团有限公司 | Method and system for predicting remaining driving mileage of new energy vehicle |
| CN114019380B (en) * | 2021-10-29 | 2024-05-17 | 天津市捷威动力工业有限公司 | Calendar life extension prediction method for battery cell |
| CN115099020A (en) * | 2022-06-17 | 2022-09-23 | 湖北亿纬动力有限公司 | Power battery parameter full life cycle prediction method and device |
| CN118131057B (en) * | 2024-05-08 | 2024-07-05 | 山东理工职业学院 | New energy automobile fortune dimension management system based on thing networking |
| CN118209893B (en) * | 2024-05-21 | 2024-07-30 | 深圳市杰成镍钴新能源科技有限公司 | Method for determining remaining calendar life of retired battery |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10371753B1 (en) * | 2013-12-20 | 2019-08-06 | Hrl Laboratories, Llc | Methods for online estimation of battery capacity and state of health |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN205787041U (en) * | 2016-05-27 | 2016-12-07 | 郑州精益达汽车零部件有限公司 | The test checking system of new-energy automobile power battery SOC estimation strategy |
| CN107069122A (en) * | 2017-04-01 | 2017-08-18 | 山东省科学院自动化研究所 | A kind of Forecasting Methodology of electrokinetic cell remaining life |
| CN108333528B (en) * | 2018-02-07 | 2019-08-20 | 重庆大学 | SOC and SOT united state estimation method based on power battery electric-thermal coupling model |
| CN108919129B (en) * | 2018-06-08 | 2020-11-27 | 北京长城华冠汽车科技股份有限公司 | Service life prediction method of power battery under time-varying working condition |
| CN109799463A (en) * | 2019-01-18 | 2019-05-24 | 上海卡鲁自动化科技有限公司 | The estimation and prediction technique of power battery SOC/SOH/SOP under actual operating mode based on big data method |
| CN109738810B (en) * | 2019-01-21 | 2021-06-15 | 温州大学 | Comprehensive estimation method for remaining service life of battery |
| CN109934408A (en) * | 2019-03-18 | 2019-06-25 | 常伟 | A kind of application analysis method carrying out automobile batteries RUL prediction based on big data machine learning |
| CN110750874B (en) * | 2019-09-26 | 2020-07-28 | 长沙理工大学 | Retired power battery life prediction method |
| CN110775043B (en) * | 2019-11-11 | 2020-09-29 | 吉林大学 | Hybrid electric vehicle energy optimization method based on battery life attenuation pattern recognition |
| CN110888059B (en) * | 2019-12-03 | 2022-04-19 | 西安科技大学 | Charge state estimation algorithm based on improved random forest combined volume Kalman |
| CN111649954A (en) * | 2020-04-26 | 2020-09-11 | 奇瑞汽车股份有限公司 | Laboratory automobile dynamic balance testing method and device |
| CN111898325A (en) * | 2020-08-14 | 2020-11-06 | 天津大学 | Method for predicting remaining service life of power battery of electric automobile |
-
2020
- 2020-11-13 CN CN202011271609.4A patent/CN112327170B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10371753B1 (en) * | 2013-12-20 | 2019-08-06 | Hrl Laboratories, Llc | Methods for online estimation of battery capacity and state of health |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112327170A (en) | 2021-02-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112327170B (en) | Power battery full-period residual life estimation method based on neural network | |
| CN112433169B (en) | Cloud power battery health degree evaluation system and method | |
| CN102998623B (en) | The estimation on line method and system of storage battery charge state | |
| CN102156265B (en) | Device and method for testing health state of battery | |
| US7888911B2 (en) | Method and system for determining the SOC of a rechargeable battery | |
| CN101860056A (en) | Power lithium battery pack balancing and managing system based on Map model | |
| CN102124360A (en) | Storage battery device, storage battery state of charge evaluation device and method | |
| CN113109729B (en) | Vehicle power battery SOH evaluation method based on accelerated aging test and real vehicle working condition | |
| EP3594705B1 (en) | Method and device for estimating service capacity and state of health of minimum battery cell and battery system | |
| CN102331314A (en) | Dynamic estimation of cell core temperature by simple external measurements | |
| CN111308356A (en) | SOC estimation method with weighted ampere-hour integration | |
| CN111537885B (en) | Multi-time scale short circuit resistance estimation method for series battery pack | |
| CN103713264A (en) | Battery management system SOC estimation precision test system and test method | |
| CN109975715B (en) | Method for obtaining residual electric quantity of lithium ion battery module of electric vehicle | |
| CN111766530B (en) | Method for detecting service life of lithium ion storage battery monomer | |
| CN104950263A (en) | Estimation method for SOC of automobile power battery | |
| CN106249158A (en) | Ferric phosphate lithium cell actual active volume detection method, system and electric automobile | |
| CN113093027B (en) | Battery SOC calibration method, device, system, medium and program product | |
| CN114384421A (en) | Early warning method and analysis method for performance attenuation of lithium ion battery system | |
| CN109753697B (en) | Energy consumption calculation method for externally-connected rechargeable hybrid power fuel cell vehicle | |
| CN110988728A (en) | Method for quickly diagnosing abnormal internal connection of lithium battery pack | |
| CN106338642A (en) | Single cell consistency testing method | |
| CN106324520B (en) | Battery core capacity calculation methods and system in a kind of electrokinetic cell system based on monitor supervision platform data | |
| CN117388737A (en) | Method, device, equipment and storage medium for evaluating battery health state | |
| CN116804715A (en) | Method for judging reasons for inconsistent occurrence of battery system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |