CN110988723A - LSTM-based battery internal resistance prediction and fault early warning method - Google Patents
LSTM-based battery internal resistance prediction and fault early warning method Download PDFInfo
- Publication number
- CN110988723A CN110988723A CN201911303278.5A CN201911303278A CN110988723A CN 110988723 A CN110988723 A CN 110988723A CN 201911303278 A CN201911303278 A CN 201911303278A CN 110988723 A CN110988723 A CN 110988723A
- Authority
- CN
- China
- Prior art keywords
- battery
- internal resistance
- battery internal
- current
- fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- 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]
- G01R31/389—Measuring internal impedance, internal conductance or related 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]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
- Tests Of Electric Status Of Batteries (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention provides a battery internal resistance prediction and fault early warning method based on LSTM, which comprises the following steps: s1, classifying the causes of the change of the internal resistance of the battery; s2, selecting the battery internal resistance influence factor parameters of n batteries as the input of a battery internal resistance prediction model based on a long-time and short-time memory method neural network; s3, constructing a battery internal resistance prediction model based on a long-time memory method neural network; s4, obtaining current battery internal resistance data and battery internal resistance change rate according to the current battery internal resistance influence factor parameters; s5, setting a battery internal resistance threshold, a battery internal resistance change rate threshold and a charging and discharging frequency interval; and S6, generating battery fault early warning information according to the information in the previous step. The advantages are that: the method predicts the internal resistance of the battery through the internal resistance prediction model of the battery based on the long-time memory neural network, can more clearly and quickly locate the battery fault, simplifies the complicated procedures of blindly checking the battery by maintainers, and lays a foundation for early warning of the battery fault.
Description
Technical Field
The invention relates to the field of battery internal resistance prediction and fault early warning, in particular to a battery internal resistance prediction and fault early warning method based on a long-time memory neural network (LSTM).
Background
The valve-controlled lead-acid storage battery has the advantages of no acid mist and other gas exhaust, no need of adding water, high power density and the like, is widely used in a transformer substation, plays an important role as a standby power supply of a direct current system in the transformer substation, and can influence the safe and stable operation of the system in the health state. At present, the failure of the valve-controlled lead-acid storage battery forms or is forming a great threat to the power supply safety of the power supply for the substation, and the related aspects need to give enough attention to the problem.
The internal resistance of the valve-regulated lead-acid storage battery is inevitably increased to a certain extent along with the increase of the service time of the valve-regulated lead-acid storage battery, and various faults of the valve-regulated lead-acid storage battery can also cause the abnormal increase of the internal resistance of the battery. The problem of influencing the performance of the battery can be detected according to the change of the internal resistance of the battery, however, due to the sealing characteristic of the valve-regulated lead-acid storage battery, the manual test of the maintenance and the overhaul of the battery is time-consuming and labor-consuming, and the problem of the storage battery is often known only after the battery fails, in addition, the measured value of the internal resistance of the battery can also be changed due to the failure reasons of some non-battery bodies, such as the failure of a sensor, the loose connection and the like, so that the problem of how to predict the internal resistance of the battery on.
The internal resistance of the battery can be accurately tested by a test method, and a set of internal resistance testing device suitable for multi-type and high-capacity valve-controlled lead-acid storage batteries is developed by comparing several methods for testing the internal resistance of the current valve-controlled lead-acid storage battery in documents [ testing the internal resistance of the storage battery based on a direct-current secondary discharge method [ J ]. power technology, 2017,41(11):1599 and 1601 ]. The document [ equivalent circuit model and parameter identification [ J ] of valve-regulated lead-acid storage battery power technology, 2017,41(3): 460-. In the document [ storage battery internal resistance test based on a direct-current secondary discharge method [ J ] power technology, 2017,41(11): 1599-. The test method is time consuming and laborious and is not suitable for use in an operating state of the battery.
Disclosure of Invention
The invention aims to provide a battery internal resistance prediction and fault early warning method based on LSTM, which comprises the steps of firstly analyzing the change reasons of the internal resistance of a battery, and dividing the change reasons of the internal resistance into three types of battery faults, battery aging and artificial removable faults; secondly, a battery internal resistance prediction model based on a long-time memory neural network is constructed, characteristic factors influencing the battery internal resistance are analyzed, quantifiable factors are selected as model input, and the model output is the battery internal resistance; obtaining the internal resistance value of the battery at the current moment according to the input value of the battery at the current moment and the constructed internal resistance prediction model of the battery, and calculating the internal resistance change rate of the resistor according to the internal resistance value of the battery at the previous moment and the sampling time; setting a resistance internal resistance threshold value, a charge-discharge frequency interval corresponding to the service life of the battery and a battery internal resistance change rate threshold value; and finally, providing a battery fault early warning method according to the predicted internal resistance value and the relation between the change rate and the set threshold value. The method saves the time and cost for testing the internal resistance of the battery by maintainers, can more quickly and effectively predict the internal resistance of the battery, and lays a foundation for early warning of battery faults.
In order to achieve the purpose, the invention is realized by the following technical scheme:
a battery internal resistance prediction and fault early warning method based on LSTM comprises the following steps:
s1, classifying the causes of the change of the internal resistance of the battery;
s2, selecting the battery internal resistance influence factor parameters of n batteries as the input of a battery internal resistance prediction model based on a long-time and short-time memory method neural network;
s3, constructing a battery internal resistance prediction model based on a long-time memory method neural network;
s4, predicting current battery internal resistance data according to the current battery internal resistance influence factor parameters;
s5, setting a battery internal resistance threshold, a battery internal resistance change rate threshold and a charging and discharging frequency interval;
and S6, generating battery fault early warning information according to the information in the previous step.
Preferably, the cause of the change in the internal resistance of the battery includes: battery aging, battery failure, manual troubleshooting.
Preferably, the battery internal resistance influencing factors include: a charge-discharge state S, charge-discharge times m, a charge-discharge voltage U, a charge-discharge current I and a battery temperature T.
Preferably, the step S3 specifically includes:
t1, preprocessing the input data in the step S2 to obtain an n × m group data set;
t2, dividing the n x m group data set into a training set and a testing set;
t3, constructing and adjusting a long-term and short-term memory neural network;
t4, training the long-short time memory neural network by adopting a training set until an expected effect is achieved, obtaining a battery internal resistance prediction model based on the long-short time memory neural network, and otherwise, repeating the steps from T3 to T4;
t5, testing the battery internal resistance prediction model based on the neural network of the long and short term memory method by adopting a test set until an expected effect is achieved, otherwise, repeating the steps from T3 to T5;
and T6, outputting a battery internal resistance prediction model based on the long-time memory neural network.
Preferably, the step S4 includes:
initializing a battery internal resistance prediction model based on the long-time memory method neural network;
and substituting the current battery internal resistance influence factor parameters into the battery internal resistance prediction model based on the long-time memory neural network to obtain the current battery internal resistance data.
Preferably, the threshold value of the internal resistance of the battery is 1.6 times of the rated internal resistance of the battery, the threshold value of the change rate of the internal resistance of the battery is 0.5, and the charging and discharging frequency interval is [ 200-300 ].
Preferably, the step S6 includes:
n1, when the current battery internal resistance data is smaller than the battery internal resistance threshold value, calculating the current battery internal resistance change rate;
and N2, when the current change rate of the internal resistance of the battery is smaller than the threshold value of the change rate of the internal resistance of the battery, outputting a signal that the battery is normal.
Preferably, the current battery internal resistance change rate is obtained by combining the current battery internal resistance data with the battery internal resistance data at the last moment.
Preferably, the step S6 further includes:
when the current battery internal resistance data is larger than or equal to the battery internal resistance threshold value, if the current charging and discharging times of the battery are within the charging and discharging time interval, outputting a battery aging signal, otherwise, outputting a battery fault signal.
Preferably, the step S6 further includes:
and when the current change rate of the internal resistance of the battery is greater than or equal to the change rate threshold value of the internal resistance of the battery, judging whether the fault can be eliminated manually or not, if so, eliminating the fault, then, checking the current internal resistance influence factor parameters of the battery after the elimination, predicting the internal resistance of the battery again, and if not, outputting a signal of the fault of the battery.
Compared with the prior art, the invention has the following advantages:
(1) according to the invention, based on the long-time memory method neural network, the internal resistance influence factors of the valve-controlled lead-acid storage battery are quantized, a battery internal resistance prediction model based on the long-time memory method neural network is constructed, and the internal resistance of the battery is predicted according to the model, so that the time and the cost for testing the internal resistance of the battery by maintainers are saved, the internal resistance of the battery can be predicted more quickly and effectively, and a foundation is laid for early warning of battery faults;
(2) the invention provides a battery fault early warning method according to the internal resistance judgment of the valve-controlled lead-acid storage battery, judges the performance of the battery and the fault early warning according to the relation among the internal resistance value of the battery, the internal resistance change rate and the set threshold value, can more clearly and quickly locate the battery fault, simplifies the complicated process of the maintenance personnel for blindly checking the battery, further saves the time and the cost for the maintenance personnel to check the fault, ensures that the maintenance work is more scientific and effective, and improves the reliability of the safe operation of the valve-controlled lead-acid storage battery.
Drawings
FIG. 1 is a schematic diagram of a LSTM-based battery internal resistance prediction and fault early warning method according to the present invention;
FIG. 2 is a schematic diagram of the prediction of the internal resistance of the battery from the parameters of the factors affecting the internal resistance of the battery;
FIG. 3 is a schematic diagram of a battery internal resistance prediction model based on a long-term and short-term memory neural network;
fig. 4 is a schematic diagram of generating battery failure warning information according to the present invention.
Detailed Description
The present invention will now be further described by way of the following detailed description of a preferred embodiment thereof, taken in conjunction with the accompanying drawings.
As shown in fig. 1, a method for predicting internal resistance of battery and early warning of failure based on LSTM of the present invention includes:
and S1, classifying the change reasons of the internal resistance R of the battery.
In this embodiment, a battery device composed of n valve-controlled lead-acid batteries is selected as a research object. The reasons for the change in the internal resistance R of the battery include: battery aging, battery failure, manual troubleshooting.
Wherein, the battery aging is the continuous increase of the internal resistance R of the battery caused by the long-term use of the battery, the internal resistance R of the battery does not greatly expand, but when the battery reaches the charging and discharging frequency interval [ m ] corresponding to the service lifemin,mmax]The internal resistance R of the battery exceeds the internal resistance threshold value R of the batteryth. The reason why the battery failure causes the sudden change of the internal resistance R of the battery may be that the internal resistance R of the battery is increased due to the failure of the battery body, and the battery does not reach the charging and discharging frequency interval [ m ] corresponding to the service lifemin,mmax]. The manual troubleshooting can also cause the increase of the internal resistance R of the battery, and the sudden change of the internal resistance R of the battery can be caused by sensor failure, loose wire ends, battery signal acquisition or the failure of battery management equipment and the like.
And S2, as shown in figure 2, selecting the battery internal resistance influence factor parameters of the n batteries as the input of the battery internal resistance prediction model based on the long-time memory method neural network. The characteristic factors influencing the internal resistance of the battery are analyzed, and quantifiable internal resistance influencing factors of the battery are selected as the input of the model.
The battery internal resistance influencing factors include: the charging and discharging state S (0, 1, 2), the charging and discharging times m, the charging and discharging voltage U, the charging and discharging current I and the battery temperature T, wherein 0 represents the charging state, 1 represents the discharging state, and 2 represents the floating charging state.
S3, as shown in fig. 3, is a schematic flow chart of the battery internal resistance prediction model based on the long-and-short-term memory neural network. The output of the battery model is the battery internal resistance R.
The step S3 specifically includes:
and T1, preprocessing the input data in the step S2, wherein each battery has m groups of data, and n batteries obtain n multiplied by m groups of data sets.
T2, the nxm groups of data sets are divided into training sets and testing sets, in this embodiment, seven tenths of the groups of data sets in the nxm groups of data sets are used as the training sets, and the remaining three tenths of the groups of data sets are used as the testing sets.
T3, constructing and adjusting the neural network of long-term and short-term memory method.
And T4, training the long-short time memory neural network by adopting a training set, determining network parameters until an expected effect is achieved, obtaining a battery internal resistance prediction model based on the long-short time memory neural network, and otherwise, repeating the steps from T3 to T4. The expected effect here is: the error of the battery internal resistance R predicted by the battery internal resistance prediction model based on the long-time memory neural network is in a set range. As shown in fig. 3, when the error of the battery internal resistance R is less than or equal to 0.01, it is satisfactory, i.e., the desired effect is achieved, otherwise it is unsatisfactory, i.e., the desired effect is not achieved.
And T5, testing the battery internal resistance prediction model based on the neural network of the long and short term memory method by adopting the test set until an expected effect is achieved so as to verify the accuracy of the model, and repeating the steps from T3 to T5 if the expected effect is not achieved. The expected effect here is: and substituting the data of the test set into a battery internal resistance prediction model based on the long-time memory neural network, wherein the predicted error of the battery internal resistance R is within a set range. For example, in fig. 3, when the error of the battery internal resistance R is less than or equal to 0.01, the desired effect is satisfied, and otherwise, the desired effect is not satisfied, i.e., the desired effect is not achieved.
And T6, outputting a battery internal resistance prediction model based on the long-time memory neural network.
S4, inputting the parameters of the current battery internal resistance influence factors of the (n + 1) th lead-acid storage battery into the battery internal resistance prediction model based on the long-time and short-time memory neural network constructed in the step S3, and predicting the battery internal resistance R of the (n + 1) th lead-acid storage battery at the current moment1。
The step S4 includes:
initializing a battery internal resistance prediction model based on the long-time memory method neural network;
substituting the current battery internal resistance influence factor parameters of the (n + 1) th lead-acid storage battery into the battery internal resistance prediction model based on the long-time memory neural network to obtain the current battery internal resistance R1And (4) data.
S5, setting internal resistance threshold R of batterythAnd battery internal resistance change rate threshold value R'thAnd the interval of charging and discharging times [ m ]min,mmax]。
The parameters of the batteries of different manufacturers are different, the corresponding threshold values and the interval values are different, and under the general condition, the internal resistance threshold value R of the battery isthIs 1.6 times of rated internal resistance of the battery, and the threshold value R 'of the change rate of the internal resistance of the battery'thIs 0And 5, the charging and discharging frequency interval is 200-300]。
S6, as shown in fig. 4, generating battery failure warning information according to the information of the foregoing steps.
The step S6 includes:
n1, and when the current battery internal resistance R of the (N + 1) th lead-acid storage battery1The data is less than the internal resistance threshold value R of the batterythCalculating the current change rate k (namely R') of the internal resistance of the battery;
the internal resistance R of the current (n + 1) th lead-acid storage battery1The data is combined with the battery internal resistance data R at the last moment1', calculating the change rate k of the internal resistance of the battery, wherein the calculation formula is k ═ R1-R1')/Δ t, where Δ t is the sampling time.
N2, when the current battery internal resistance change rate k is smaller than the battery internal resistance change rate threshold value R'thWhen the battery is normal, the signal that the battery is normal is output.
The step S6 further includes:
current internal resistance of battery R1The data is greater than or equal to the internal resistance threshold value R of the batterythIf the current charge and discharge times m of the battery1In the interval of charging and discharging times [ m ]min,mmax]And if not, outputting a signal of battery failure.
The step S6 further includes:
the current battery internal resistance change rate R 'is greater than or equal to a battery internal resistance change rate threshold value R'thJudging whether the fault can be eliminated manually or not, if so, eliminating the fault, checking the current battery internal resistance influence factor parameters of the battery after the fault is eliminated, and predicting the battery internal resistance R again1And if not, outputting a signal of battery failure.
The invention relates to a battery internal resistance prediction and fault early warning method based on LSTM, which comprises the steps of firstly analyzing the change reasons of the internal resistance of a battery, and dividing the change reasons of the internal resistance into three types of battery faults, battery aging and manual troubleshooting; secondly, a battery internal resistance prediction model based on a long-time memory neural network is constructed, characteristic factors influencing the battery internal resistance are analyzed, and quantifiable factors are selected as modelsThe model input is used for inputting the model output into the battery internal resistance R; obtaining the internal resistance value R of the battery at the current moment according to the input value at the current moment and the constructed internal resistance prediction model of the battery1Calculating the resistance internal resistance change rate R' according to the battery internal resistance value and the sampling time at the previous moment; setting resistance internal resistance threshold value RthInterval of charging and discharging times [ m ] corresponding to service life of batterymin,mmax]Cell internal resistance change rate threshold value R'th(ii) a And finally, providing a battery fault early warning method according to the predicted relationship between the internal resistance value of the battery and the change rate thereof and a set threshold value. The method can more clearly and quickly locate the battery fault, simplifies the complicated procedures of the maintenance personnel for blindly checking the battery, saves the time and cost for the maintenance personnel to test the internal resistance of the battery, can more quickly and effectively predict the internal resistance of the battery, and lays a foundation for early warning of the battery fault.
While the present invention has been described in detail with reference to the preferred embodiments, it should be understood that the above description should not be taken as limiting the invention. Various modifications and alterations to this invention will become apparent to those skilled in the art upon reading the foregoing description. Accordingly, the scope of the invention should be determined from the following claims.
Claims (10)
1. A battery internal resistance prediction and fault early warning method based on LSTM is characterized by comprising the following steps:
s1, classifying the causes of the change of the internal resistance of the battery;
s2, selecting the battery internal resistance influence factor parameters of n batteries as the input of a battery internal resistance prediction model based on a long-time and short-time memory method neural network;
s3, constructing a battery internal resistance prediction model based on a long-time memory method neural network;
s4, predicting current battery internal resistance data according to the current battery internal resistance influence factor parameters;
s5, setting a battery internal resistance threshold, a battery internal resistance change rate threshold and a charging and discharging frequency interval;
and S6, generating battery fault early warning information according to the information in the previous step.
2. The LSTM-based battery internal resistance prediction and fault pre-warning method of claim 1,
the causes of the change in the internal resistance of the battery include: battery aging, battery failure, manual troubleshooting.
3. The LSTM-based valve-regulated lead-acid battery internal resistance prediction and fault early warning method of claim 1,
the battery internal resistance influencing factors include: a charge-discharge state S, charge-discharge times m, a charge-discharge voltage U, a charge-discharge current I and a battery temperature T.
4. The LSTM-based battery internal resistance prediction and fault pre-warning method of claim 3, wherein the step S3 specifically includes:
t1, preprocessing the input data in the step S2 to obtain an n × m group data set;
t2, dividing the n x m group data set into a training set and a testing set;
t3, constructing and adjusting a long-term and short-term memory neural network;
t4, training the neural network of long-short time memory method by adopting a training set until the expected effect is achieved, obtaining a battery internal resistance prediction model based on the neural network of long-short time memory method, otherwise, repeating the steps from T3 to T3
T4；
T5, testing the battery internal resistance prediction model based on the neural network of the long and short term memory method by adopting a test set until an expected effect is achieved, otherwise, repeating the steps from T3 to T5;
and T6, outputting a battery internal resistance prediction model based on the long-time memory neural network.
5. The LSTM-based battery internal resistance prediction and fault pre-warning method of claim 1, wherein the step S4 includes:
initializing a battery internal resistance prediction model based on the long-time memory method neural network;
and substituting the current battery internal resistance influence factor parameters into the battery internal resistance prediction model based on the long-time memory neural network to obtain the current battery internal resistance data.
6. The LSTM-based battery internal resistance prediction and fault pre-warning method of claim 1,
the battery internal resistance threshold is 1.6 times of the rated internal resistance of the battery, the battery internal resistance change rate threshold is 0.5, and the charging and discharging frequency interval is [ 200-300 ].
7. The LSTM-based battery internal resistance prediction and fault pre-warning method of claim 1, wherein the step S6 includes:
n1, when the current battery internal resistance data is smaller than the battery internal resistance threshold value, calculating the current battery internal resistance change rate;
and N2, when the current change rate of the internal resistance of the battery is smaller than the threshold value of the change rate of the internal resistance of the battery, outputting a signal that the battery is normal.
8. The LSTM-based battery internal resistance prediction and fault pre-warning method of claim 7,
and the current change rate of the internal resistance of the battery is obtained by combining the current internal resistance data of the battery with the internal resistance data of the battery at the last moment.
9. The LSTM-based battery internal resistance prediction and fault pre-warning method of claim 7, wherein the step S6 further comprises:
when the current battery internal resistance data is larger than or equal to the battery internal resistance threshold value, if the current charging and discharging times of the battery are within the charging and discharging time interval, outputting a battery aging signal, otherwise, outputting a battery fault signal.
10. The LSTM-based battery internal resistance prediction and fault pre-warning method according to claim 7, 8 or 9, wherein the step S6 further includes:
and when the current change rate of the internal resistance of the battery is greater than or equal to the change rate threshold value of the internal resistance of the battery, judging whether the fault can be eliminated manually or not, if so, eliminating the fault, then, checking the current internal resistance influence factor parameters of the battery after the elimination, predicting the internal resistance of the battery again, and if not, outputting a signal of the fault of the battery.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911303278.5A CN110988723B (en) | 2019-12-17 | 2019-12-17 | LSTM-based battery internal resistance prediction and fault early warning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911303278.5A CN110988723B (en) | 2019-12-17 | 2019-12-17 | LSTM-based battery internal resistance prediction and fault early warning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110988723A true CN110988723A (en) | 2020-04-10 |
| CN110988723B CN110988723B (en) | 2022-01-25 |
Family
ID=70094928
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911303278.5A Active CN110988723B (en) | 2019-12-17 | 2019-12-17 | LSTM-based battery internal resistance prediction and fault early warning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110988723B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112198443A (en) * | 2020-09-28 | 2021-01-08 | 烽火通信科技股份有限公司 | Method and device for detecting service life of storage battery |
| CN112749509A (en) * | 2020-12-30 | 2021-05-04 | 西华大学 | Intelligent substation fault diagnosis method based on LSTM neural network |
| CN113191081A (en) * | 2021-04-29 | 2021-07-30 | 浙江吉利控股集团有限公司 | New energy vehicle power battery internal resistance prediction method and system |
| CN113591404A (en) * | 2021-09-29 | 2021-11-02 | 杭州宇谷科技有限公司 | Battery abnormity detection system and method based on deep learning |
| CN114089202A (en) * | 2022-01-24 | 2022-02-25 | 天津力神电池股份有限公司 | Method for nondestructively analyzing electrode impedance stability in battery circulation process |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6477024B1 (en) * | 1999-03-12 | 2002-11-05 | Toyota Jidosha Kabushiki Kaisha | Fault determination apparatus and fault determination method for a battery set |
| CN103123992A (en) * | 2011-11-17 | 2013-05-29 | 财团法人工业技术研究院 | Battery pack and method for controlling charge and discharge of battery pack by thermoelectric characteristics thereof |
| CN104656024A (en) * | 2013-11-22 | 2015-05-27 | 韩燕� | Method and device for detecting battery electric quantity and battery |
| CN105015360A (en) * | 2015-06-24 | 2015-11-04 | 安徽江淮汽车股份有限公司 | SOF monitoring method of vehicle power battery |
| CN105068007A (en) * | 2015-07-01 | 2015-11-18 | 清华大学 | Method and system for predicting changes of parameters of lithium ion battery model |
| CN106125009A (en) * | 2016-08-31 | 2016-11-16 | 深圳天珑无线科技有限公司 | Battery performance detection method and battery performance detection device |
| CN107608863A (en) * | 2017-07-31 | 2018-01-19 | 维沃移动通信有限公司 | The calibration method and mobile terminal that a kind of electricity is shown |
| CN107861070A (en) * | 2017-10-25 | 2018-03-30 | 北京交通大学 | A kind of health state of lithium ion battery inline diagnosis method |
| CN109725266A (en) * | 2018-12-29 | 2019-05-07 | 蜂巢能源科技有限公司 | A kind of calculation method and device of cell health state SOH |
| CN110133533A (en) * | 2019-06-10 | 2019-08-16 | 珠海东帆科技有限公司 | The method and cell managing device of estimating state of health of battery |
| CN111210049A (en) * | 2019-12-05 | 2020-05-29 | 云南电网有限责任公司玉溪供电局 | LSTM-based method for predicting degradation trend of lead-acid valve-controlled storage battery of transformer substation |
| CN112098850A (en) * | 2020-09-21 | 2020-12-18 | 山东工商学院 | Lithium ion battery voltage fault diagnosis method and system based on SDO algorithm |
| CN112444754A (en) * | 2020-11-18 | 2021-03-05 | 国网上海市电力公司 | Battery state of health estimation method and system based on dynamic impedance |
-
2019
- 2019-12-17 CN CN201911303278.5A patent/CN110988723B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6477024B1 (en) * | 1999-03-12 | 2002-11-05 | Toyota Jidosha Kabushiki Kaisha | Fault determination apparatus and fault determination method for a battery set |
| CN103123992A (en) * | 2011-11-17 | 2013-05-29 | 财团法人工业技术研究院 | Battery pack and method for controlling charge and discharge of battery pack by thermoelectric characteristics thereof |
| CN104656024A (en) * | 2013-11-22 | 2015-05-27 | 韩燕� | Method and device for detecting battery electric quantity and battery |
| CN105015360A (en) * | 2015-06-24 | 2015-11-04 | 安徽江淮汽车股份有限公司 | SOF monitoring method of vehicle power battery |
| CN105068007A (en) * | 2015-07-01 | 2015-11-18 | 清华大学 | Method and system for predicting changes of parameters of lithium ion battery model |
| CN106125009A (en) * | 2016-08-31 | 2016-11-16 | 深圳天珑无线科技有限公司 | Battery performance detection method and battery performance detection device |
| CN107608863A (en) * | 2017-07-31 | 2018-01-19 | 维沃移动通信有限公司 | The calibration method and mobile terminal that a kind of electricity is shown |
| CN107861070A (en) * | 2017-10-25 | 2018-03-30 | 北京交通大学 | A kind of health state of lithium ion battery inline diagnosis method |
| CN109725266A (en) * | 2018-12-29 | 2019-05-07 | 蜂巢能源科技有限公司 | A kind of calculation method and device of cell health state SOH |
| CN110133533A (en) * | 2019-06-10 | 2019-08-16 | 珠海东帆科技有限公司 | The method and cell managing device of estimating state of health of battery |
| CN111210049A (en) * | 2019-12-05 | 2020-05-29 | 云南电网有限责任公司玉溪供电局 | LSTM-based method for predicting degradation trend of lead-acid valve-controlled storage battery of transformer substation |
| CN112098850A (en) * | 2020-09-21 | 2020-12-18 | 山东工商学院 | Lithium ion battery voltage fault diagnosis method and system based on SDO algorithm |
| CN112444754A (en) * | 2020-11-18 | 2021-03-05 | 国网上海市电力公司 | Battery state of health estimation method and system based on dynamic impedance |
Non-Patent Citations (7)
| Title |
|---|
| KE LI ET AL: "Load forecasting method for CCHP system based on", 《2019 14TH IEEE CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS (ICIEA)》 * |
| SEONRI HONG ET AL: "State of Health Estimation for Lithium-Ion", 《 IECON 2020 THE 46TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY》 * |
| XIAOYU LI: "Remaining useful life prediction for lithium-ion batteries based on a hybrid model combining the long short-term memory and Elman neural networks", 《JOURNAL OF ENERGY STORAGE》 * |
| YONGZHIZHANG: "Aging characteristics-based health diagnosis and remaining useful life prognostics for lithium-ion batteries", 《ETRANSPORTATION》 * |
| 张菲菲等: "基于内阻预测的阀控铅酸蓄电池故障预警方法", 《电源技术》 * |
| 李海莹: "阀控式铅酸蓄电池的维护与监测", 《通信电源技术》 * |
| 耿攀等: "基于LSTM 循环神经网络的电池SOC 预测方法", 《上海海事大学学报》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112198443A (en) * | 2020-09-28 | 2021-01-08 | 烽火通信科技股份有限公司 | Method and device for detecting service life of storage battery |
| CN112198443B (en) * | 2020-09-28 | 2023-09-22 | 烽火通信科技股份有限公司 | Method and device for detecting service life of storage battery |
| CN112749509A (en) * | 2020-12-30 | 2021-05-04 | 西华大学 | Intelligent substation fault diagnosis method based on LSTM neural network |
| CN113191081A (en) * | 2021-04-29 | 2021-07-30 | 浙江吉利控股集团有限公司 | New energy vehicle power battery internal resistance prediction method and system |
| CN113591404A (en) * | 2021-09-29 | 2021-11-02 | 杭州宇谷科技有限公司 | Battery abnormity detection system and method based on deep learning |
| CN113591404B (en) * | 2021-09-29 | 2021-12-07 | 杭州宇谷科技有限公司 | Battery abnormity detection system and method based on deep learning |
| CN114089202A (en) * | 2022-01-24 | 2022-02-25 | 天津力神电池股份有限公司 | Method for nondestructively analyzing electrode impedance stability in battery circulation process |
| CN114089202B (en) * | 2022-01-24 | 2022-05-10 | 天津力神电池股份有限公司 | Method for nondestructively analyzing electrode impedance stability in battery circulation process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110988723B (en) | 2022-01-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110988723B (en) | LSTM-based battery internal resistance prediction and fault early warning method | |
| CN108254696A (en) | The health state evaluation method and system of battery | |
| CN114050633A (en) | Dynamic management and control method and device for lithium battery energy storage system and electronic equipment | |
| EP3719515B1 (en) | Evaluation device, evaluation method, and computer program | |
| CN110764014A (en) | Method and device for detecting short circuit in battery, terminal and readable storage medium | |
| JP5089619B2 (en) | Secondary battery deterioration diagnosis device | |
| Chen et al. | Modelling of lithium-ion battery for online energy management systems | |
| CN108205114B (en) | Method and system for predicting service life of battery | |
| CN116381541B (en) | Health assessment method and system for energy storage lithium battery system | |
| CN116559684A (en) | Large-scale battery energy storage power station running state monitoring and evaluating system | |
| CN116401585B (en) | Energy storage battery failure risk assessment method based on big data | |
| CN104316879A (en) | Method for forecasting service life of lead-acid storage battery | |
| CN109061521A (en) | Battery group state-of-charge calculation method and system | |
| CN104198942A (en) | Online judging system for invalidation of valve regulated lead acid storage battery | |
| CN114329760A (en) | Vehicle-mounted lithium ion battery modeling and fault diagnosis method based on digital twinning | |
| CN117491899B (en) | Reliability diagnosis system of mobile energy storage power supply | |
| SE1950652A1 (en) | Method for estimating state of health of a battery | |
| CN113687251B (en) | Double-model-based lithium ion battery pack voltage abnormality fault diagnosis method | |
| CN110794319A (en) | Method and device for predicting parameters of lithium battery impedance model and readable storage medium | |
| CN112379271B (en) | Passivation-considered capacity detection method for carbon-coated lithium thionyl chloride battery | |
| CN116736142B (en) | Method, system and device for early warning of health condition of battery pack | |
| CN118017632A (en) | Method and device for controlling charging of storage battery pack of transformer substation | |
| CN107561452A (en) | A kind of appraisal procedure of batteries health degree | |
| CN116930764A (en) | Power-electron-fused fault diagnosis and danger prediction method for lithium battery energy storage system | |
| CN110376528B (en) | On-line evaluation method and system for lead-acid storage battery pack and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |