CN113687251B - Double-model-based lithium ion battery pack voltage abnormality fault diagnosis method - Google Patents
Double-model-based lithium ion battery pack voltage abnormality fault diagnosis method Download PDFInfo
- Publication number
- CN113687251B CN113687251B CN202110993005.9A CN202110993005A CN113687251B CN 113687251 B CN113687251 B CN 113687251B CN 202110993005 A CN202110993005 A CN 202110993005A CN 113687251 B CN113687251 B CN 113687251B
- Authority
- CN
- China
- Prior art keywords
- model
- soc
- voltage
- terminal voltage
- models
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 title claims abstract description 14
- 229910001416 lithium ion Inorganic materials 0.000 title claims abstract description 14
- 238000003745 diagnosis Methods 0.000 title abstract description 9
- 230000005856 abnormality Effects 0.000 title abstract description 7
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 claims abstract description 17
- 229910052744 lithium Inorganic materials 0.000 claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 6
- 230000002159 abnormal effect Effects 0.000 claims description 14
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 19
- 238000005516 engineering process Methods 0.000 description 5
- 238000002474 experimental method Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000010287 polarization Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- GELKBWJHTRAYNV-UHFFFAOYSA-K lithium iron phosphate Chemical compound [Li+].[Fe+2].[O-]P([O-])([O-])=O GELKBWJHTRAYNV-UHFFFAOYSA-K 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
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]
- G01R31/385—Arrangements for measuring battery or accumulator variables
- G01R31/387—Determining ampere-hour charge capacity or SoC
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Secondary Cells (AREA)
Abstract
The invention relates to a double-model-based lithium ion battery pack voltage abnormality fault diagnosis method, which belongs to the technical field of battery safety and comprises the following steps: collecting battery charge and discharge data including current, voltage, temperature and SOC; step 2: establishing a second-order equivalent circuit model, and identifying model parameters by using a least square method to obtain various parameters of the model under different temperatures and SOCs; step 3: establishing LSTM and Dense models, and training a network model by using collected normal lithium battery operation data; step 4: the SOC obtained by LSTM prediction is respectively used for the output terminal voltages of a second-order equivalent circuit model and a Dense model, and then the terminal voltages output by combining the two models are combined to obtain a terminal voltage which is more accurate than the previous terminal voltage; step 5: and generating residual errors between the model terminal voltage and the actual running terminal voltage, evaluating the residual errors by using a CUSUM, and if the residual errors exceed a threshold value, considering that faults occur.
Description
Technical Field
The invention belongs to the technical field of battery safety, and relates to a double-model-based lithium ion battery pack voltage abnormality fault diagnosis method.
Background
With the increasing severity of energy crisis, the development of new energy sources is becoming more and more important. The current lithium battery technology is the core of the new energy field, and is comprehensively developed in the fields of portable equipment, satellite, reserve power supply, electric automobile and the like due to the ultrahigh applicability of the lithium battery technology. In the application of the secondary power supply which is greatly promoted in China at present, the lithium battery has excellent potential and wide prospect. During long-time use of the lithium battery, unavoidable aging, various faults and other abnormal conditions can occur, if the abnormal conditions are not recognized and isolated in time, serious faults are likely to occur, and then thermal runaway is caused, and even explosion occurs. The safety of the lithium battery is very important, and the development of new energy industry is restricted, so that the fault diagnosis technology of the lithium battery is indispensable.
The existing battery management system is mostly operated by monitoring and estimating various state parameters of the lithium battery, wherein the safety management of the battery is still immature, the current fault diagnosis technology is mostly diagnosed by voltage, and the voltage precision influences the reliability of the fault diagnosis technology because various faults and abnormal conditions of the lithium battery are usually mainly represented by terminal voltage.
Disclosure of Invention
In view of the above, the present invention aims to provide a method for diagnosing abnormal voltage faults of a lithium ion battery pack based on a double model, which improves the accuracy of output voltage based on the model.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a lithium ion battery pack voltage abnormality fault diagnosis method based on a double model comprises the following steps:
step 1: collecting battery charge and discharge data including current, voltage, temperature and SOC;
Step 2: establishing a second-order equivalent circuit model, and identifying model parameters by using a least square method to obtain various parameters of the model under different temperatures and SOCs, wherein the parameters comprise open circuit voltage, ohmic internal resistance, electrochemical polarization RC and concentration polarization RC;
step 3: establishing LSTM and full-connection layer Dense models, and training a network model by using collected normal lithium battery operation data;
Step 4: the SOC obtained by LSTM prediction is respectively used for the output terminal voltages of a second-order equivalent circuit model and a full-connection layer Dense model, and then the terminal voltages output by combining the two models are combined to obtain a terminal voltage which is more accurate than the previous terminal voltage;
Step 5: and generating residual errors between the model terminal voltage and the actual running terminal voltage, evaluating the residual errors by using a CUSUM, and if the residual errors exceed a threshold value, considering that faults occur.
Further, in the step 2, the model parameters are identified by the least square method, and the mathematical expression is:
Finally obtaining the parameters of the model under different temperatures and SOCs, wherein the relation is expressed as
X＝fX(SOC，Te)
X is a certain parameter of the model, SOC is the state of charge of the battery, and Te is the measured temperature.
Further, in step 3, the LSTM network and the full connection layer Dense each include an input layer, an output layer and an hidden layer, where the inputs of the LSTM network are:
Wherein k and n represent an input sample time window and a sample number, respectively, I represents a sample current, ut represents a sample voltage, and T represents a sample temperature;
The output of the LSTM network is the SOC of the predicted next moment;
The LSTM network adjusts super parameters of the network according to the data volume, wherein the super parameters comprise the number of hidden layer neurons and the sizes of time windows k and batchsize;
The input of the full-connection-layer Dense network is (I t,Tt,SOCt) at the current moment, wherein I t represents current at the current moment, T t represents temperature at the current moment, SOC t represents SOC at the current moment, the output of the full-connection-layer Dense network is terminal voltage, and the full-connection-layer Dense network adjusts super parameters of the network according to data quantity, including the number of hidden neurons and batchsize size.
Further, in step 4, the equivalent circuit model ECM and the full connection layer Dense respectively obtain terminal voltages Ut, which are respectively denoted as Ut E,UtD, and the two models are combined to obtain a more accurate Ut, and the specific mathematical expression is as follows:
SOC＝LSTM(I,Ut,T)；
UtD＝Dense(I,T,SOC)；
UtE＝ECM(I，T，SOC)；
In step 5, residual errors are generated between the model terminal voltage and the actual running terminal voltage, the residual errors are evaluated by CUSUM, if the threshold value is exceeded, faults are considered to occur, and accumulated points are taken and calculated: x i - (mu+ksigma), wherein x i is a residual value at each moment, namely, the difference between the model terminal voltage and the actual running terminal voltage, mu is a target value and is 0, sigma is a total deviation, hsigma is a threshold value, k and h are a reference value and a decision value respectively, and the value is selected according to the running length.
Further, the period T of voltage, current, SOC, and temperature at the time of experimental acquisition of battery data was 1 second.
Further, the least square method with forgetting factor recognizes that the parameter is (1-a 1-a2)Uoc(k),a1,a2,a3,a4,a5
The parameters of the final transformed model are:
τ1＝R1C1,τ2＝R2C2。
The invention has the beneficial effects that: the invention adopts the lithium ion battery pack voltage abnormality fault diagnosis method based on the double models, the method adopts the equivalent circuit model and the neural network model to jointly output voltage, and the voltage precision finally obtained is higher than that obtained by adopting a single model. The invention needs to collect data for lithium battery experiments, identifies six equivalent circuit parameters, and has higher model precision and lower calculated amount. The neural network model is divided into two, namely an LSTM network for predicting the SOC and a full-connection layer for outputting the terminal voltage, wherein the predicted SOC is used as the input of the equivalent circuit model and the full-connection layer model respectively. The final terminal voltage is the average of the full connection layer model outputs of the equivalent circuit model. And finally, in actual operation, generating residual errors with the measured voltage, and judging whether abnormality occurs by accumulation and evaluation. After the identification model and the offline training are completed, the method can be used for monitoring the energy storage battery in real time, has higher reliability, provides a new solution for timely finding potential faults of the battery, prevents serious faults and even thermal runaway, and improves the performance of a battery management system, particularly the battery safety management.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objects and other advantages of the invention may be realized and obtained by means of the instrumentalities and combinations particularly pointed out in the specification.
Drawings
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in the following preferred detail with reference to the accompanying drawings, in which:
FIG. 1 is a flow chart of a method for diagnosing abnormal voltage faults of a lithium ion battery pack based on a double model;
FIG. 2 shows an equivalent circuit parameter identification result diagram of an embodiment of the present invention, wherein (a) is a parameter Em result diagram, (b) is a parameter R0 result diagram, (c) is a parameter R1 result diagram, (d) is a parameter R2 result diagram, (e) is a parameter tau1 result diagram, and (f) is a parameter tau2 result diagram;
FIG. 3 shows the LSTM and Dense network test results of the embodiment of the invention, wherein (a) is a LSTM network test result diagram and (b) is a Dense network test result diagram;
FIG. 4 shows the result of Ut output of the equivalent circuit model Ut and the combination of the models in the embodiment of the invention, wherein (a) is a diagram of the result of Ut output of the equivalent circuit model and (b) is a diagram of the result of Ut output of the combination of the two models;
Fig. 5 shows a residual diagram and an accumulated sum diagram of an actual operation of an embodiment of the present invention, (a) shows a residual diagram of a sample 1, (b) shows an accumulated sum diagram of a sample 1, (c) shows a residual diagram of a sample 2, (d) shows an accumulated sum diagram of a sample 2, (e) shows a residual diagram of a sample 3, and (f) shows an accumulated sum diagram of a sample 3.
Detailed Description
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the illustrations provided in the following embodiments merely illustrate the basic idea of the present invention by way of illustration, and the following embodiments and features in the embodiments may be combined with each other without conflict.
Wherein the drawings are for illustrative purposes only and are shown in schematic, non-physical, and not intended to limit the invention; for the purpose of better illustrating embodiments of the invention, certain elements of the drawings may be omitted, enlarged or reduced and do not represent the size of the actual product; it will be appreciated by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numbers in the drawings of embodiments of the invention correspond to the same or similar components; in the description of the present invention, it should be understood that, if there are terms such as "upper", "lower", "left", "right", "front", "rear", etc., that indicate an azimuth or a positional relationship based on the azimuth or the positional relationship shown in the drawings, it is only for convenience of describing the present invention and simplifying the description, but not for indicating or suggesting that the referred device or element must have a specific azimuth, be constructed and operated in a specific azimuth, so that the terms describing the positional relationship in the drawings are merely for exemplary illustration and should not be construed as limiting the present invention, and that the specific meaning of the above terms may be understood by those of ordinary skill in the art according to the specific circumstances.
Referring to fig. 1 to 5, the battery data used in the embodiment of the present invention is a public battery data set of university of maryland. The data acquired in the first step of the inventive content is thus the data set here. The battery used for obtaining the data set experiment is an A123 lithium iron phosphate battery, and the charge and discharge experiments are respectively carried out at 0, 10, 20, 25, 30 and 40 degrees, and 3 working conditions are used, namely DST, US06 and FUDS. The high-precision sensor for experiments collects voltage, current, temperature and charge and discharge capacity.
The present embodiment is as follows:
And step 1, collecting voltage, current, temperature and SOC (system on chip) through charge and discharge experiments on the lithium battery at different temperatures, wherein the period is 1 second. The public data set of university of maryland is used herein. The data used in the data set are time, current, voltage, charge-discharge capacity and temperature.
Step 2, establishing a second-order equivalent circuit model, and carrying out parameter identification by using the data in the step 1 to obtain corresponding parameters under different temperatures and SOCs, wherein the identification result of the parameters of the equivalent circuit at 25 degrees is shown in a table 1:
TABLE 1
The error of the equivalent circuit model under the identification parameters for three working conditions at 25 degrees is shown in table 2:
TABLE 2
Parameters at the remaining temperatures are identified as shown in fig. 1.
And 3, firstly, building an LSTM network to predict the SOC. The LSTM network has an input format (number of samples, time step, sample characteristics). Wherein the number of samples and the number of sample characteristics are known, the sample characteristics are current, voltage and temperature, and the time step is a hyper-parameter that needs to be adjusted. The output is SOC. The DST working condition data is normalized and used for training a network, and the time step, the hidden layer neuron number, the optimizer, batchsize size and epoch size are adjusted in a grid search mode. The results after adjustment according to loss are shown in Table 3:
TABLE 3 Table 3
A full connection layer network is also built for the output terminal voltage, the input format of the Dense network being (number of samples, sample characteristics). Wherein the sample is characterized by current, temperature and SOC and the output is Ut. And the optimal hidden layer neuron number, the optimal device, batchsize size and epoch size are obtained by adopting a grid search mode, and the results are shown in the table after adjustment. After training the two networks, the test results using FUDS operating conditions are shown in fig. 2.
Step 4, in order to obtain more accurate voltage, the voltage output of the two ends in the step 2 and the step 3 are combined, and the specific mathematical expression is as follows:
SOC＝LSTM(I,Ut,T)；
UTDense＝Dense(I,T,SOC)；
UtECM＝ECM(I,T,SOC)；
FIG. 3 is the terminal voltage output by the equivalent circuit under 20 DEG FUDS conditions and the terminal voltage output after combining the double models.
And 5, in order to simulate the abnormal condition of the actually operated lithium battery, the working condition of FUDS degrees is used for illustration. And connecting proper resistors in parallel at two ends of the lithium battery to simulate the abnormal condition of the lithium battery, collecting actual operation data, generating residual errors by the actual operation measurement voltage and the output voltage based on the double models, and accumulating and evaluating the residual errors. The specific process is as follows:
Firstly, respectively connecting 10 ohms, 30 ohms and 5000 ohms in parallel at two ends of a lithium battery, wherein the triggering time is 4000 seconds, 3500 seconds and 2000 seconds respectively, charging and discharging are carried out under the working condition of FUDS at 20 ℃ to obtain 3 samples, and the same working condition is used for acting on two models to obtain the output voltage of the models. The difference between the sample voltage and the model output voltage is the residual. The results are shown in FIG. 4. It can be seen that for the first two samples, the abnormal condition is accurately identified by the method, and the parallel resistance of the 3 rd sample is very large, which can be basically regarded as the normal condition.
Finally, it is noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made thereto without departing from the spirit and scope of the present invention, which is intended to be covered by the claims of the present invention.
Claims (6)
1. A method for diagnosing abnormal voltage faults of a lithium ion battery pack based on a double model is characterized by comprising the following steps of: the method comprises the following steps:
step 1: collecting battery charge and discharge data including current, voltage, temperature and SOC;
step 2: establishing a second-order equivalent circuit model ECM, and identifying model parameters by using a least square method to obtain all parameters of the second-order equivalent circuit model ECM under different temperatures and SOCs;
step 3: establishing LSTM and full-connection layer Dense models, and training a network model by using collected normal lithium battery operation data;
step 4: the SOC obtained by LSTM prediction is respectively used for the output terminal voltages of a second-order equivalent circuit model ECM and a full-connection layer Dense model, and then the terminal voltages output by the two models are combined to obtain an accurate terminal voltage;
Step 5: and generating residual errors between the model terminal voltage and the actual running terminal voltage, evaluating the residual errors by using a CUSUM, and if the residual errors exceed a threshold value, considering that faults occur.
2. The method for diagnosing abnormal voltage faults of the lithium ion battery pack based on the double models as claimed in claim 1, wherein the method comprises the following steps of: in the step 2, the parameters of the ECM model are identified by a least square method, and the mathematical expression is as follows:
Finally obtaining the parameters of the model under different temperatures and SOCs, wherein the relation is expressed as
X＝fX(SOC，Te)
X is a certain parameter of the model, SOC is the state of charge of the battery, te is the measured temperature;
The least square method with forgetting factor recognizes that the parameter is (1-a 1-a2)Uoc(k),a1,a2,a3,a4,a5
The parameters of the final transformed model are:
τ1＝R1C1,τ2＝R2C2。
3. the method for diagnosing abnormal voltage faults of the lithium ion battery pack based on the double models as claimed in claim 1, wherein the method comprises the following steps of: in step 3, the LSTM network and the full connection layer Dense each include an input layer, an output layer and an hidden layer, where the inputs of the LSTM network are:
Wherein k and n respectively represent an input sample time window and a sample number, I represents a sample current, ut represents a sample terminal voltage, and T represents a sample temperature;
The output of the LSTM network is the SOC of the predicted next moment;
The LSTM network adjusts super parameters of the network according to the data volume, wherein the super parameters comprise the number of hidden layer neurons and the sizes of time windows k and batchsize;
The input of the full-connection-layer Dense network is (I t,Tt,SOCt) at the current moment, wherein I t represents current at the current moment, T t represents temperature at the current moment, SOC t represents SOC at the current moment, the output of the full-connection-layer Dense network is terminal voltage, and the full-connection-layer Dense network adjusts super parameters of the network according to data quantity, including the number of hidden neurons and batchsize size.
4. The method for diagnosing abnormal voltage faults of the lithium ion battery pack based on the double models as claimed in claim 1, wherein the method comprises the following steps of: in the step 4, the second-order equivalent circuit model ECM and the full connection layer Dense respectively obtain terminal voltages, which are respectively expressed as Ut E,UtD, and the two models are combined to obtain more accurate Ut, and the specific mathematical expression is as follows:
SOC＝LSTM(I,Ut,T)；
UtD＝Dense(I,T,SOC)；
UtE＝ECM(I,T,SOC)；
5. The method for diagnosing abnormal voltage faults of the lithium ion battery pack based on the double models as claimed in claim 1, wherein the method comprises the following steps of: in step 5, residual errors are generated between the model terminal voltage and the actual running terminal voltage, CUSUM is used for evaluating the residual errors, if the residual errors exceed a threshold value, faults are considered to occur, and each point is accumulated and calculated: x i - (mu+ksigma), wherein x i is a residual value at each moment, namely, the difference between the model terminal voltage and the actual running terminal voltage, mu is a target value and is 0, sigma is a total deviation, hsigma is a threshold value, k and h are a reference value and a decision value respectively, and the value is selected according to the running length.
6. The method for diagnosing abnormal voltage faults of the lithium ion battery pack based on the double models as claimed in claim 1, wherein the method comprises the following steps of: the period T of voltage, current, SOC and temperature at the time of experimental battery data acquisition was 1 second.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110993005.9A CN113687251B (en) | 2021-08-23 | 2021-08-23 | Double-model-based lithium ion battery pack voltage abnormality fault diagnosis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110993005.9A CN113687251B (en) | 2021-08-23 | 2021-08-23 | Double-model-based lithium ion battery pack voltage abnormality fault diagnosis method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113687251A CN113687251A (en) | 2021-11-23 |
| CN113687251B true CN113687251B (en) | 2024-07-30 |
Family
ID=78583191
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110993005.9A Active CN113687251B (en) | 2021-08-23 | 2021-08-23 | Double-model-based lithium ion battery pack voltage abnormality fault diagnosis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113687251B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114994543A (en) * | 2022-08-01 | 2022-09-02 | 湖南华大电工高科技有限公司 | Energy storage power station battery fault diagnosis method and device and storage medium |
| CN116068479A (en) * | 2023-03-07 | 2023-05-05 | 潍柴动力股份有限公司 | Abnormality detection method and device for output performance signal in fuel cell endurance test |
| CN118311432A (en) * | 2024-05-10 | 2024-07-09 | 山东大学 | Battery short-circuit fault diagnosis method and system based on future parameter prediction |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107390138A (en) * | 2017-09-13 | 2017-11-24 | 山东大学 | Electrokinetic cell equivalent circuit model parameter iteration new method for identifying |
| CN110208704A (en) * | 2019-04-29 | 2019-09-06 | 北京航空航天大学 | A kind of lithium battery modeling method and system based on voltage delay effect |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110568360B (en) * | 2019-09-12 | 2020-08-14 | 华中科技大学 | Lithium battery aging diagnosis method based on fuzzy logic algorithm |
| CN111220921A (en) * | 2020-01-08 | 2020-06-02 | 重庆邮电大学 | Lithium battery capacity estimation method based on improved convolution-long-and-short-term memory neural network |
| CN111999657B (en) * | 2020-10-29 | 2021-01-29 | 北京航空航天大学 | Method for evaluating driving mileage of lithium ion battery of electric vehicle in residual life |
| CN112285569B (en) * | 2020-10-29 | 2022-02-01 | 哈尔滨工业大学（威海） | Electric vehicle fault diagnosis method based on dynamic threshold model |
| CN112946480B (en) * | 2021-01-28 | 2022-08-12 | 中国矿业大学 | Lithium battery circuit model simplification method for improving SOC estimation real-time performance |
| CN113049962B (en) * | 2021-03-24 | 2022-07-19 | 国网浙江省电力有限公司电力科学研究院 | LSTM-based energy storage device operation situation deduction method |
-
2021
- 2021-08-23 CN CN202110993005.9A patent/CN113687251B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107390138A (en) * | 2017-09-13 | 2017-11-24 | 山东大学 | Electrokinetic cell equivalent circuit model parameter iteration new method for identifying |
| CN110208704A (en) * | 2019-04-29 | 2019-09-06 | 北京航空航天大学 | A kind of lithium battery modeling method and system based on voltage delay effect |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113687251A (en) | 2021-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lipu et al. | A review of state of health and remaining useful life estimation methods for lithium-ion battery in electric vehicles: Challenges and recommendations | |
| Gan et al. | Data-driven fault diagnosis of lithium-ion battery overdischarge in electric vehicles | |
| Yang et al. | A fractional-order model-based battery external short circuit fault diagnosis approach for all-climate electric vehicles application | |
| Zhang et al. | Aging characteristics-based health diagnosis and remaining useful life prognostics for lithium-ion batteries | |
| US11422194B2 (en) | Battery diagnosis apparatus and battery diagnosis method based on current pulse method | |
| CN113687251B (en) | Double-model-based lithium ion battery pack voltage abnormality fault diagnosis method | |
| Lyu et al. | A new method for lithium-ion battery uniformity sorting based on internal criteria | |
| Seo et al. | Online detection of soft internal short circuit in lithium-ion batteries at various standard charging ranges | |
| CN113933732B (en) | New energy automobile power battery health state analysis method, system and storage medium | |
| Takyi-Aninakwa et al. | An optimized relevant long short-term memory-squared gain extended Kalman filter for the state of charge estimation of lithium-ion batteries | |
| CN113447828B (en) | Lithium battery temperature estimation method and system based on Bayesian neural network | |
| CN106526488A (en) | Fault diagnosis method of sensors in tandem type power battery pack | |
| Chang et al. | Electric vehicle battery pack micro-short circuit fault diagnosis based on charging voltage ranking evolution | |
| Liu et al. | Online health prognosis for lithium-ion batteries under dynamic discharge conditions over wide temperature range | |
| CN114924193A (en) | Battery safety assessment method | |
| Zheng et al. | Quantitative short circuit identification for single lithium-ion cell applications based on charge and discharge capacity estimation | |
| Qiuting et al. | State of health estimation for lithium-ion battery based on D-UKF | |
| Zhao et al. | State-of-health estimation with anomalous aging indicator detection of lithium-ion batteries using regression generative adversarial network | |
| Shang et al. | Research progress in fault detection of battery systems: A review | |
| Wu et al. | Research on short-circuit fault-diagnosis strategy of lithium-ion battery in an energy-storage system based on voltage cosine similarity | |
| Fan et al. | A novel method of quantitative internal short circuit diagnosis based on charging electric quantity in fixed voltage window | |
| Wang et al. | An Incipient Multi-Fault Diagnosis Method for Lithium-Ion Battery Pack Based on Data-Driven with Incremental-Scale | |
| CN113391214A (en) | Battery micro-fault diagnosis method based on battery charging voltage ranking change | |
| Ren et al. | Multi-fault diagnosis strategy based on a non-redundant interleaved measurement circuit and improved fuzzy entropy for the battery system | |
| Tang et al. | An aging-and load-insensitive method for quantitatively detecting the battery internal-short-circuit resistance |
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 |