CN115856682B - Lithium battery capacity jump point personalized early warning method based on critical point transition - Google Patents
Lithium battery capacity jump point personalized early warning method based on critical point transition Download PDFInfo
- Publication number
- CN115856682B CN115856682B CN202211674573.3A CN202211674573A CN115856682B CN 115856682 B CN115856682 B CN 115856682B CN 202211674573 A CN202211674573 A CN 202211674573A CN 115856682 B CN115856682 B CN 115856682B
- Authority
- CN
- China
- Prior art keywords
- early warning
- capacity
- curve
- lithium battery
- point
- 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
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Secondary Cells (AREA)
Abstract
The invention discloses a lithium battery capacity jump point personalized early warning method based on critical point transition, which belongs to the technical field of battery storage and comprises the following steps: collecting voltage and capacity data of the lithium battery in different charge and discharge cycles to calculate and obtain a capacity degradation curve and an IC peak value curve; inputting the capacity degradation curve and the IC peak curve into a pre-established jump point early warning model so as to extract a plurality of early warning signals based on a critical point early warning method; acquiring corresponding early warning signal curves based on a plurality of early warning signals; and setting different discrimination thresholds according to individuation of the early warning signal curve aiming at lithium batteries of different types and working conditions, and early warning the capacity jump point of the lithium battery by utilizing the discrimination thresholds. The method solves the problem that the existing manual judgment and experience prediction method is difficult to predict the diving point in advance, realizes personalized early warning, and has good accuracy and robustness.
Description
Technical Field
The invention belongs to the technical field of battery storage, and particularly relates to a lithium battery capacity jump point personalized early warning method based on critical point transition.
Background
In the use process of the lithium battery, capacity degradation can occur, and due to the reasons of lithium precipitation on the surface of a negative electrode, failure of an active material of a positive electrode, consumption of electrolyte and the like, sudden capacity jump phenomenon often occurs, namely, after the capacity of the lithium battery is degraded to a certain degree, the degradation is suddenly accelerated, and the capacity is degraded to the end of service life in a short time. The capacity water jump of the lithium battery can lead to the great reduction of the service performance of the lithium battery, the problem of lithium battery failure and even thermal runaway is more easy to occur, the lithium battery becomes a great hidden danger for influencing the service safety of the lithium battery, and the operation safety and reliability of a lithium battery system are challenged. Therefore, early warning is carried out before the capacity jump of the lithium battery occurs, and the lithium battery with the capacity jump to be generated is replaced in time, so that the problem which is urgent to be solved at present is solved.
However, there is no prediction method for lithium battery capacity jump, and the existing method mainly comprises manual judgment and experience prediction. The manual judgment method predicts the diving point through offline visual recognition, and has low time and labor consumption and low accuracy; the empirical estimation method judges the approximate position of the jump point through experience, for example, the capacity jump inflection point of most lithium batteries is about 0.8 in state of health (SOH), and the corresponding cycle number can be used as the jump point, but the deviation between the method and the actual result is larger. Meanwhile, the two methods are difficult to predict the jump point in advance, so that development of a new method for realizing stable and accurate early warning of the jump point of the capacity of the lithium battery is needed.
Disclosure of Invention
Aiming at the defects or improvement demands of the prior art, the invention provides a lithium battery capacity jump point personalized early warning method based on critical point transition, which aims to input an acquired capacity degradation curve and an IC peak curve into a pre-established jump point early warning model so as to extract a plurality of early warning signals based on the critical point early warning method, and personalized setting different discrimination thresholds according to the early warning signal curve, thereby solving the technical problems of low accuracy and poor advance in the existing jump point early warning technology.
In order to achieve the above object, according to an aspect of the present invention, there is provided a lithium battery capacity jump point personalized early warning method based on critical point transition, including:
s1: calculating to obtain a capacity degradation curve and an IC peak value curve by using voltage and capacity data of the lithium battery in different charge and discharge cycles;
s2: inputting the capacity degradation curve and the IC peak curve into a pre-established jump point early warning model so as to extract a plurality of early warning signals based on a critical point early warning method; acquiring corresponding early warning signal curves based on a plurality of early warning signals;
s3: and setting different discrimination thresholds according to individuation of the early warning signal curve aiming at lithium batteries of different types and working conditions, and early warning the capacity jump point of the lithium battery by utilizing the discrimination thresholds.
In one embodiment, the S1 includes:
s11: the method comprises the steps of acquiring voltage and capacity data in different charge and discharge cycles of the lithium battery through experiments, wherein the voltage and capacity data comprise: constant current charging voltage curve, constant current charging capacity curve and total discharge capacity data;
s12: drawing the capacity degradation curve according to the total discharge capacity data;
s13: and extracting the IC peak value curve according to the constant-current charging voltage curve and the constant-current charging capacity curve.
In one embodiment, the step S13 includes: fitting and differentiating the constant-current charging voltage curve and the constant-current charging capacity curve by adopting an incremental capacity analysis method, so as to obtain IC curves of the lithium battery under different charge and discharge cycles; and carrying out peak extraction on the IC curves of the lithium battery under different charge and discharge cycles to determine the IC peak curves.
In one embodiment, the jump point early warning model includes: a curve smoothing section, a residual calculation section, and a sliding window extraction section; the step S2 comprises the following steps:
the curve smoothing part smoothes the input capacity degradation curve and the IC peak value curve by adopting local weighted regression;
the residual calculation part is used for calculating the capacity degradation curve and the IC peak value curve and the smoothed curves respectively corresponding to calculate residual errors, so as to obtain residual error sequences, and the residual error sequences correspond to the degree of deviation of signals from the equilibrium state at different moments;
and the sliding window signal extraction part performs sliding window on the residual sequence by utilizing a window and calculates a plurality of early warning signals so as to acquire the early warning signal curves under different charge and discharge cycles.
In one embodiment, the pre-warning signal comprises: variance signal Var, autocorrelation coefficient AC, kurtosis and skewness Shew;
wherein x is i The input data is represented by a representation of the input data,and n is the length of the input data and is the average value of the input data.
In one embodiment, as the capacity jump point approaches, the variance signal Var increases with the autocorrelation coefficient AC, and the skewness Skew and kurtosis Kurt will change accordingly.
In one embodiment, the method further comprises: for the lithium battery in operation, the jump point early warning model calculates early warning signals corresponding to historical data and continuously monitors the early warning signals in a rolling way; and when the early warning signal meets the discrimination threshold, early warning is carried out, so that early warning of the diving point is realized.
According to another aspect of the present invention, there is provided a lithium battery capacity trip point personalized early warning device based on critical point transition, including:
the calculation module is used for calculating a capacity degradation curve and an IC peak value curve by utilizing the voltage and capacity data of the lithium battery in different charge and discharge cycles;
the input module is used for inputting the capacity degradation curve and the IC peak value curve into a pre-established jump point early warning model so as to extract a plurality of early warning signals based on a critical point early warning method; acquiring corresponding early warning signal curves based on a plurality of early warning signals;
and the judging module is used for setting different judging thresholds according to individuation of the early warning signal curve aiming at lithium batteries of different types and working conditions, and carrying out early warning on the capacity jump point of the lithium batteries by utilizing the judging thresholds.
According to another aspect of the invention there is provided an electronic device comprising a memory storing a computer program and a processor implementing the steps of the above method when the processor executes the computer program.
According to another aspect of the present invention there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above method.
In general, the above technical solutions conceived by the present invention, compared with the prior art, enable the following beneficial effects to be obtained:
(1) The invention provides a lithium battery capacity jump point early warning method, which inputs an acquired capacity degradation curve and an IC peak curve into a pre-established jump point early warning model so as to extract a plurality of early warning signals based on a critical point early warning method; aiming at the early warning signals extracted by the lithium batteries with different types and different working conditions, the discrimination threshold corresponding to optimization is set individually, so that the individual early warning of the lithium battery jump point is realized. The problem that the existing manual judgment and experience prediction method is difficult to predict the diving point in advance is solved, personalized early warning is realized, and good accuracy and robustness are achieved.
(2) The invention is based on a complex system critical point early warning method, and an interpretable mechanism model is used for extracting a lithium battery capacity water jump early warning signal; due to the critical deceleration phenomenon, the extracted early warning signal can reflect the approaching degree of the diving point, and has higher interpretability.
(3) And the early warning signals are extracted from data such as historical voltage, capacity and the like by adopting a sliding window mode, and the prediction is continuously rolled, so that the monitoring and early warning of the capacity jump point of the lithium battery in real time are ensured.
Drawings
FIG. 1 is a schematic diagram of a personalized early warning method for lithium capacitance jump points based on a critical point phenomenon according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a personalized early warning method for lithium capacitance trip points based on a critical point phenomenon according to another embodiment of the present invention;
FIG. 3 is a graph of a characteristic curve of a lithium battery and a calculated early warning signal according to an embodiment of the present invention;
fig. 4 is a diagram of a jump point early warning effect of a lithium battery according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. In addition, the technical features of the embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
In order to achieve the purpose, the personalized early warning method for the lithium battery capacity jump point based on the critical point phenomenon comprises the following steps:
s1: calculating to obtain a capacity degradation curve and an IC peak value curve by using voltage and capacity data of the lithium battery in different charge and discharge cycles;
s2: inputting the capacity degradation curve and the IC peak curve into a pre-established jump point early warning model so as to extract a plurality of early warning signals based on a critical point early warning method; acquiring a corresponding early warning signal curve based on the plurality of early warning signals;
s3: different discrimination thresholds are set individually according to the early warning signal curves aiming at lithium batteries of different types and working conditions, and the capacity jump points of the lithium batteries are early warned by utilizing the discrimination thresholds.
Specifically, firstly, processing collected lithium battery data, and calculating an IC curve by using charging capacity data (Q) and charging voltage data (V); and fitting the Q-V curve by using a 5 th order polynomial (the corresponding IC curve comprises two peaks), and differentiating the fitted curve to obtain the IC curve. And extracting the peak value of the IC curve under different charge and discharge cycles to obtain an IC peak value curve, and combining the capacity degradation curve for extracting the early warning signal. After the capacity degradation curve and the IC peak curve are extracted, a jump point early warning model is input to calculate an early warning signal. Different discrimination thresholds are set individually according to the early warning signal curves aiming at lithium batteries of different types and working conditions, and the capacity jump points of the lithium batteries are early warned by utilizing the discrimination thresholds.
In one embodiment, the jump point early warning model mainly comprises three parts, namely curve smoothing, residual error calculation and signal extraction by sliding window
The curve smoothing section smoothes the input curve using local weighted regression. The smoothed data point length of the locally weighted regression is 0.6 times the historical data length. And smoothing the capacity degradation curve and the IC peak curve of each lithium battery for residual calculation.
And the residual calculation part subtracts the original curve and the smoothed curve to calculate residual, so as to obtain the degree of deviation of the corresponding signal from the equilibrium state at different moments, and the degree is used for extracting the early warning signal.
The sliding window extraction part performs sliding window on the residual sequence through a window with the length of 0.5 times of the sequence length and calculates four early warning signals, and finally, early warning signal curves under different charge and discharge cycles are obtained. By the critical deceleration phenomenon, along with the approach of the lithium battery jump point, the capability of the input signal from the off-balance state to the restoration of the balance state gradually weakens, and the corresponding variance signal and the first-order autocorrelation signal gradually increase. The final input signal is biased to one side of the equilibrium state, and the kurtosis and the skewness of the corresponding curve also change regularly. Therefore, the extracted early warning signal is closely related to the capacity water jump phenomenon of the lithium battery.
In one embodiment, the early warning signal consists essentially of: the variance signal (Var), the first order autocorrelation signal (AC), the Kurt signal (Kurt) and the skewness signal (Skew) are formulated as follows:
wherein x is i The input data is represented by a representation of the input data,n is the length of the input data, which is the mean value of the input data.
Further, the discrimination threshold is optimized individually for the early warning signals extracted by lithium batteries with different types and different working conditions, so as to realize stable and accurate jump point early warning. For the actual jump occurrence point, a baseline is obtained by regression with 0.5 quantile, the quartile range is calculated and the position 1.5 times the quartile range from the baseline is taken as an upper boundary and a lower boundary. Since about 99.3% of the data is contained between the upper and lower bounds, the likelihood that consecutive points lie outside the upper and lower bounds is close to 0. When the capacity corresponding to 5 consecutive cycles is outside the upper and lower limits, the capacity of the cycle is set to be an abnormal value, and the abnormal value is taken as an actual jump occurrence point.
Further, for the lithium battery in operation, historical charging voltage, charging capacity and total discharge capacity are extracted, a lithium battery capacity degradation curve and an IC peak curve are obtained through calculation, a jump point early warning model is input to calculate early warning signals in a real-time rolling mode, and early warning is carried out when the early warning signals meet discrimination thresholds.
As shown in fig. 1 and fig. 2, the personalized early warning method for the lithium battery capacity jump point based on the critical point phenomenon comprises data acquisition, characteristic curve calculation, early warning signal extraction and personalized threshold judgment.
The data acquisition part is used for acquiring curves of the total discharge capacity, the charge voltage and the like of the lithium battery;
the characteristic curve calculation part is used for calculating a lithium battery capacity degradation curve and an IC curve and calculating an IC peak value curve for extracting an early warning signal;
the early warning signal extraction part is used for calculating residual errors of the input signal and the smooth curve, and calculating a variance curve, an autocorrelation curve, a kurtosis and skewness curve from the residual errors to serve as an early warning signal;
and the threshold value judging part is used for individually setting and optimizing different judging thresholds for lithium batteries with different types and different working conditions, so that a stable and accurate early warning effect is realized.
In order to verify the jump point early warning effect of the invention, a lithium battery data set with 3 types and 2 working conditions collected by the inventor is selected as experimental data. And extracting characteristic curves from the charge capacity, the charge voltage and the total discharge capacity of the experimental data, and calculating early warning signals according to the characteristic curves, as shown in fig. 3.
Further, different discrimination thresholds are individually set and optimized for lithium batteries with different types and different working conditions, such as for the COF-SA-NCM811-0.2C lithium battery of fig. 3, the capacity degradation curve threshold is set as Var>5×10 -6 ，AC>0.5，Kurt>4，Skew<-1.5 IC peak curve threshold Var>2×10 -3 ，AC>0.4，Kurt>4，Skew>And 0.8, the early warning effect of the diving point is shown in figure 4.
Further, the early warning results of the frame on the jump points of the lithium batteries with different types and different working conditions are shown in the following table.
TABLE 1 diving spot early warning effect
The table shows that the method has higher accuracy, timeliness and robustness in the aspect of early warning of the lithium battery jump point, and can early warn in time before the actual circulation of capacity jump.
In conclusion, the model constructed by the embodiment of the invention can perform early warning on the capacity jump point of the lithium battery in real time in a personalized way, has good accuracy, timeliness and robustness, and can be widely applied to a health management system of the lithium battery.
It will be readily appreciated by those skilled in the art that the foregoing description is merely a preferred embodiment of the invention and is not intended to limit the invention, but any modifications, equivalents, improvements or alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (8)
1. The personalized early warning method for the lithium battery capacity jump point based on critical point transition is characterized by comprising the following steps of:
s1: collecting voltage and capacity data of the lithium battery in different charge and discharge cycles to calculate and obtain a capacity degradation curve and an IC peak value curve;
s2: inputting the capacity degradation curve and the IC peak curve into a pre-established jump point early warning model so as to extract a plurality of early warning signals based on a critical point early warning method; acquiring corresponding early warning signal curves based on a plurality of early warning signals;
s3: different discrimination thresholds are set individually according to the early warning signal curves aiming at lithium batteries of different types and working conditions, and the capacity jump points of the lithium batteries are early warned by utilizing the discrimination thresholds;
the S1 comprises the following steps: s11: the method comprises the steps of acquiring voltage and capacity data in different charge and discharge cycles of the lithium battery through experiments, wherein the voltage and capacity data comprise: a constant current charging voltage curve, a constant current charging capacity curve and a total discharge capacity curve; s12: drawing the capacity degradation curve according to the total discharge capacity data; s13: extracting the IC peak value curve according to the constant-current charging voltage curve and the constant-current charging capacity curve;
the step S13 includes: fitting and differentiating the constant-current charging voltage curve and the constant-current charging capacity curve by adopting an incremental capacity analysis method, so as to obtain IC curves of the lithium battery under different charge and discharge cycles; and carrying out peak extraction on the IC curves of the lithium battery under different charge and discharge cycles to determine the IC peak curves.
2. The personalized early warning method for the jump point of the capacity of the lithium battery based on the critical point transition as claimed in claim 1, wherein the jump point early warning model comprises: a curve smoothing section, a residual calculation section, and a sliding window extraction section; the step S2 comprises the following steps:
the curve smoothing part smoothes the input capacity degradation curve and the IC peak value curve by adopting local weighted regression;
the residual calculation part is used for calculating the capacity degradation curve and the IC peak value curve and the smoothed curves respectively corresponding to calculate residual errors, so as to obtain residual error sequences, and the residual error sequences correspond to the degree of deviation of signals from the equilibrium state at different moments;
and the sliding window extraction part performs sliding window on the residual sequence by utilizing a window and calculates a plurality of early warning signals so as to acquire the early warning signal curves under different charge and discharge cycles.
3. The personalized early warning method for the lithium battery capacity jump point based on critical point transition according to claim 2, wherein the early warning signal comprises: variance signal Var, autocorrelation coefficient AC, kurtosis and skewness Shew;
wherein x is i The input data is represented by a representation of the input data,is the average value of the input data, n is theThe length of the input data.
4. The personalized early warning method for lithium battery capacity jump points based on critical point transition according to claim 3, wherein as the capacity jump point approaches, the variance signal Var increases with the autocorrelation coefficient AC, and the skewness Skew and Kurt change accordingly.
5. The critical point transition-based lithium battery capacity jump point personalized early warning method of claim 1, further comprising: for the lithium battery in operation, the jump point early warning model calculates early warning signals corresponding to historical data and continuously monitors the early warning signals in a rolling way; and when the early warning signal meets the discrimination threshold, early warning is carried out, so that early warning of the diving point is realized.
6. The personalized early warning device for the lithium battery capacity jump point based on the critical point transition is characterized by being used for executing the personalized early warning method for the lithium battery capacity jump point based on the critical point transition, which is disclosed in any one of claims 1-5, and comprises the following steps:
the data acquisition module is used for acquiring voltage and capacity data of the lithium battery in different charge and discharge cycles so as to calculate and obtain a capacity degradation curve and an IC peak value curve;
the signal extraction module is used for inputting the capacity degradation curve and the IC peak value curve into a pre-established jump point early warning model so as to extract a plurality of early warning signals based on a critical point early warning method; acquiring corresponding early warning signal curves based on a plurality of early warning signals;
and the threshold judging module is used for setting different judging thresholds according to individuation of the early warning signal curve aiming at lithium batteries of different types and working conditions, and carrying out early warning on the capacity jump point of the lithium batteries by utilizing the judging thresholds.
7. An electronic device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211674573.3A CN115856682B (en) | 2022-12-26 | 2022-12-26 | Lithium battery capacity jump point personalized early warning method based on critical point transition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211674573.3A CN115856682B (en) | 2022-12-26 | 2022-12-26 | Lithium battery capacity jump point personalized early warning method based on critical point transition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115856682A CN115856682A (en) | 2023-03-28 |
| CN115856682B true CN115856682B (en) | 2023-09-01 |
Family
ID=85654777
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211674573.3A Active CN115856682B (en) | 2022-12-26 | 2022-12-26 | Lithium battery capacity jump point personalized early warning method based on critical point transition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115856682B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011208966A (en) * | 2010-03-29 | 2011-10-20 | Nec Corp | Remaining life estimation device, computer program thereof, and data processing method |
| CN109143078A (en) * | 2018-08-28 | 2019-01-04 | 中航锂电技术研究院有限公司 | A kind of identification pre-judging method of lithium iron phosphate dynamic battery " diving " failure |
| CN110927607A (en) * | 2019-11-22 | 2020-03-27 | 武汉理工大学 | Method and system for identifying and quantitatively analyzing degradation mechanism of lithium ion battery |
| CN112327191A (en) * | 2020-10-21 | 2021-02-05 | 北京航空航天大学 | Battery diving probability evaluation method based on geometric feature fusion decision |
| CN114114049A (en) * | 2021-09-30 | 2022-03-01 | 北京交通大学 | Lithium ion battery life prediction method based on sample migration |
-
2022
- 2022-12-26 CN CN202211674573.3A patent/CN115856682B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011208966A (en) * | 2010-03-29 | 2011-10-20 | Nec Corp | Remaining life estimation device, computer program thereof, and data processing method |
| CN109143078A (en) * | 2018-08-28 | 2019-01-04 | 中航锂电技术研究院有限公司 | A kind of identification pre-judging method of lithium iron phosphate dynamic battery " diving " failure |
| CN110927607A (en) * | 2019-11-22 | 2020-03-27 | 武汉理工大学 | Method and system for identifying and quantitatively analyzing degradation mechanism of lithium ion battery |
| CN112327191A (en) * | 2020-10-21 | 2021-02-05 | 北京航空航天大学 | Battery diving probability evaluation method based on geometric feature fusion decision |
| CN114114049A (en) * | 2021-09-30 | 2022-03-01 | 北京交通大学 | Lithium ion battery life prediction method based on sample migration |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115856682A (en) | 2023-03-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110161425B (en) | Method for predicting remaining service life based on lithium battery degradation stage division | |
| WO2018059074A1 (en) | Detection method and device for micro short circuit of battery | |
| Sun et al. | Aging estimation method for lead-acid battery | |
| CN115291116B (en) | Energy storage battery health state prediction method and device and intelligent terminal | |
| CN111766462A (en) | Non-invasive load identification method based on V-I track | |
| CN113030758B (en) | Aging early warning method and system based on lithium ion battery capacity water jump point, automobile and computer storage medium | |
| CN113459894A (en) | Electric vehicle battery safety early warning method and system | |
| Kong et al. | Remaining useful life prediction for degrading systems with random shocks considering measurement uncertainty | |
| CN113791351B (en) | Lithium battery life prediction method based on transfer learning and difference probability distribution | |
| CN115856682B (en) | Lithium battery capacity jump point personalized early warning method based on critical point transition | |
| CN111308377A (en) | Battery health state detection method and system based on temperature voltage differentiation | |
| CN112530049B (en) | Battery state monitoring method and device, electronic equipment and storage medium | |
| CN116992311B (en) | Energy storage power supply state analysis method based on machine learning | |
| CN110967585A (en) | Malignant load identification method and device | |
| CN116743180B (en) | Intelligent storage method for energy storage power supply data | |
| CN112600901A (en) | Internet of things equipment state detection method, computer equipment and storage medium | |
| CN116879763A (en) | Battery fault early warning method based on Kalman filtering algorithm | |
| CN116298984A (en) | Lithium ion battery capacity jump point and battery attenuation degree identification method | |
| CN115469226A (en) | Real-time safety early warning method for electric vehicle power battery based on operation big data | |
| CN114879054A (en) | Battery safety monitoring method and device, electronic equipment and storage medium | |
| CN116990697A (en) | Method for detecting abnormal single body in lithium battery pack based on probability distribution | |
| CN115128473A (en) | Lithium analysis monitoring method and device for lithium battery | |
| KR102573964B1 (en) | Apparatus and method for estimating battery soh | |
| CN115018366B (en) | Energy storage system working state monitoring method and device, storage medium and electronic equipment | |
| CN117150325B (en) | Processing method, device, equipment and medium for abnormal residual error data |
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 |