CN115494418A - Lithium battery single body abnormity detection method and system based on time series decomposition algorithm - Google Patents
Lithium battery single body abnormity detection method and system based on time series decomposition algorithm Download PDFInfo
- Publication number
- CN115494418A CN115494418A CN202211462784.0A CN202211462784A CN115494418A CN 115494418 A CN115494418 A CN 115494418A CN 202211462784 A CN202211462784 A CN 202211462784A CN 115494418 A CN115494418 A CN 115494418A
- Authority
- CN
- China
- Prior art keywords
- periodic
- time
- trend
- decomposition algorithm
- lithium battery
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000354 decomposition reaction Methods 0.000 title claims abstract description 39
- 238000001514 detection method Methods 0.000 title claims abstract description 36
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 title claims abstract description 31
- 229910052744 lithium Inorganic materials 0.000 title claims abstract description 31
- 239000000178 monomer Substances 0.000 claims abstract description 15
- 230000002159 abnormal effect Effects 0.000 claims abstract description 5
- 230000000737 periodic effect Effects 0.000 claims description 50
- 239000013598 vector Substances 0.000 claims description 25
- 238000000034 method Methods 0.000 claims description 17
- 230000005856 abnormality Effects 0.000 claims description 15
- 238000009499 grossing Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000000746 purification Methods 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 5
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 238000003745 diagnosis Methods 0.000 description 6
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- FFBHFFJDDLITSX-UHFFFAOYSA-N benzyl N-[2-hydroxy-4-(3-oxomorpholin-4-yl)phenyl]carbamate Chemical compound OC1=C(NC(=O)OCC2=CC=CC=C2)C=CC(=C1)N1CCOCC1=O FFBHFFJDDLITSX-UHFFFAOYSA-N 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 229910001416 lithium ion Inorganic materials 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
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002269 spontaneous effect Effects 0.000 description 1
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]
- G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/378—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC] specially adapted for the type of battery or accumulator
-
- 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]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
- G01R31/3835—Arrangements for monitoring battery or accumulator variables, e.g. SoC involving only voltage measurements
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
Abstract
The invention relates to a lithium battery single body abnormity detection method and a system based on a time sequence decomposition algorithm. And then extracting the trend term component, calculating the cosine similarity of the trend term component of the adjacent battery monomer, and comparing the cosine similarity with a set threshold value, so that the lithium battery fault can be detected in real time, and the abnormal single battery can be rapidly and accurately identified. The invention has the beneficial effects that: (1) Based on a time series decomposition algorithm, the trend term component of each single battery voltage is obtained, and the interference of noise and residual terms can be effectively eliminated; (2) The cosine similarity algorithm is adopted, online real-time battery fault detection can be achieved, the calculation speed is high, and the accuracy is high.
Description
Technical Field
The invention belongs to the field of fault detection of a battery system, and particularly relates to a lithium battery monomer abnormity detection method and system based on a time series decomposition algorithm.
Background
In the use process of a new energy automobile, automobile spontaneous combustion phenomena often occur, which are generally caused by short-circuit faults of lithium ion batteries, so that fault diagnosis of the new energy automobile batteries plays an important role in improving safety of the new energy automobile batteries. At present, methods for fault diagnosis mainly include a model-based detection method, a data-driven detection method and a signal-based detection method, but these methods have respective defects and limitations, and therefore, a new battery online fault diagnosis algorithm needs to be developed, calculation speed and accuracy are improved, and online real-time battery fault abnormality diagnosis is realized.
The current methods for battery fault diagnosis are mainly model-based detection methods, data-driven detection methods, and signal-based detection methods. Most of the detection methods based on the models are very complex in model and calculation, and are inconvenient for real-time online monitoring; the false alarm rate of the detection method based on data driving is high; the signal-based detection method has complex equipment and difficult measurement.
Disclosure of Invention
The technical problem of the invention is mainly solved by the following technical scheme:
a lithium battery single body abnormity detection method based on a time series decomposition algorithm,
acquiring battery voltage data acquired by a sensor in real time and preprocessing the battery voltage data;
decomposing the preprocessed battery voltage data by using a time sequence decomposition algorithm, and extracting a trend term component of the battery voltage;
and calculating the cosine similarity of the trend item components of the adjacent single batteries, comparing the cosine similarity with a set threshold value, and judging whether the lithium battery fails according to the comparison result.
In the lithium battery cell abnormality detection method based on the time series decomposition algorithm, battery voltage data acquired by a sensor in real time is acquired, and discharge voltage data is selected by using a time window, wherein the length of the time window is set to be an even number.
In the lithium battery cell abnormality detection method based on the time series decomposition algorithm, the time series decomposition algorithm is adopted to decompose the voltage data and the time
Voltage data of
Decomposed into trend term components
Periodic term component
And remainder component
：
A positive integer.
In the lithium battery cell abnormality detection method based on the time series decomposition algorithm, the trend term component
Periodic term component
And remainder component
Specific acquisition ofThe process comprises the following steps:
give initial value order
；
The time series is subtracted by the trend term component of the previous round of results, i.e.
Removing the trend term component to obtain a residual signal and a periodic signal;
and after the periodic subsequence smoothing and low-flux filtering processing is carried out on the rest signals in sequence, the periodic subsequence periodic signals are purified after the trend of the smooth periodic subsequence is removed, and finally the periodic signals are removed, so that the final trend item component result and the periodic item component result are obtained.
In the lithium battery cell abnormality detection method based on the time series decomposition algorithm, when periodic subsequence smoothing is performed, sample points at the same position in each period, namely the same position after periodic translation, are combined into a group of sample points
A set of subsequences consisting of subsequences, the number of samples in a period being
(ii) a Each subsequence is subjected to local weighted regression Loess process, and the sequences are respectively extended by 1 time point before and after the local weighted regression Loess process, and are combined to obtain the length of
Time series of
。
In the lithium battery single body abnormity detection method based on the time series decomposition algorithm, when the low-throughput filtering of the periodic subsequence is carried out, the aperiodic signal in the periodic subsequence is extracted; to pair
Are carried out for 3 times respectively in lengths of
，
3, performing a Loess process 1 time to obtain a length of
Time series of
And removing the periodic difference. In the lithium battery monomer abnormity detection method based on the time series decomposition algorithm, the trend of removing the smooth periodic subsequence is removed, and periodic subsequence periodic signals are purified, namely
The trend of (2) is removed:
removing the periodic signal from the periodic signal obtained after purification, namely:
in the above lithium battery cell abnormality detection method based on the time series decomposition algorithm, trend smoothing is performed: performing Loess process on the sequence after the removal period to obtain
Judging whether convergence is needed, and if not, continuing to perform the next iteration; if the iteration converges, outputting the final trend term component result and the periodic term component result of the current iteration:
in the lithium battery monomer abnormality detection method based on the time series decomposition algorithm, the cosine similarity of the trend item components of the adjacent battery monomers is calculated, two attribute vectors A and B are given, and the similarity of the rest chords
Given by the dot product and the vector length:
wherein
Are subscripts to the components of the vector,
，
is a positive integer representing the total number of components of the vector;
regarding two voltage values of each single battery at adjacent moments as a vector, wherein each single battery is provided with two adjacent single batteries, the first single battery and the last single battery are considered to be adjacent to each other, and calculating the vector formed by the voltage values of each single battery at two continuous moments and the adjacent single batteries to obtain two cosine similarity values;
when the cosine similarity of the trend item component of a certain battery monomer and the adjacent monomer is smaller than a set threshold T, the monomer is considered to have a fault at the moment of the vector, and an abnormal warning is sent out; if the vector values are both greater than or equal to the threshold value T and less than or equal to 1, the single body is normal at the moment of the vector.
A lithium battery single body abnormity detection system based on a time series decomposition algorithm comprises
A first module: acquiring battery voltage data acquired by a sensor in real time and preprocessing the battery voltage data;
a second module: decomposing the preprocessed battery voltage data by using a time sequence decomposition algorithm, and extracting a trend term component of the battery voltage;
a third module: and calculating the cosine similarity of the trend item components of the adjacent single batteries, comparing the cosine similarity with a set threshold value, and judging whether the lithium battery fails according to the comparison result.
Therefore, the invention has the following advantages: (1) The voltage of each single battery is decomposed by adopting a time series decomposition algorithm, and data are effectively processed; (2) The cosine similarity of the voltage trend quantity of the adjacent single batteries is calculated, online real-time battery fault diagnosis can be realized, the calculation speed is high, and the accuracy is high.
Drawings
FIG. 1 is a flow chart of a method of the present invention.
Detailed Description
The technical scheme of the invention is further specifically described by the following embodiments and the accompanying drawings.
Example (b):
the implementation steps of the technical scheme are as shown in figure 1, firstly real vehicle voltage data acquired by a sensor in real time is obtained, then discharge voltage data is selected in a time window, the voltage data is decomposed by a time series decomposition algorithm, and trend item components in the decomposition result are extracted
And calculating the cosine similarity of the trend term components of the adjacent single batteries, comparing the calculated result with a set threshold value, and finally judging whether each single battery is abnormal or not according to the comparison result.
The technical scheme comprises the following specific implementation steps:
(a) The battery voltage data acquired by the sensor in real time is obtained, and the discharge voltage data is selected by utilizing a time window (the length of the time window is set to be an even number, so that the cosine similarity is conveniently calculated subsequently), and the data is conveniently decomposed and processed subsequently.
(b) Decomposing the voltage data by adopting a time-series decomposition algorithm STL (Serial-to-dense depletion on Loess), and decomposing the voltage data at a certain moment
Decomposed into a Trend term Component (tend Component), a period term Component (sensor Component) and a Remainder Component (remaining Component):
STL is divided into inner loops (inner loops), which primarily perform trend fitting and periodic component calculations, and outer loops (outer loops), which are primarily used to adjust robustness weights, i.e., remove outliers. The flow details of the time series decomposition algorithm are as follows:
1) Initialization:
the inner loop starts from the trend item component and is firstly assigned with an initial value
After initialization is finished, internal circulation is started;
2) Removing the trend term component:
subtracting the trend component of the previous round result from the total semaphore of the round, namely
；
3) Removing the periodic signal:
after the trend term component is removed, the remaining signal mainly consists of two parts, namely a residual signal and a periodic signal, and then the periodic signal is extracted;
3.1 ) periodic subsequence smoothing
Grouping the sample points at the same position in each period (the same position after period translation) into a subsequence set (subsequences), wherein the number of the subsequences is equal to that of the subsequences
One (the number of samples in one period is
). Each subsequence is subjected to local Weighted regression (Loess) process, the front and the back of each subsequence are extended by 1 time point, and the length is obtained by combining
Time series of
；
3.2 Low-Pass Filtering (Low-Pass Filtering) of the periodic sub-sequence, extracting the non-periodic signal in the periodic sub-sequence. To pair
Are carried out for 3 times respectively as long as
，
3, 3 sliding average, 1 Loess process is carried out to obtain the length of
Time series of
Removing the periodic difference; 3.3 Removing the trend of the smooth periodic subsequence, and purifying the periodic subsequence periodic signal, i.e.
The trend of (c) is removed:
obtaining periodic signals after purification;
3.4 Remove periodic signals, i.e.:
4) Trend smoothing — extracting the trend signal needed in the next iteration:
performing Loess process on the sequence after the removal period to obtain
Judging whether convergence is needed, and if not, continuing to perform the next iteration; if the iteration converges, outputting the final trend term component result and the periodic term component result of the current iteration:
(c) Extracting trend term component in decomposition result
。
(d) And calculating the cosine similarity of the trend term components of the adjacent battery cells. Cosine similarity, also called cosine similarity, is to evaluate the similarity between two vectors by calculating the cosine value of the angle between them. Given two attribute vectors A and B, the remaining chord similarities
Given by the dot product and the vector length:
(e) Setting a threshold value T, and when the cosine similarity of the trend item components of a certain battery monomer and the adjacent monomer is smaller than T, determining that the monomer has a fault at the moment of the vector and sending an abnormal warning; if the vector values are both greater than or equal to the threshold value T and less than or equal to 1, the single body is normal at the moment of the vector. The specific setting of the threshold T depends on the actual need.
The invention also provides a lithium battery monomer abnormity detection system based on the time series decomposition algorithm, which comprises
A first module: acquiring battery voltage data acquired by a sensor in real time and preprocessing the battery voltage data;
a second module: decomposing the preprocessed battery voltage data by using a time sequence decomposition algorithm, and extracting a trend term component of the battery voltage;
a third module: and calculating the cosine similarity of the trend item components of the adjacent single batteries, comparing the cosine similarity with a set threshold value, and judging whether the lithium battery fails according to the comparison result.
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (10)
1. A lithium battery single body abnormity detection method based on a time series decomposition algorithm is characterized in that,
acquiring battery voltage data acquired by a sensor in real time and preprocessing the battery voltage data;
decomposing the preprocessed battery voltage data by using a time sequence decomposition algorithm, and extracting a trend term component of the battery voltage;
and calculating the cosine similarity of the trend item components of the adjacent single batteries, comparing the cosine similarity with a set threshold value, and judging whether the lithium battery fails according to the comparison result.
2. The lithium battery cell abnormality detection method based on the time-series decomposition algorithm as claimed in claim 1, wherein battery voltage data acquired by the sensor in real time is obtained, and discharge voltage data is selected using a time window, wherein the length of the time window is set to an even number.
3. The lithium battery cell abnormality detection method based on the time-series decomposition algorithm as claimed in claim 1, wherein the time-series decomposition algorithm is used to decompose the voltage data to determine the time
Voltage data of
Decomposed into trend term components
Periodic term component
And remainder component
：
A positive integer.
4. The lithium battery cell abnormality detection method based on time series decomposition algorithm as claimed in claim 1, wherein the trend term component
Periodic term component
And remainder component
The specific acquisition process comprises:
give initial value order
；
The time series is subtracted by the trend term component of the previous round of results, i.e.
Removing the trend item component to obtain a residual signal with residual signals and periodic signals;
and after periodic subsequence smoothing and low-throughput filtering are sequentially carried out on the rest signals, the periodic subsequence periodic signals are purified after the trend of the smooth periodic subsequence is removed, and finally the periodic signals are removed, so that the final trend item component result and the periodic item component result are obtained.
5. The lithium battery cell abnormality detection method based on the time-series decomposition algorithm as claimed in claim 1, wherein a periodic cycle is performedWhen the sub-sequence is smoothed, the sample points at the same position in each period, namely the same position after period translation, are combined into a group
A set of subsequences consisting of subsequences, the number of samples in a period being
(ii) a Each subsequence is subjected to local weighted regression Loess process, and the sequences are respectively extended by 1 time point before and after the local weighted regression Loess process, and are combined to obtain the length of
Time series of
。
6. The lithium battery cell abnormality detection method based on the time series decomposition algorithm according to claim 1, characterized in that when low-throughput filtering of the periodic subsequence is performed, non-periodic signals in the periodic subsequence are extracted; to pair
Are carried out for 3 times respectively in lengths of
，
3, 3 sliding average, 1 Loess process is carried out to obtain the length of
Time series of
Removal of periodicityA difference.
7. The lithium battery cell abnormality detection method based on the time series decomposition algorithm as claimed in claim 1, wherein a trend of removing a smooth periodic subsequence is performed, and periodic subsequence periodic signals are purified, that is
The trend of (c) is removed:
removing the periodic signal from the periodic signal obtained after purification, namely:
8. the lithium battery cell abnormality detection method based on the time series decomposition algorithm according to claim 1, characterized by performing trend smoothing: performing Loess process on the sequence after the removal period to obtain
Judging whether convergence is needed, and if not, continuing to perform the next iteration; if the iteration converges, outputting the final trend term component result and the periodic term component result of the current iteration:
9. the lithium battery cell abnormality detection method based on the time-series decomposition algorithm as claimed in claim 1, wherein cosine similarity of trend term components of adjacent battery cells is calculated, and two attribute directions are givenQuantity A and B, remaining chord similarity
Given by the dot product and the vector length:
wherein
Are subscripts to the components of the vector,
，
is a positive integer representing the total number of components of the vector;
regarding two voltage values of each single battery at adjacent moments as a vector, wherein each single battery is provided with two adjacent single batteries, the first single battery and the last single battery are considered to be adjacent to each other, and calculating the vector formed by the voltage values of each single battery at two continuous moments and the adjacent single batteries to obtain two cosine similarity values;
when the cosine similarity of the trend item components of a certain battery monomer and the adjacent monomer is smaller than a set threshold value T, the monomer is considered to have a fault at the moment of the vector, and an abnormal warning is sent; if the vector values are both greater than or equal to the threshold value T and less than or equal to 1, the single body is normal at the moment of the vector.
10. A lithium battery single body abnormity detection system based on a time series decomposition algorithm is characterized by comprising
A first module: acquiring battery voltage data acquired by a sensor in real time and preprocessing the battery voltage data;
a second module: decomposing the preprocessed battery voltage data by using a time sequence decomposition algorithm, and extracting a trend term component of the battery voltage;
a third module: and calculating the cosine similarity of the trend item components of the adjacent single batteries, comparing the cosine similarity with a set threshold value, and judging whether the lithium battery fails according to the comparison result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211462784.0A CN115494418A (en) | 2022-11-22 | 2022-11-22 | Lithium battery single body abnormity detection method and system based on time series decomposition algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211462784.0A CN115494418A (en) | 2022-11-22 | 2022-11-22 | Lithium battery single body abnormity detection method and system based on time series decomposition algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115494418A true CN115494418A (en) | 2022-12-20 |
Family
ID=85115445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211462784.0A Pending CN115494418A (en) | 2022-11-22 | 2022-11-22 | Lithium battery single body abnormity detection method and system based on time series decomposition algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115494418A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117368765A (en) * | 2023-10-07 | 2024-01-09 | 福建时代星云科技有限公司 | Method and terminal for detecting abnormal battery capacity retention rate of electric automobile |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110824376A (en) * | 2019-11-12 | 2020-02-21 | 东软睿驰汽车技术（沈阳）有限公司 | Battery pack abnormity detection method and device, storage medium and electronic equipment |
| CN111428908A (en) * | 2020-02-21 | 2020-07-17 | 上海海洋大学 | Sea surface temperature prediction algorithm based on ST L-NN model |
| CN112798963A (en) * | 2021-04-14 | 2021-05-14 | 杭州宇谷科技有限公司 | Method, apparatus and medium for detecting battery charging characteristic abnormality based on time series |
| CN113406525A (en) * | 2021-06-15 | 2021-09-17 | 安庆师范大学 | Lithium battery pack residual life prediction method based on optimized variational modal decomposition |
| CN113552496A (en) * | 2021-06-29 | 2021-10-26 | 哈尔滨理工大学 | Voltage cosine similarity-based diagnosis method for short circuit fault in battery series module |
| CN114114039A (en) * | 2021-12-06 | 2022-03-01 | 湖北亿纬动力有限公司 | Method and device for evaluating consistency of single battery cells of battery system |
-
2022
- 2022-11-22 CN CN202211462784.0A patent/CN115494418A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110824376A (en) * | 2019-11-12 | 2020-02-21 | 东软睿驰汽车技术（沈阳）有限公司 | Battery pack abnormity detection method and device, storage medium and electronic equipment |
| CN111428908A (en) * | 2020-02-21 | 2020-07-17 | 上海海洋大学 | Sea surface temperature prediction algorithm based on ST L-NN model |
| CN112798963A (en) * | 2021-04-14 | 2021-05-14 | 杭州宇谷科技有限公司 | Method, apparatus and medium for detecting battery charging characteristic abnormality based on time series |
| CN113406525A (en) * | 2021-06-15 | 2021-09-17 | 安庆师范大学 | Lithium battery pack residual life prediction method based on optimized variational modal decomposition |
| CN113552496A (en) * | 2021-06-29 | 2021-10-26 | 哈尔滨理工大学 | Voltage cosine similarity-based diagnosis method for short circuit fault in battery series module |
| CN114114039A (en) * | 2021-12-06 | 2022-03-01 | 湖北亿纬动力有限公司 | Method and device for evaluating consistency of single battery cells of battery system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117368765A (en) * | 2023-10-07 | 2024-01-09 | 福建时代星云科技有限公司 | Method and terminal for detecting abnormal battery capacity retention rate of electric automobile |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109948647B (en) | Electrocardiogram classification method and system based on depth residual error network | |
| CN111241744B (en) | Low-pressure casting machine time sequence data abnormity detection method based on bidirectional LSTM | |
| CN105259895B (en) | A kind of detection of industrial process small fault and separation method and its monitoring system | |
| CN113569338B (en) | Gas compressor rotating stall early warning method based on time expansion convolutional network | |
| CN109783903B (en) | Industrial water pipeline fault diagnosis method and system based on time sequence | |
| CN116861354A (en) | Abnormality identification and mode distinguishing method and system for monitoring data of power transformer | |
| CN108804740B (en) | Long-distance pipeline pressure monitoring method based on integrated improved ICA-KRR algorithm | |
| CN113177537B (en) | Fault diagnosis method and system for rotary mechanical equipment | |
| CN112414694B (en) | Equipment multistage abnormal state identification method and device based on multivariate state estimation technology | |
| CN113255835A (en) | Hydropower station pump equipment anomaly detection method | |
| CN111426905B (en) | Power distribution network common bus transformation relation abnormity diagnosis method, device and system | |
| CN115494418A (en) | Lithium battery single body abnormity detection method and system based on time series decomposition algorithm | |
| CN113671380B (en) | Power battery system multi-fault diagnosis method based on deep learning | |
| Niu et al. | Remaining useful life prediction of machining tools by 1D-CNN LSTM network | |
| CN114266197A (en) | Method for diagnosing equipment fault of hydropower station | |
| CN110119579B (en) | OICA-based complex industrial process fault monitoring method | |
| CN113743541B (en) | Method for predicting residual life of marine power system bearing based on degradation mode | |
| CN113947597B (en) | Industrial defect detection method, device and medium based on shielding reconstruction | |
| CN110308713A (en) | A kind of industrial process failure identification variables method based on k neighbour reconstruct | |
| CN117061318A (en) | Fault diagnosis method, device, equipment, medium and product | |
| CN115600116B (en) | Dynamic detection method, system, storage medium and terminal for time sequence abnormality | |
| CN116712099A (en) | Fetal heart state detection method based on multi-mode data, electronic equipment and storage medium | |
| CN113361579A (en) | Underwater target detection and identification method, system, equipment and readable storage medium | |
| CN109946096B (en) | High-speed train air pipe fault diagnosis method based on model space | |
| CN113359679A (en) | Industrial process fault diagnosis method based on reconstructed amplitude trend characteristics |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20221220 |