CN112098876B - Abnormality detection method for single battery in storage battery - Google Patents
Abnormality detection method for single battery in storage battery Download PDFInfo
- Publication number
- CN112098876B CN112098876B CN202010878711.4A CN202010878711A CN112098876B CN 112098876 B CN112098876 B CN 112098876B CN 202010878711 A CN202010878711 A CN 202010878711A CN 112098876 B CN112098876 B CN 112098876B
- Authority
- CN
- China
- Prior art keywords
- voltage curve
- battery
- abnormal
- single battery
- historical
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 31
- 230000005856 abnormality Effects 0.000 title claims abstract description 25
- 230000002159 abnormal effect Effects 0.000 claims abstract description 51
- 238000012360 testing method Methods 0.000 claims abstract description 37
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000007599 discharging Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 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]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
-
- 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]
- G01R31/389—Measuring internal impedance, internal conductance or related variables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery
-
- 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
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention provides a method for detecting abnormality of a single battery in a storage battery, which is characterized by comprising the following steps: (1) Acquiring a historical voltage curve of each single battery in a historical checkup capacity test; (2) Marking each historical voltage curve as a normal voltage curve or an abnormal voltage curve according to experience; (3) Training a detection model according to the normal voltage curve and the abnormal voltage curve, and setting a threshold value; (4) And acquiring a real-time voltage curve of the single battery in the current check capacity test, predicting the real-time voltage curve according to the detection model to obtain an abnormality index of the single battery, and judging the single battery to be an abnormal battery if the abnormality index exceeds the threshold value, otherwise, judging the single battery to be a normal battery. The method has high accuracy and can effectively avoid the problem of misjudgment of the battery because the battery is in a stable state during floating charge.
Description
Technical Field
The invention relates to the technical field of power supply detection, in particular to an abnormality detection method of a single battery in a storage battery.
Background
The UPS is very important as a power supply guarantee after power failure of a machine room. As the service life increases, the battery in the UPS is not aged, and a verification capacity test is periodically performed to obtain the state of the battery. The total voltage, total current, temperature and voltage values of the individual cells of the battery are recorded at regular intervals (e.g., 1 minute) during the test. At present, a tester generally obtains a data curve through observation and test after the test is completed, calculates the capacity of the storage battery according to experience, and judges whether each single battery is damaged. But this approach has major drawbacks: on one hand, testers need to have relevant working experience to finish the check capacity test; on the other hand, there is no fixed standard how to judge whether a certain single battery is damaged, different testers may make different judgments, and misjudgments may occur, which may cause loss to enterprises.
Based on this, china patent with the application number 2019110333475 discloses a battery health assessment method, which utilizes data of a battery during floating charge to establish an isolated forest model for battery health assessment, and the operation premise is that the battery is in a floating charge state, and then the isolated forest model is constructed through the voltage, the internal resistance and the working temperature of the battery to assess the health state of the battery. The battery is in a machine room, the working environment is stable, the battery is in a relatively stable state in a floating state, the floating voltage, the internal resistance and the working temperature of the battery change slightly, and if the detected value of a certain battery changes obviously, the abnormal condition of the battery can be easily captured by only monitoring whether the value of the battery deviates from the daily fluctuation range. Meanwhile, the battery is in a stable state in a floating state, and even if the battery is abnormal, the floating voltage, the internal resistance and the working temperature of the battery are not changed, so that an isolated forest model established based on the floating voltage, the internal resistance and the working temperature in the floating state is difficult to distinguish.
Disclosure of Invention
In order to solve the technical problems, the invention provides an abnormality detection method for a single battery in a storage battery, which has high accuracy and can effectively avoid the problem of misjudgment of the battery because the battery is in a stable state during floating charge.
Based on the above object, the present invention provides a method for detecting abnormality of a single cell in a storage battery, the method comprising the steps of:
(1) Acquiring a historical voltage curve of each single battery in a historical checkup capacity test;
(2) Marking each historical voltage curve as a normal voltage curve or an abnormal voltage curve according to experience;
(3) Training a detection model according to the normal voltage curve and the abnormal voltage curve, and setting a threshold value;
(4) And acquiring a real-time voltage curve of the single battery in the current check capacity test, predicting the real-time voltage curve according to the detection model to obtain an abnormality index of the single battery, and judging the single battery to be an abnormal battery if the abnormality index exceeds the threshold value, otherwise, judging the single battery to be a normal battery.
Preferably, in the step (2), the specific method for marking each historical voltage curve as a marked normal voltage curve or an abnormal voltage curve according to experience is as follows: each historical voltage curve is marked by two workers respectively, and if the judgment results are consistent, the historical voltage curves are used as final marking results; if the judging results are inconsistent, the third person marks, and finally, a plurality of results are taken as final marking results.
Preferably, in the step (3), a detection model is obtained by training with an isolated forest algorithm.
Preferably, in step (3), the method for setting the threshold value includes: and according to the actual service demand, comprehensively considering the accuracy and the recall rate to obtain a proper threshold.
Preferably, the method further comprises step (5): and manually marking the voltage curve of the battery judged to be abnormal as an abnormal voltage curve, and continuing training of the detection model by taking the abnormal voltage curve as training data to update the detection model.
Preferably, the method further comprises step (6): and storing the data acquired in the check capacity, and archiving the data based on the brand, the model, the number of the single batteries and the discharge rate of the batteries so as to respectively establish a proper test model for different batteries at a later stage.
Compared with the prior art, the invention has the beneficial effects that:
after the single voltage data acquired in the check capacity test are processed, the abnormal degree of the single battery is judged through an isolated forest algorithm; the single voltage data collected in the check capacity test is used instead of the battery data during floating charge, the accuracy is high, and misjudgment of the battery due to the fact that the battery is in a stable state during floating charge and the key parameters are not changed greatly is avoided.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application.
FIG. 1 is a flow chart of a method according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a discharging curve of a single battery according to an embodiment of the present invention;
FIG. 3 is a graph showing voltage data during discharge of each cell in accordance with an embodiment of the present invention;
FIG. 4 is a schematic diagram showing the variation of the precision and recall of the test model in an embodiment of the present invention.
Detailed Description
The invention will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present application. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
The embodiment provides a method for detecting abnormality of a single battery in a storage battery, as shown in fig. 1, the method includes the following steps:
(1) Acquiring a historical voltage curve of each single battery in a historical checkup capacity test;
(2) Marking each historical voltage curve as a normal voltage curve or an abnormal voltage curve according to experience;
(3) Training a detection model according to the normal voltage curve and the abnormal voltage curve, and setting a threshold value;
(4) And acquiring a real-time voltage curve of the single battery in the current check capacity test, predicting the real-time voltage curve according to the detection model to obtain an abnormality index of the single battery, and judging the single battery to be an abnormal battery if the abnormality index exceeds the threshold value, otherwise, judging the single battery to be a normal battery.
As a preferred embodiment, in the step (2), the specific method for marking each historical voltage curve as a marked normal voltage curve or an abnormal voltage curve according to experience is as follows: each historical voltage curve is marked by two workers respectively, and if the judgment results are consistent, the historical voltage curves are used as final marking results; if the judging results are inconsistent, the third person marks, and finally, a plurality of results are taken as final marking results. Specifically, a first-line staff member who performs maintenance and test of the storage battery for a long time is selected, and the voltage curve data of each single battery is marked, wherein the marked content is whether a certain voltage curve is normal or not. In the embodiment of the invention, each data is marked by two workers respectively, if the judgment is consistent, the data is used as a final marking result, if the judgment is inconsistent, the data is marked by a third person, and the final result takes the result of the same two parts in the three judgments as the final marking result. Thus, the situation of human misjudgment can be avoided.
As a preferred embodiment, in the step (3), training is performed by using an isolated forest algorithm to obtain a detection model; the following describes the method in detail by taking primary cell detection as an example:
Fig. 2 is a graph showing a discharge voltage curve of a certain unit cell discharged for two hours. As can be seen from fig. 2, when a normal single battery is discharged, the voltage value of the normal single battery is characterized by firstly rapidly decreasing, then slightly rising, then slowly decreasing, and abnormality detection can be performed by screening the change trend of the voltage by an algorithm. The data acquisition mode is consistent with the traditional check capacity test, and no special modification is needed. In this embodiment, the voltage of a single battery of a certain brand when full is about 2.2V, the single battery is discharged at a rate of two hours, the voltage of the single battery is collected every 1 minute, and the data of partial collection is shown in fig. 3.
Specifically, in this embodiment, the discharge is performed at a rate of two hours, and the voltage acquisition frequency is 1 minute and 1 time, and the obtained cell voltages have 121 data points (including the initial voltage and the end voltage). The isolated forest algorithm was trained with each data point as a feature, i.e., the model had 121 features input.
It should be noted that, the test model calculated by the isolated forest algorithm is composed of a plurality of isolated trees, for each isolated tree, a certain number of samples (denoted as ψ < N) are extracted from all training data (total number N) without substitution, then one of a plurality of characteristics of the data (such as voltage values of the battery at 121 moments in the checkup capacity test) is randomly selected, then a segmentation point is randomly selected from the range of the characteristics, the samples are segmented, if the depth of the fruit tree reaches the maximum set value, or the number of the child nodes is smaller than the set value, the construction of the isolated tree is terminated, otherwise, the next segmentation of the segmented child nodes is continued until the construction of the isolated tree is completed. The construction process of the isolated trees is the training process of the isolated forest model.
After the test model training is completed, M isolated trees are obtained, and the newly acquired sample to be evaluated is marked as x. Classifying each orphan tree using which the depth e of the leaf node that the sample x eventually reaches is recorded, and the number of samples that also fall on the leaf node in the training set (denoted Lsize), the path length h j of the data x on the orphan tree j is calculated using the following formula:
h j =e+C (Lsize) equation (1-1)
The calculation method of C (Lsize) is as follows:
Wherein H (Lsize-1) is a harmonic number, which can be estimated from ln (Lsize-1) +ζ, which is Euler constant, and is 0.5772156649.
According to the above method, it is possible to calculate the path lengths h j (x) of the sample x to be evaluated on all the isolated trees, respectively. Then, based on this h j (x) and the values C (ψ) of the samples, the anomaly Score (x) of the sample to be evaluated is calculated using the following formula:
Wherein E [ h j (x) ] is the expected value of M h j (x), and j is [1, M ]. The result of this anomaly score is between 0 and 1.
In the embodiment of the invention, when the discharge is performed at a rate of two hours and the voltage acquisition frequency is 1 minute and 1 time, the model training can be performed by using any number of data points before, for example, the model training can be performed by using data of 20 minutes before (21 data points including initial values) or the model training can be performed by using data of 30 minutes before (31 data points including initial values). If the model is obtained by training the data for the previous 20 minutes (21 data points, including the initial value), when the new capacity check experiment is performed for 20 minutes, the model can be used for prediction, and the function of predicting whether the single battery is abnormal or not in the process of performing the capacity check experiment can be achieved.
And (3) inputting the 21 data points currently collected by each single battery into a detection model for prediction, outputting the abnormal score of each single battery by the model, and if the abnormal score of a certain single battery is greater than a preset threshold value, considering that the abnormal single battery exists in the battery pack, sending a signal, stopping the test, and avoiding the risk caused by continuous test. By the above method, a plurality of models can be constructed, even 1 model every 1 minute. The more models that are built, the more burdensome the model training and maintenance. In this embodiment, the basic idea of selecting the number of models is to construct one model every 20 minutes, and then discharge at a rate of 2 hours, so that 6 models can be obtained in total, which are constructed based on the data acquired at 20, 40, 60, 80, 100, and 120 minutes of test.
And then in a newly developed capacity check test, collecting data of each single battery voltage of the storage battery in real time, predicting whether each single battery is abnormal according to a test model, calculating an abnormal score for each single battery by the test model, and if the abnormal score of one single battery exceeds a preset threshold value, judging the single battery as an abnormal battery, otherwise, judging the single battery as a normal battery.
And when the abnormal score obtained by the detection model is larger than a preset threshold value, judging that the battery is an abnormal single battery. By adjusting the threshold value, a certain cell may be judged as an abnormal cell or as a normal cell. In an actual working scene, the accurate rate and the recall rate can be comprehensively considered by comparing the model predicted result with the manually marked result and combining the actual service requirement, and a proper threshold value is found and used as a preset threshold value.
In a preferred embodiment, in the step (3), the method for setting the threshold is as follows: according to the actual service requirement, the accuracy (Precision) and the Recall (Recall) are comprehensively considered to obtain a proper threshold. The variation in accuracy and recall caused by the threshold variation can be seen in FIG. 4; the accuracy is a proportion of the battery predicted to be abnormal by the model, and the actual determination is an abnormal battery. The recall is the proportion of the actual abnormal cells that is correctly predicted by the model as the abnormal cells.
Fig. 4 shows the effect of the model using PR curves (precision versus recall curves), it can be seen that at some threshold, the model can maintain both precision and recall above 0.7. In fig. 4, the abscissa is the recall rate, the ordinate is the precision rate, and when the threshold value is large, only a cell with a high abnormality score is determined as an abnormal cell, and at this time, a possible cell is an abnormal cell, and the abnormality score is not so high, which is determined as a normal cell, so the precision rate is high, and the recall rate is low. Conversely, when the threshold value is small, a battery whose abnormality score is not so high is also determined as an abnormal battery, and at this time, it may itself be a normal battery, so the accuracy rate is low, and the recall rate is high. The threshold can be adjusted according to the actual service requirement to obtain the required accuracy and recall, for example, if the maintenance funds are limited, the threshold can be adjusted to be larger, the larger accuracy and smaller recall can be obtained, the battery with larger abnormal value can be replaced preferentially, if the maintenance funds are abundant, the threshold can be adjusted to be smaller, the smaller accuracy and larger recall can be obtained, and some possible abnormal batteries can be replaced as much as possible to avoid risks caused by the abnormal batteries.
As a preferred embodiment, the method further comprises step (5): and manually marking the voltage curve of the abnormal battery as an abnormal voltage curve, and continuing training of the detection model by taking the abnormal voltage curve as training data, and updating the detection model, so that the detection model is retrained, and the effect of the model is further improved.
As a preferred embodiment, the method further comprises step (6): the data collected in the check capacity is stored and archived based on the brand, model, number of single batteries and discharge rate of the batteries, and a proper isolated forest model can be respectively built for different brands, models, number of single batteries and discharge rate in the later period, so that the check capacity test of the storage battery is not limited to the storage battery data such as fixed battery brands, battery models, number of single batteries in the battery pack and the like, and is also not limited to the fixed discharge rate.
The check capacity test is monitored and controlled by a battery management system, and the voltage of each single battery is monitored at fixed time intervals during the test.
After the single voltage data acquired in the check capacity test are processed, the abnormal degree of the single battery is judged through an isolated forest algorithm; the single voltage data collected in the check capacity test is used instead of the battery data during floating charge, the accuracy is high, and misjudgment of the battery due to the fact that the battery is in a stable state during floating charge and the key parameters are not changed greatly is avoided.
Although embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by those skilled in the art without departing from the spirit and principles of the invention, and any simple modification, equivalent variation and modification of the above embodiments in light of the technical principles of the invention may be made within the scope of the present invention.
Claims (6)
1. The method for detecting the abnormality of the single battery in the storage battery is characterized by comprising the following steps:
(1) Acquiring a historical voltage curve of each single battery in a historical checkup capacity test;
(2) Marking each historical voltage curve as a normal voltage curve or an abnormal voltage curve according to experience;
(3) Training a detection model according to the normal voltage curve and the abnormal voltage curve, and setting a threshold value;
(4) Collecting a real-time voltage curve of a single battery in a current checkup capacity test, predicting the real-time voltage curve according to the detection model to obtain an abnormality index of the single battery, judging the single battery to be an abnormal battery if the abnormality index exceeds the threshold value, otherwise, judging the single battery to be a normal battery;
wherein, the historical voltage curve, the normal voltage curve, the abnormal voltage curve and the real-time voltage curve are all single battery discharging curves, the horizontal axis is discharging time, and the vertical axis is voltage;
the detection model carries out abnormal detection by screening the variation trend that the voltage value of the normal single battery can be rapidly reduced, slightly raised and slowly reduced when the normal single battery is discharged;
Wherein, a test model is built every 20 minutes, and then discharged at a rate of 2 hours, to obtain 6 test models in total, which are models built based on data acquired when the test was performed to 20, 40, 60, 80, 100 and 120 minutes, respectively.
2. The method for detecting abnormality of a single battery cell in a storage battery according to claim 1, wherein in the step (2), the specific method for empirically marking each historical voltage curve as a labeled normal voltage curve or an abnormal voltage curve is as follows: each historical voltage curve is marked by two workers respectively, and if the judgment results are consistent, the historical voltage curves are used as final marking results; if the judging results are inconsistent, the third person marks, and finally, a plurality of results are taken as final marking results.
3. The method for detecting abnormality of a single battery in a storage battery according to claim 1, wherein in the step (3), a detection model is obtained by training with an isolated forest algorithm.
4. The method for detecting abnormality of a single cell in a storage battery according to claim 1, wherein in the step (3), the threshold setting method is as follows: and according to the actual service demand, comprehensively considering the accuracy and the recall rate to obtain a proper threshold.
5. The abnormality detection method for a single cell in a battery according to any one of claims 1 to 4, characterized in that the method further comprises the step (5) of: and manually marking the voltage curve of the battery judged to be abnormal as an abnormal voltage curve, and continuing training of the detection model by taking the abnormal voltage curve as training data to update the detection model.
6. The abnormality detection method for a single cell in a battery according to claim 5, characterized in that the method further comprises the step (6) of: and storing the data acquired in the check capacity, and archiving the data based on the brand, the model, the number of the single batteries and the discharge rate of the batteries so as to respectively establish a proper test model for different batteries at a later stage.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010878711.4A CN112098876B (en) | 2020-08-27 | 2020-08-27 | Abnormality detection method for single battery in storage battery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010878711.4A CN112098876B (en) | 2020-08-27 | 2020-08-27 | Abnormality detection method for single battery in storage battery |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112098876A CN112098876A (en) | 2020-12-18 |
| CN112098876B true CN112098876B (en) | 2024-06-28 |
Family
ID=73758047
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010878711.4A Active CN112098876B (en) | 2020-08-27 | 2020-08-27 | Abnormality detection method for single battery in storage battery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112098876B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112991704A (en) * | 2021-05-19 | 2021-06-18 | 武汉工程大学 | Overvoltage data processing method and device for charging energy storage system and storage medium |
| CN113640683A (en) * | 2021-08-06 | 2021-11-12 | 江苏金帆电源科技有限公司 | Method for identifying abnormal battery |
| CN115575846B (en) * | 2022-12-07 | 2023-04-25 | 北京志翔科技股份有限公司 | Method, device, equipment and medium for detecting health state of battery pack |
| CN116243199A (en) * | 2023-02-02 | 2023-06-09 | 湖北亿纬动力有限公司 | Method and device for detecting abnormal battery cell and computer storage medium |
| WO2024183009A1 (en) * | 2023-03-07 | 2024-09-12 | 宁德时代新能源科技股份有限公司 | Battery detection method and apparatus |
| CN116400126B (en) * | 2023-06-08 | 2023-08-01 | 广东佰林电气设备厂有限公司 | Low-voltage power box with data processing system |
| CN116780914B (en) * | 2023-06-19 | 2024-02-27 | 深圳市安科讯实业有限公司 | Hybrid switch mode power supply conversion method and device |
| CN116736150B (en) * | 2023-08-16 | 2023-11-03 | 杭州高特电子设备股份有限公司 | Battery abnormality detection method, battery system and computer program |
| CN117706387B (en) * | 2023-12-15 | 2024-08-09 | 佛山数港科技有限公司 | Battery health state monitoring method and device, electronic equipment and medium |
| CN117849653B (en) * | 2024-03-08 | 2024-05-07 | 备倍电科技(深圳)有限公司 | Working state monitoring method and system based on power management |
| CN118151039B (en) * | 2024-05-11 | 2024-07-23 | 国网山东省电力公司鄄城县供电公司 | Working state evaluation method and system for substation storage battery pack |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007123007A (en) * | 2005-10-27 | 2007-05-17 | Hitachi Ltd | Method and equipment for diagnosing fuel cell system |
| JP2020025452A (en) * | 2018-07-31 | 2020-02-13 | 東北電力株式会社 | Inspection device of solar cell, inspection system, inspection method and program |
| CN110806546A (en) * | 2019-10-28 | 2020-02-18 | 腾讯科技（深圳）有限公司 | Battery health assessment method and device, storage medium and electronic equipment |
Family Cites Families (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100889244B1 (en) * | 2005-04-20 | 2009-03-17 | 주식회사 엘지화학 | Secondary Battery Module Having Piezo Sensor |
| CN102298116A (en) * | 2010-06-22 | 2011-12-28 | 上海申通轨道交通研究咨询有限公司 | Vehicle-mounted monitoring device for temperature detection and diagnosis alarm of vehicle-mounted storage battery pack |
| JPWO2012053487A1 (en) * | 2010-10-18 | 2014-02-24 | 有限会社オーエイチケー研究所 | Battery charger and battery charging method |
| CN103884987B (en) * | 2012-12-19 | 2017-11-07 | 北京创智信科科技股份有限公司 | The detection method of battery |
| CN103605103B (en) * | 2013-06-26 | 2016-12-28 | 广东电网公司东莞供电局 | Electric energy metrical intelligent fault diagnosis method based on S type curvilinear function |
| CN104597406B (en) * | 2014-12-30 | 2017-11-28 | 深圳市科陆电子科技股份有限公司 | Lithium battery energy storage battery power system capacity declines analysis and processing method and analysis processing device |
| CN105759212B (en) * | 2016-01-27 | 2019-08-30 | 惠州市蓝微新源技术有限公司 | Battery pack failure simulation method and fault detection method |
| CN106845441B (en) * | 2017-02-15 | 2022-02-01 | 广州志正电气有限公司 | Aviation storage battery electric quantity full-charge prediction method based on image recognition |
| US10609631B2 (en) * | 2017-10-27 | 2020-03-31 | LGS Innovations LLC | Rogue base station router detection with configurable threshold algorithms |
| EP3537531B1 (en) * | 2017-11-13 | 2021-08-04 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Method for monitoring safety of adapter, terminal device and battery thereof and monitoring system |
| CN109991550B (en) * | 2017-12-28 | 2022-07-05 | 中国电信股份有限公司 | Storage battery performance detection method, device, system and computer readable storage medium |
| CN108232342B (en) * | 2018-01-03 | 2020-02-14 | 中车株洲电力机车有限公司 | Storage battery management method and system and storage battery management equipment |
| JP7234140B2 (en) * | 2018-01-11 | 2023-03-07 | 株式会社半導体エネルギー研究所 | Secondary battery abnormality detection device, abnormality detection method, program, secondary battery state estimation method, and secondary battery charge state estimation device |
| CN108544925B (en) * | 2018-04-02 | 2019-10-01 | 北京理工大学 | Battery management system |
| CN108445410B (en) * | 2018-04-02 | 2021-02-26 | 国家计算机网络与信息安全管理中心 | Method and device for monitoring running state of storage battery pack |
| CN109031143A (en) * | 2018-07-20 | 2018-12-18 | 天津市气象探测中心 | A kind of field automatic weather station battery abnormality comprehensive judging method |
| CN109375116B (en) * | 2018-08-09 | 2021-12-14 | 上海国际汽车城（集团）有限公司 | Battery system abnormal battery identification method based on self-encoder |
| CN109604192B (en) * | 2018-11-21 | 2020-02-28 | 中国科学院自动化研究所 | Battery sorting method and system based on big data analysis |
| CN110598729B (en) * | 2019-07-24 | 2022-03-29 | 华南理工大学 | Method for classifying defects on surface of lithium battery electrode |
| CN111178456B (en) * | 2020-01-15 | 2022-12-13 | 腾讯科技（深圳）有限公司 | Abnormal index detection method and device, computer equipment and storage medium |
| CN111257755B (en) * | 2020-03-31 | 2022-06-10 | 上海玫克生储能科技有限公司 | Method for preventive detection and diagnosis of battery pack |
-
2020
- 2020-08-27 CN CN202010878711.4A patent/CN112098876B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007123007A (en) * | 2005-10-27 | 2007-05-17 | Hitachi Ltd | Method and equipment for diagnosing fuel cell system |
| JP2020025452A (en) * | 2018-07-31 | 2020-02-13 | 東北電力株式会社 | Inspection device of solar cell, inspection system, inspection method and program |
| CN110806546A (en) * | 2019-10-28 | 2020-02-18 | 腾讯科技（深圳）有限公司 | Battery health assessment method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112098876A (en) | 2020-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112098876B (en) | Abnormality detection method for single battery in storage battery | |
| CN112731159B (en) | Method for pre-judging and positioning battery faults of battery compartment of energy storage power station | |
| CN114114049B (en) | Lithium ion battery life prediction method based on sample migration | |
| CN108254696A (en) | The health state evaluation method and system of battery | |
| CN113933732B (en) | New energy automobile power battery health state analysis method, system and storage medium | |
| CN112485689A (en) | Method for predicting residual cycle life of lithium battery in energy storage system based on Xgboost model | |
| CN109471036B (en) | Battery evaluation and early warning method for sensor network node | |
| CN116401585B (en) | Energy storage battery failure risk assessment method based on big data | |
| CN104569844A (en) | Valve control seal type lead-acid storage battery health condition monitoring method | |
| CN116774057B (en) | Method and device for training battery life prediction model and predicting battery life | |
| CN114720883A (en) | Lithium battery fault identification method based on isolated forest algorithm | |
| CN117289162A (en) | Battery health prediction method and system based on group end convergence method | |
| CN116381545A (en) | Method and device for determining consistency grade of energy storage battery pack | |
| CN115267585A (en) | Improved single particle electrochemical model modeling method based on gradient enhanced decision tree | |
| CN118444186A (en) | Quick accurate detection device of retired power battery health status | |
| CN116613864B (en) | Online nuclear capacity inspection method and device for storage battery | |
| CN117310538A (en) | Energy storage battery electric quantity monitoring system capable of automatically detecting electric quantity residual conversion efficiency | |
| CN117996896A (en) | Full-oil lithium iron phosphate battery charge and discharge monitoring method | |
| CN115331745A (en) | Improved single-particle electrochemical model modeling method based on historical data verification | |
| CN110456191B (en) | Method and system for detecting operation unit of super-large-scale battery energy storage power station | |
| CN114997375A (en) | Insulator surface metal pollution model building system in air type switch cabinet | |
| CN118501720B (en) | Lithium battery abnormality detection system based on big data analysis | |
| CN118693964B (en) | Intelligent control method and system for charging and discharging of energy storage battery pack | |
| CN117117356B (en) | Energy storage battery pack thermal runaway monitoring and tracing method and system | |
| CN116540097A (en) | Online evaluation method and device for degradation degree of battery |
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 |