CN118336877B - Battery charging large model anomaly identification method based on electric power fingerprint - Google Patents
Battery charging large model anomaly identification method based on electric power fingerprint Download PDFInfo
- Publication number
- CN118336877B CN118336877B CN202410757006.7A CN202410757006A CN118336877B CN 118336877 B CN118336877 B CN 118336877B CN 202410757006 A CN202410757006 A CN 202410757006A CN 118336877 B CN118336877 B CN 118336877B
- Authority
- CN
- China
- Prior art keywords
- time
- current
- value
- time period
- real
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000002159 abnormal effect Effects 0.000 claims abstract description 38
- 238000012544 monitoring process Methods 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 10
- 230000005856 abnormality Effects 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 7
- 238000011897 real-time detection Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 3
- 230000003203 everyday effect Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 11
- 230000008859 change Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000007405 data analysis Methods 0.000 abstract description 2
- 230000007774 longterm Effects 0.000 abstract description 2
- 230000007246 mechanism Effects 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Landscapes
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention discloses a battery charging large model anomaly identification method based on electric power fingerprints, relates to the technical field of battery anomaly identification, and solves the problem that the existing technical means often lack an effective historical data comparison mechanism, so that whether anomalies exist in the charging process cannot be accurately judged based on the change trend of current. Through time division and long-term data analysis, the common time period, the micro-abnormal time period and the abnormal time period can be timely identified, so that early warning and intervention are performed in advance before potential risks of the battery occur. In addition, the technology can judge the real-time current according to the current error range interval, so that the accuracy of fault identification is further improved, and the problem of overload or weak current possibly occurring in the battery charging process can be effectively prevented.
Description
Technical Field
The invention relates to the technical field of battery anomaly identification, in particular to a battery charging large model anomaly identification method based on power fingerprints.
Background
In the development of battery charging technology, power fingerprint has been used as an emerging technical means for monitoring and analyzing the charging process of a battery, and recognizing the state and health of the battery through real-time monitoring of power parameters, such as voltage, current, temperature, etc., during the charging process of the battery. The method utilizes the electric fingerprint collector to collect data generated in the charging process, and processes the data by means of a specific algorithm so as to monitor and analyze the charging performance of the battery in real time. Through continuous tracking of the parameters, the charging efficiency, the life expectancy and the potential fault risk of the battery can be effectively predicted, and the battery charging safety is ensured.
However, although the power fingerprinting technology provides an effective battery monitoring means, there are certain limitations in practical applications. Particularly, in the aspect of abnormality identification of main detection data of charging current, the existing method often cannot accurately judge whether abnormality occurs. The reason is that the current data is not only required to be identified in an abnormal manner, but also needs to be compared with the past historical data, but the existing technical means often lack an effective historical data comparison mechanism, so that whether the current data is abnormal or not cannot be accurately judged based on the current change trend. Therefore, there is a need to develop a method for identifying battery charging large model anomalies based on power fingerprint, which can more effectively utilize history and real-time data to perform deep analysis on key parameters such as current, so as to improve the accuracy and timeliness of identifying battery charging anomalies.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a battery charging large model anomaly identification method based on power fingerprint, which solves the problems in the background art.
In order to achieve the above purpose, the invention is realized by the following technical scheme: the battery charging large model anomaly identification method based on the power fingerprint comprises the following steps:
step one: selecting a corresponding electric fingerprint collector to be analyzed, setting a standard current, marking as I s, and collecting real-time current of battery charging in real time, marking as I b; wherein the setting of the standard current is performed by a professional;
step two: then dividing the time period into X time periods, analyzing the X time periods within preset time T, and respectively dividing the X time periods into a common time period, a slight difference time period and an abnormal time period, wherein the preset time T refers to a time period of s days forward from the current time, s is a preset value, and the preset time period is specifically set by professional staff;
Step three: after the common period, the slight different period and the abnormal period are determined, randomly selecting one day from s days as a selected day, and determining an analysis result as a current error range interval by analyzing the deviation values of the common time and the abnormal time of the selected day;
step four: acquiring all common time periods, slight different time periods and abnormal time periods, acquiring real-time currents at different intervals according to the properties of the time periods through an electric fingerprint acquisition device, and determining current real-time detection;
step five: and the measured real-time current is recorded as I r through the electric fingerprint collector, is judged with a current error range interval G, whether the real-time current I s generates an early warning signal or not is determined according to a judging result, and the generated early warning signal is sent to a platform control center.
Preferably, in the second step, the specific manner of dividing into the normal period, the micro-abnormal period and the abnormal period is as follows:
S1: setting an interval t1 time in X time periods to collect real-time current I b;
S2: then, a time period is selected at will, real-time current I b is collected, absolute values of real-time current I b and standard current I s are calculated, namely | I b-I s |, the calculated result is recorded as a difference current value Hi, then all difference current values H i in the time period are obtained, wherein 0<i is less than or equal to n, n is the number of all difference current values collected in the time period, and n is more than or equal to 1;
S3: the average value Hp of n differential stream values Hi is obtained, and then the formula is passed: Obtaining a deviation value Uk of the time period;
S4: then, acquiring a deviation value Uk of the time period for every day in s days, wherein k is equal to or less than 1 and equal to or less than s, and k represents any deviation value of the time period in s days;
s5: then taking the average value of s deviation values Uk, recording as Up, judging Up, and defining the time period as the common period when Up < the preset value P.
Preferably, in step S5, further includes:
When Up is more than or equal to a preset value P, obtaining a deviation value Uk which is more than the average value Up, sorting from large to small, sequentially selecting Uk and Up which are the foremost in sorting, performing phase difference calculation, namely Uk-Up, marking the calculated result as Ug, judging the magnitude of Ug and the preset value M1, automatically generating 1 when Ug is more than or equal to M1, finally counting the number Y1 of 1, and defining the time period as an abnormal time period when Y1 is more than or equal to the preset value Y2;
when Y1< Y2, the period is defined as a differential period.
Preferably, the collecting real-time current I b is collected at an interval t1 in a working state of battery charging, and t1 is a preset value.
Preferably, in the third step, the specific manner of determining the current error range is as follows:
P1: randomly selecting one day from s days as a selected day, acquiring the common time period and the abnormal time period of the selected day, extracting the deviation values Uj of Z common time periods of the selected day, calculating the average value of Z deviation values Uj, and taking the average value as a judgment value Ut; wherein, 1 is less than or equal to j is less than or equal to Z, Z is the total number of the common time period of the selected day;
P2: then selecting an abnormal period with the largest deviation value of the day, recording the deviation value of the abnormal period as Uc, obtaining the average value Hp of the difference stream value H i of the abnormal period, sorting Hi from big to small according to the result of I Hi-Hp I, sequentially deleting H i with the forefront of the sorting, recalculating the deviation value Uc until Uc is less than or equal to the judgment value Ut, obtaining the deleted difference stream value Hi, and obtaining the average value Hi of the difference stream value through a formula Wherein D is an error value, w is the number of deleted differential stream values H i, D is more than or equal to 1 and less than or equal to w, and H i-d is any one of the number of deleted differential stream values H i;
Preferably, after step P2, the method further comprises:
p3: standard current I s is acquired, and a current error range interval G is defined: [ I s-D, I s +D ].
Preferably, in the fourth step, the specific manner of current real-time detection is as follows:
When the detection time period is a common time period, defining to collect real-time current once every time T1;
when the detection time period is a slight difference time period, defining to collect real-time current once every time T2;
When the detection time period is an abnormal time period, defining to collect real-time current once every time T3;
wherein T1> T2> T3.
Preferably, in the fifth step, the specific judging mode is that of an early warning signal, which is that:
when I b-D < I r < I b +D, determining that the real-time current I r is within a reasonable range, and performing no treatment at this time;
when I b +D < I r, determining that the real-time current I r is an overload current, and triggering an overload early warning signal to be sent to a platform control center;
When I r is smaller than I b-D, the real-time current I r is judged to be weak current, and a weak early warning signal is triggered to be sent to a platform control center.
Preferably, the platform control center determines an evaluation value according to the generated early warning signal, inputs the evaluation value into a preset problem model for recognition, outputs a recognition result to a monitoring person, and the monitoring person evaluates the implementation problem of the early warning signal according to the recognition result.
Preferably, the specific mode of determining the evaluation value is as follows:
AS1: when an overload early warning signal is received, acquiring real-time current I s of the overload early warning signal, and obtaining a judgment value FS through FS=alpha× I r-Bvc;
AS2: when a weak early warning signal is received, acquiring real-time current I s of the weak early warning signal, and acquiring a judgment value FD through FD= |beta multiplied by I r-Bvc |;
AS3: inputting the judgment value FS or the judgment value FD into a preset problem model for recognition, obtaining a recognition result, and outputting the recognition result to monitoring staff;
Wherein, alpha is a coefficient factor, bvc is a current median value and is a preset value.
The invention provides a battery charging large model anomaly identification method based on power fingerprints. Compared with the prior art, the method has the following beneficial effects:
(1) The invention collects the current data of battery charging in real time, compares the current data with the set standard current, and realizes the fine monitoring of the battery charging state by calculating the difference value and the deviation value. Through time division and long-term data analysis, the common time period, the micro-abnormal time period and the abnormal time period can be timely identified, so that early warning and intervention are performed in advance before potential risks of the battery occur. In addition, the method can judge the real-time current according to the current error range interval, and further improves the accuracy of fault identification. Through the series of measures, the possible overload or weak current problem in the battery charging process can be effectively prevented, the full monitoring of the battery charging state is realized, the service life of the battery is prolonged, and solid guarantee is provided for the battery charging safety.
(2) According to the invention, through comprehensively utilizing real-time and historical data, intelligent monitoring and abnormality identification of the battery charging process are realized, the requirement of manual intervention is reduced, and the efficiency and response speed of system management are improved. Through the automatically generated early warning signals and the preset problem model, the potential problems can be rapidly identified. The safety and reliability of the battery charging process are improved, and more efficient and accurate data support is provided for operation and maintenance management of a battery charging system.
Drawings
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is a general flow chart of a battery charging large model anomaly identification method based on power fingerprint;
Fig. 2 is a specific flowchart of the battery charging large model anomaly identification method based on the power fingerprint, which is divided into a common period, a slight difference period and an anomaly period.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1-2, the invention provides a battery charging large model anomaly identification method based on power fingerprint, comprising the following steps of;
step one: selecting a corresponding electric fingerprint collector to be analyzed, setting a standard current, marking as I s, and collecting real-time current of battery charging in real time, marking as I b; wherein the setting of the standard current is performed by a professional;
step two: then dividing the time period into X time periods, analyzing the X time periods within preset time T, and respectively dividing the X time periods into a common time period, a slight difference time period and an abnormal time period, wherein the preset time T refers to a time period of s days forward from the current time, s is a preset value, and the preset time period is specifically set by professional staff;
Referring to fig. 2, the specific partitioning is as follows:
S1: setting an interval t1 time in X time periods to collect real-time current I b;
It should be noted that, the collecting real-time current I b is collected at an interval t1 in the working state of battery charging, and the other conditions are not processed, where t1 is a preset value;
S2: then, a time period is selected at will, real-time current I b is collected, absolute values of real-time current I b and standard current I s are calculated, namely | I b-I s |, the calculated result is recorded as a difference current value Hi, then all difference current values H i in the time period are obtained, wherein 0<i is less than or equal to n, n is the number of all difference current values collected in the time period, and n is more than or equal to 1;
S3: the average value Hp of n differential stream values Hi is obtained, and then the formula is passed: Obtaining a deviation value Uk of the time period;
s4: then, acquiring a deviation value Uk of each day in the time period, wherein in the implementation, s is 30, and the data of the day of acquiring the data are not counted, wherein 1 is less than or equal to k is less than or equal to s, and k represents any deviation value of the time period in s days;
S5: taking the average value of s deviation values Uk, recording as Up, judging Up, and defining the time period as a common time period when Up is smaller than a preset value P;
When Up is more than or equal to a preset value P, obtaining a deviation value Uk which is more than the average value Up, sorting from large to small, sequentially selecting Uk and Up which are the foremost in sorting, performing phase difference calculation, namely Uk-Up, marking the calculated result as Ug, judging the magnitude of Ug and the preset value M1, automatically generating 1 when Ug is more than or equal to M1, finally counting the number Y1 of 1, and defining the time period as an abnormal time period when Y1 is more than or equal to the preset value Y2;
when Y1< Y2, defining the period as a differential period;
wherein, the preset value P, the preset value M1 and the preset value Y2 are all set by professionals;
S6: repeating the steps S2-S5, and dividing the X time periods into a common period, a slight difference period and an abnormal period respectively;
step three: after the common period, the slight different period and the abnormal period are determined, randomly selecting one day from s days as a selected day, and determining an analysis result as a current error range interval by analyzing the deviation value of the common moment and the abnormal moment of the selected day;
The specific mode for determining the current error range interval is as follows:
p1: randomly selecting one day from s days as a selected day, acquiring the common time period and the abnormal time period of the selected day, extracting the deviation values Uj of Z common time periods of the selected day, and calculating the average value of Z deviation values Uj to serve as a judgment value Ut; wherein, 1 is less than or equal to j is less than or equal to Z, Z is the total number of the common time period of the selected day;
P2: then selecting an abnormal period with the largest deviation value of the day, recording the deviation value of the abnormal period as Uc, obtaining the average value Hp of the difference stream value H i of the abnormal period, sorting Hi from big to small according to the result of I Hi-Hp I, sequentially deleting H i with the forefront of the sorting, recalculating the deviation value Uc until Uc is less than or equal to the judgment value Ut, obtaining the deleted difference stream value Hi, and obtaining the average value Hi of the difference stream value through a formula Wherein D is an error value, w is the number of deleted differential stream values H i, D is more than or equal to 1 and less than or equal to w, and H i-d is any one of the number of deleted differential stream values H i;
P3: standard current I s is acquired, and a current error range interval G is defined: [ I s-D, I s +D ];
It should be noted that, the deviation value in the third step is the same as the deviation value in the second step;
Step four: all the common time period, the slight different time period and the abnormal time period are acquired, and the current real-time detection is carried out through the electric fingerprint collector according to the property of the time period, wherein the specific mode of the current real-time detection is as follows:
When the detection time period is a common time period, defining to collect real-time current once every time T1;
when the detection time period is a slight difference time period, defining to collect real-time current once every time T2;
When the detection time period is an abnormal time period, defining to collect real-time current once every time T3;
Wherein T1> T2> T3, the specific T1, T2 and T3 times being set by the practitioner;
Step five: the measured real-time current is recorded as I r through the electric fingerprint collector, the real-time current is judged with a current error range interval G, whether a pre-warning signal is generated by the real-time current I s is determined according to a judging result, and the generated pre-warning signal is sent to a platform control center;
Example two
In the implementation process of the embodiment, on the basis of the first embodiment, the difference between the embodiment and the first embodiment is that the measured real-time current I r and the current error range interval G are judged by the electric fingerprint collector, and the specific judging mode is as follows:
when I b-D < I r < I b +D, determining that the real-time current I r is within a reasonable range, and performing no treatment at this time;
when I b +D < I r, determining that the real-time current I r is an overload current, and triggering an overload early warning signal to be sent to a platform control center;
when I r is smaller than I b-D, the real-time current I r is judged to be weak current, and a weak early warning signal is triggered to be sent to a platform control center;
Example III
In the specific implementation process of the embodiment, on the basis of the first embodiment and the second embodiment, the difference between the first embodiment and the second embodiment is that the platform control center determines an evaluation value according to the generated early warning signal, inputs the evaluation value into a preset problem model for recognition, outputs a recognition result to a monitoring person, and the monitoring person evaluates the implementation problem of the early warning signal according to the recognition result;
The specific mode for determining the judgment value is as follows:
AS1: when an overload early warning signal is received, acquiring real-time current I s of the overload early warning signal, and obtaining a judgment value FS through FS=alpha× I r-Bvc;
AS2: when a weak early warning signal is received, acquiring real-time current I s of the weak early warning signal, and acquiring a judgment value FD through FD= |beta multiplied by I r-Bvc |;
AS3: inputting the judgment value FS or the judgment value FD into a preset problem model for recognition, obtaining a recognition result, and outputting the recognition result to monitoring staff;
Wherein, alpha is a coefficient factor, bvc is a current median, and specific parameters are set by staff;
It should be noted that: the preset problem model is set in advance by a professional according to historical current change, records various problems of abnormal current, and particularly judges through the numerical value of a judgment value, for example, when the judgment value FS is large, the judgment result can be that a charged battery is aged, and when the judgment value FS is small, the judgment result can be that the charging equipment fails;
Example IV
This embodiment includes all of the three embodiments described above in the specific implementation.
Some of the data in the above formulas are numerical calculated by removing their dimensionality, and the contents not described in detail in the present specification are all well known in the prior art.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (8)
1. The battery charging large model anomaly identification method based on the power fingerprint is characterized by comprising the following steps of:
step one: selecting a corresponding electric fingerprint collector to be analyzed, setting standard current, recording as Is, and collecting real-time current of battery charging in real time, recording as Ib; wherein the setting of the standard current is performed by a professional;
step two: then dividing the time period into X time periods, analyzing the X time periods within preset time T, and respectively dividing the X time periods into a common time period, a slight difference time period and an abnormal time period, wherein the preset time T refers to a time period of s days forward from the current time, s is a preset value, and the preset time period is specifically set by professional staff;
Step three: after the common period, the slight different period and the abnormal period are determined, randomly selecting one day from s days as a selected day, and determining an analysis result as a current error range interval by analyzing the deviation values of the common time and the abnormal time of the selected day;
step four: acquiring all common time periods, slight different time periods and abnormal time periods, acquiring real-time currents at different intervals according to the properties of the time periods through an electric fingerprint acquisition device, and determining current real-time detection;
Step five: the measured real-time current Is recorded as Ir through the electric fingerprint collector, the real-time current Is judged with a current error range interval G, whether the real-time current Is generates an early warning signal or not Is determined according to a judging result, and the generated early warning signal Is sent to a platform control center;
In the second step, the specific modes of dividing into a common period, a slight different period and an abnormal period are as follows:
s1: setting an interval t1 time in X time periods to collect real-time current Ib;
s2: then, a time period Is selected at will, real-time current Ib Is collected, absolute values of the real-time current Ib and standard current Is are calculated, namely |Ib-is|, a calculated result Is recorded as a difference current value Hi, and then all difference current values Hi in the time period are obtained, wherein 0<i +.n, n Is expressed as the number of all difference current values collected in the time period, and n Is more than or equal to 1;
S3: the average value Hp of n differential stream values Hi is obtained, and then the formula is passed: Obtaining a deviation value Uk of the time period;
S4: then, acquiring a deviation value Uk of the time period for every day in s days, wherein k is equal to or less than 1 and equal to or less than s, and k represents any deviation value of the time period in s days;
S5: taking the average value of s deviation values Uk, recording as Up, judging Up, and defining the time period as a common time period when Up is smaller than a preset value P;
the step S5 further includes:
When Up is more than or equal to a preset value P, obtaining a deviation value Uk which is more than the average value Up, sorting from large to small, sequentially selecting Uk and Up which are the foremost in sorting, performing phase difference calculation, namely Uk-Up, marking the calculated result as Ug, judging the magnitude of Ug and the preset value M1, automatically generating 1 when Ug is more than or equal to M1, finally counting the number Y1 of 1, and defining the time period as an abnormal time period when Y1 is more than or equal to the preset value Y2;
when Y1< Y2, the period is defined as a differential period.
2. The method for identifying the abnormality of the battery charging large model based on the power fingerprint according to claim 1, wherein the acquisition of the real-time current Ib is performed at an interval t1 time in the battery charging operation state, and t1 is a preset value.
3. The method for identifying the abnormality of the battery charging large model based on the power fingerprint according to claim 1, wherein in the third step, the specific manner of determining the current error range interval is as follows:
P1: randomly selecting one day from s days as a selected day, acquiring the common time period and the abnormal time period of the selected day, extracting the deviation values Uj of Z common time periods of the selected day, calculating the average value of Z deviation values Uj, and taking the average value as a judgment value Ut; wherein, 1 is less than or equal to j is less than or equal to Z, Z is the total number of the common time period of the selected day;
P2: then selecting an abnormal period with the largest deviation value of the day, recording the deviation value of the abnormal period as Uc, obtaining the average value Hp of the difference stream value Hi of the abnormal period, sorting Hi from big to small according to the result of I Hi-Hp I, sequentially deleting Hi with the forefront sorting, recalculating the deviation value Uc until Uc is less than or equal to the judgment value Ut, obtaining the deleted difference stream value Hi, and obtaining the average value Hp of the difference stream value Hi by the formula Wherein D is an error value, w is the number of deleted difference stream values Hi, D is more than or equal to 1 and less than or equal to w, and H i-d is any one of the number of deleted difference stream values Hi.
4. The battery charging large model anomaly identification method based on power fingerprint according to claim 3, further comprising, after step P2:
P3: standard current Is obtained, and a current error range interval G Is defined: [ Is-D, is+D ].
5. The method for identifying the abnormality of the battery charging large model based on the power fingerprint according to claim 1, wherein in the fourth step, the specific mode of current real-time detection is as follows:
When the detection time period is a common time period, defining to collect real-time current once every time T1;
when the detection time period is a slight difference time period, defining to collect real-time current once every time T2;
When the detection time period is an abnormal time period, defining to collect real-time current once every time T3;
wherein T1> T2> T3.
6. The method for identifying battery charging large model abnormality based on power fingerprint according to claim 3, wherein in the fifth step, the specific judgment mode is that of an early warning signal:
when Ib-D is smaller than Ir < Ib+D, the real-time current Ir is judged to be within a reasonable range, and no treatment is performed at the moment;
When Ib+D < Ir, determining that the real-time current Ir is an overload current, and triggering an overload early warning signal to be sent to a platform control center;
When Ir is smaller than Ib-D, the real-time current Ir is judged to be weak current, and a weak early warning signal is triggered to be sent to a platform control center.
7. The method for identifying the abnormality of the battery charging large model based on the power fingerprint according to claim 1, wherein the platform control center determines an evaluation value according to the generated early warning signal, inputs the evaluation value into a preset problem model for identification, outputs an identification result to a monitoring person, and the monitoring person evaluates the implementation problem of the early warning signal according to the identification result.
8. The method for identifying the battery charging large model abnormality based on the power fingerprint according to claim 7, wherein the specific determination judgment value mode is as follows:
AS1: when an overload early warning signal Is received, acquiring real-time current Is of the overload early warning signal, and obtaining a judging value FS through FS=alpha×Ir-Bvc;
AS2: when a weak early warning signal Is received, acquiring real-time current Is of the weak early warning signal, and acquiring a judgment value FD through FD= |beta multiplied by Ir-Bvc |;
AS3: inputting the judgment value FS or the judgment value FD into a preset problem model for recognition, obtaining a recognition result, and outputting the recognition result to monitoring staff;
wherein, alpha is a coefficient factor, bvc is a current median value and is a preset value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410757006.7A CN118336877B (en) | 2024-06-13 | 2024-06-13 | Battery charging large model anomaly identification method based on electric power fingerprint |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410757006.7A CN118336877B (en) | 2024-06-13 | 2024-06-13 | Battery charging large model anomaly identification method based on electric power fingerprint |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118336877A CN118336877A (en) | 2024-07-12 |
| CN118336877B true CN118336877B (en) | 2024-08-20 |
Family
ID=91766647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410757006.7A Active CN118336877B (en) | 2024-06-13 | 2024-06-13 | Battery charging large model anomaly identification method based on electric power fingerprint |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118336877B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109799419A (en) * | 2019-01-29 | 2019-05-24 | 国家电网有限公司 | A kind of secondary error connection analyzer of exchange |
| CN117520818A (en) * | 2023-11-08 | 2024-02-06 | 广州水沐青华科技有限公司 | Power fingerprint identification method and device, electronic equipment and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11774944B2 (en) * | 2016-05-09 | 2023-10-03 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for the industrial internet of things |
| KR101934103B1 (en) * | 2017-09-28 | 2018-12-31 | 주식회사 스타코프 | Virtual measurement instrumentation for electric power, electric power meter and electric power quality measurement, and method for acquiring, transferring and processing measured data using them |
| US11476685B2 (en) * | 2019-09-09 | 2022-10-18 | General Electric Company | System and method for detecting battery faults in a pitch system of a wind turbine |
| CN116341788A (en) * | 2022-11-09 | 2023-06-27 | 国网甘肃省电力公司兰州供电公司 | Accurate electric power fingerprint management method for power distribution network line loss analysis |
| CN117233615B (en) * | 2023-11-10 | 2024-02-06 | 中油绿电新能源有限公司 | Battery charging process abnormality detection method and device based on comparison learning network |
-
2024
- 2024-06-13 CN CN202410757006.7A patent/CN118336877B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109799419A (en) * | 2019-01-29 | 2019-05-24 | 国家电网有限公司 | A kind of secondary error connection analyzer of exchange |
| CN117520818A (en) * | 2023-11-08 | 2024-02-06 | 广州水沐青华科技有限公司 | Power fingerprint identification method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118336877A (en) | 2024-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112561736A (en) | Fault diagnosis system and method for relay protection device of intelligent substation | |
| CN116308305B (en) | Bridge health monitoring data management system | |
| CN111046582A (en) | Nuclear power station diesel generating set coil temperature early warning method and system | |
| CN112861350B (en) | Temperature overheating defect early warning method for stator winding of water-cooled steam turbine generator | |
| CN109784668B (en) | Sample feature dimension reduction processing method for detecting abnormal behaviors of power monitoring system | |
| CN110929751A (en) | Current transformer unbalance warning method based on multi-source data fusion | |
| CN116664015A (en) | Intelligent charging pile management system and method thereof | |
| CN116166983A (en) | Train bow net fault detection method based on machine learning | |
| CN115796708B (en) | Big data intelligent quality inspection method, system and medium for engineering construction | |
| CN117691722B (en) | Lithium battery charging safety monitoring and early warning method and system | |
| CN115372816A (en) | Power distribution switchgear operation fault prediction system and method based on data analysis | |
| CN116315173A (en) | Battery temperature sampling system based on new energy automobile | |
| CN113902241A (en) | Power grid equipment maintenance strategy system and method based on comprehensive state evaluation | |
| CN115034094A (en) | Prediction method and system for operation state of metal processing machine tool | |
| CN117150418B (en) | Transformer operation detection period formulation method and system based on state characteristic fault tree | |
| CN118336877B (en) | Battery charging large model anomaly identification method based on electric power fingerprint | |
| CN116923188B (en) | Charging protection system of new energy vehicle | |
| CN113220799A (en) | Big data early warning management system | |
| CN116720983A (en) | Power supply equipment abnormality detection method and system based on big data analysis | |
| CN117132225A (en) | Digital intelligent management platform for laboratory | |
| CN115186935B (en) | Electromechanical device nonlinear fault prediction method and system | |
| CN113407520A (en) | Power network safety data cleaning system and method based on machine learning | |
| CN112434955A (en) | Distribution network line operation risk sensing method based on multi-data fusion | |
| CN111103487A (en) | Non-invasive PST anomaly monitoring method based on power consumption analysis | |
| CN118277924B (en) | Desktop power supply intelligent detection method based on data driving |
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 |