CN117554844A - Battery monomer fault detection method and device of energy storage system - Google Patents
Battery monomer fault detection method and device of energy storage system Download PDFInfo
- Publication number
- CN117554844A CN117554844A CN202311832549.2A CN202311832549A CN117554844A CN 117554844 A CN117554844 A CN 117554844A CN 202311832549 A CN202311832549 A CN 202311832549A CN 117554844 A CN117554844 A CN 117554844A
- Authority
- CN
- China
- Prior art keywords
- battery
- data
- energy storage
- storage system
- fault
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 82
- 238000004146 energy storage Methods 0.000 title claims abstract description 63
- 239000000178 monomer Substances 0.000 title claims abstract description 50
- 230000002159 abnormal effect Effects 0.000 claims abstract description 47
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 40
- 238000000034 method Methods 0.000 claims abstract description 34
- 239000012634 fragment Substances 0.000 claims abstract description 33
- 238000004140 cleaning Methods 0.000 claims abstract description 19
- 238000003745 diagnosis Methods 0.000 claims abstract description 18
- 238000013450 outlier detection Methods 0.000 claims abstract description 18
- 239000011159 matrix material Substances 0.000 claims description 32
- 238000005457 optimization Methods 0.000 claims description 16
- 238000007781 pre-processing Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 13
- 230000004044 response Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000012983 electrochemical energy storage Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 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]
- G01R31/378—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]
- G01R31/385—Arrangements for measuring battery or accumulator variables
- G01R31/387—Determining ampere-hour charge capacity or SoC
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
Abstract
The invention discloses a battery monomer fault detection method and device of an energy storage system, wherein the method comprises the steps of obtaining data of thermal runaway of each battery monomer in the energy storage system under an operation condition to obtain full life cycle data; the full life cycle data is preprocessed in a cleaning state to obtain a plurality of charge and discharge fragment data; based on a pre-constructed successive variation modal model, carrying out successive variation modal decomposition by adjusting model parameters to obtain each maximum voltage dynamic fluctuation component and each voltage dynamic fluctuation component; based on the selected outlier threshold, carrying out local outlier detection on each maximum voltage dynamic fluctuation component to obtain an abnormal battery monomer detection result; and diagnosing the internal faults of the battery according to the selected first sliding window and the preset slope condition, and obtaining the internal fault detection result of the battery cell. The embodiment realizes the effective diagnosis of the faults of the battery single body, and improves the rapidity, the accuracy and the universality of detection.
Description
Technical Field
The invention relates to the field of fault detection of energy storage batteries, in particular to a method and a device for detecting single battery faults of an energy storage system.
Background
The safety and thermal runaway problems of energy storage batteries seriously affect the development of the electrochemical energy storage industry. Due to factors such as improper use behavior, difference in factory process and the like, serious electric abuse and mechanical abuse are caused, the abuse accelerates battery aging, service life is rapidly attenuated, and the inconsistency of the monomers is increased, so that the risk of thermal runaway is easily triggered. Therefore, the power battery fault diagnosis and the safety early warning play an important role in saving the life and property safety of people, the safe and stable operation of the energy storage system can be ensured, the system efficiency is improved, and the operation cost is reduced.
At present, a neural network or a derivative of the neural network is mostly adopted for fault diagnosis and safety early warning of a battery, but the neural network model is utilized for optimizing and complicating, and a deep neural network has the defects of long optimizing time and the like, and the practicability of engineering is not considered.
Disclosure of Invention
The invention provides a battery cell fault detection method and device for an energy storage system, which can effectively diagnose the battery cell fault of the energy storage system and improve the rapidity, accuracy and universality of the battery cell fault detection.
In order to solve the above technical problems, an embodiment of the present invention provides a method and an apparatus for detecting a fault of a battery cell of an energy storage system, including:
acquiring data of thermal runaway of each battery monomer in the energy storage system under the operating condition, and acquiring full life cycle data;
the full life cycle data is preprocessed in a cleaning state to obtain a plurality of charge and discharge fragment data;
based on a pre-constructed successive variation modal model, carrying out successive variation modal decomposition on each charge and discharge fragment data by adjusting model parameters to obtain a maximum voltage dynamic fluctuation component and a voltage dynamic fluctuation component corresponding to each charge and discharge fragment data;
based on the selected outlier threshold, carrying out local outlier detection on each maximum voltage dynamic fluctuation component to obtain an abnormal battery monomer detection result;
and diagnosing the internal faults of the battery according to the selected first sliding window and the preset slope condition, and obtaining the internal fault detection result of the battery cell.
By implementing the embodiment of the invention, the data of thermal runaway of each battery monomer in the energy storage system under the operating condition is obtained, and full life cycle data is obtained; the full life cycle data is preprocessed in a cleaning state to obtain a plurality of charge and discharge fragment data; based on a pre-constructed successive variation modal model, carrying out successive variation modal decomposition on each charge and discharge fragment data by adjusting model parameters to obtain a maximum voltage dynamic fluctuation component and a voltage dynamic fluctuation component corresponding to each charge and discharge fragment data; based on the selected outlier threshold, carrying out local outlier detection on each maximum voltage dynamic fluctuation component to obtain an abnormal battery monomer detection result; and diagnosing the internal faults of the battery according to the selected first sliding window and the preset slope condition, and obtaining the internal fault detection result of the battery cell. The full life cycle data under the operation working condition is subjected to cleaning state pretreatment and gradual variation modal decomposition, and abnormal faults and internal faults of the battery monomers of the energy storage system are effectively diagnosed by utilizing the local outlier detection of the box diagram and the internal fault diagnosis of the battery, so that the method can be suitable for various working conditions, can rapidly and accurately diagnose the battery monomers of different types, and can further effectively explain the effectiveness of the fault detection of the battery monomers by verifying the data of the thermal runaway of the energy storage system, thereby improving the rapidity, the accuracy and the universality of the fault detection of the battery monomers.
As a preferred scheme, cleaning state preprocessing is performed on full life cycle data to obtain a plurality of charge and discharge fragment data, which specifically comprises:
processing the data null value and the abnormal value in the full life cycle data by adopting a preset data cleaning mode to obtain cleaned full life cycle data;
based on the positive and negative characteristics of current, monotonically increasing characteristics of charge state and data point continuous conditions, carrying out charge and discharge state division on the cleaned full life cycle data to obtain data of each charge and discharge segment; the continuous condition of the data points is that the number of the continuous data points is not smaller than a preset number value.
As a preferable scheme, the successive variation modal model constructed in advance specifically comprises:
the constrained optimization problem of the successive empirical mode structure is converted into the unconstrained optimization problem by introducing a quadratic penalty term and a Lagrange multiplier term, and a successive variation mode model constructed in advance is obtained, specifically:
wherein u is k (t) is the single component amplitude modulated FM signal, ω, obtained by the kth decomposition k Is the center frequency of the single-component amplitude modulation frequency modulation signal obtained by the kth decomposition, ω is a frequency parameter, ζ is a balance parameter,as a wiener filtering result of the current margin of saddle points of the modal component after Fourier transformation, ++>Frequency domain values after fourier transformation after saddle points are found for the time series of modal components, +.>Saddle point is calculated for the original input signal and then the frequency domain value is subjected to Fourier transform for the 1 st time, ++>Saddle-point-determined frequency domain value after kth Fourier transform for original input signal, ++>For the filter, gamma is Lagrange multiplier, k is the total number of modes, infinity is the value added by iterative optimization, and +_>For the frequency response of the ith filter, < +.>Frequency response of the original signal after fourier transformation, < >>Is the frequency response of the lagrangian multiplier.
As a preferred scheme, the model parameters are adjusted specifically as follows:
setting the input in the pre-constructed successive variation modal model as a single voltage sequence of a battery, setting a compact index of original data as a preset index value, setting Gaussian noise as 0, setting a standard tolerance of convergence as a preset tolerance value, and setting a stop type as 1.
As a preferred scheme, based on a selected outlier threshold, each maximum voltage dynamic fluctuation component is subjected to box line diagram local outlier detection to obtain an abnormal single battery detection result, which specifically comprises:
obtaining a maximum dynamic voltage fluctuation component matrix according to each maximum voltage dynamic fluctuation component;
calculating a mean matrix and a standard deviation matrix based on the selected second sliding window and the maximum dynamic voltage fluctuation component matrix;
according to the mean value matrix and the standard deviation matrix, an outlier threshold is selected to obtain outliers, and the formula is:
ο＝(U＞μ+W*σ)|(U＜μ-W*σ)
wherein o is an outlier, W is an outlier threshold, mu is a mean matrix, sigma is a standard deviation matrix, and U is a maximum dynamic voltage fluctuation component matrix;
and drawing outliers and a box line graph, and judging abnormal data based on the box line graph to obtain an abnormal single battery detection result.
As a preferred scheme, according to the selected first sliding window and a preset slope condition, diagnosing the internal faults of the battery for each voltage dynamic fluctuation component to obtain the detection result of the internal faults of the battery monomer, specifically:
carrying out dimensionless treatment on each voltage dynamic fluctuation component to obtain the absolute value of each voltage mean value difference value;
sliding based on the selected first sliding window according to the absolute value of the difference value of each voltage mean value, calculating a kurtosis factor, and calculating the slope between the highest peak value and the lowest peak value in the current window to obtain the slope of the current window;
if the slope of the current window meets the first slope condition, judging that the current battery cell is an internal short circuit fault; the first slope condition specifically includes:
fault1＝k c ＜0|((k c ≤0)&(0≤k n ＜1))
wherein k is c For the slope, k, of the current window n As the slope of the next window, fault1 is an internal short circuit fault;
if the slope of the current window meets the second slope condition, judging that the current battery cell is an open circuit fault; wherein, the second slope condition specifically is:
fault2＝(0≤k c ＜1)|((0≤k c ＜1)&k n ＜0)
wherein fault2 is an open circuit fault;
and counting the battery cells which are judged to correspond to the internal short circuit fault and the open circuit fault, and obtaining the internal fault detection result of the battery cells.
Preferably, before counting the battery cells determined to correspond to the internal short circuit fault and the open circuit fault, the method further comprises:
and when the sliding of the selected first sliding window is finished, counting the occurrence times of short-circuit faults and open-circuit faults meeting the preset slope conditions, selecting a sliding total window with the upper threshold value of fault processing, calculating the slope of the window based on the sliding total window, and judging the internal short-circuit faults and open-circuit faults of the corresponding battery cells according to the preset slope conditions and the slope of the window.
In order to solve the same technical problem, the embodiment of the invention further provides a battery monomer fault detection device of an energy storage system, which comprises: the system comprises a data acquisition module, a data preprocessing module, a modal decomposition module, an abnormal battery monomer detection module and a battery internal fault diagnosis module;
the data acquisition module is used for acquiring data of thermal runaway of each battery monomer in the energy storage system under the operating condition to obtain full life cycle data;
the data preprocessing module is used for preprocessing the full life cycle data in a cleaning state to obtain a plurality of charge and discharge fragment data;
the modal decomposition module is used for carrying out successive variation modal decomposition on each charge and discharge segment data by adjusting model parameters based on a successive variation modal model constructed in advance to obtain a maximum voltage dynamic fluctuation component and a voltage dynamic fluctuation component corresponding to each charge and discharge segment data;
the abnormal battery cell detection module is used for carrying out local outlier detection on each maximum voltage dynamic fluctuation component based on the selected outlier threshold value to obtain an abnormal battery cell detection result;
the battery internal fault diagnosis module is used for carrying out battery internal fault diagnosis on each voltage dynamic fluctuation component according to the selected first sliding window and a preset slope condition, and obtaining a battery cell internal fault detection result.
In order to solve the same technical problems, the embodiment of the invention also provides a computer device, which comprises a processor and a memory, wherein the memory is used for storing a computer program, and the computer program is executed by the processor to realize a battery cell fault detection method of the energy storage system.
To solve the same technical problem, the embodiment of the invention further provides a computer readable storage medium storing a computer program, which when executed by a processor, implements a method for detecting a battery cell fault of an energy storage system.
Compared with the prior art, the invention has the advantages that:
(1) The abnormal battery monomer detection result is obtained by adjusting the model parameters of the pre-constructed successive variation modal model, the dilemma that the variation modal decomposition VMD has low convergence speed and long calculation time is solved, the uncertainty of the number and parameters of the modes needing to be set in advance is reduced, the position of the abnormal monomer can be accurately positioned, and a certain early warning effect can be achieved on the inconsistency of the monomers.
(2) The generation slope of the sliding window is used for realizing the detection of single internal faults, the slope calculation and statistics mode are adopted for internal short-circuit faults and open-circuit faults, potential internal short-circuit faults and open-circuit faults are detected through the change times of the slopes of the current sliding window and the next sliding window, the early warning time can be 55 minutes in advance at maximum, enough time is provided for enterprises and users to find and process fault single bodies in the energy storage system before thermal runaway occurs, and the stability of the electrochemical energy storage system is improved while life and property are saved.
(3) The battery single fault detection method is realized by utilizing successive variation modal decomposition, box diagram local outlier detection and battery internal fault diagnosis, so that the battery single fault detection method has the advantages of effectively diagnosing the battery single fault of the energy storage system, reducing the calculated amount, along with rapidness, accuracy and universality, and can be better applied to engineering practice.
Additional features and advantages of the invention will be set forth in the detailed description which follows.
Drawings
Fig. 1: a schematic flow chart of an embodiment of a method for detecting a single battery fault of an energy storage system is provided in the invention;
fig. 2: a simplified flow chart of one embodiment of a method for detecting a battery cell failure of an energy storage system provided by the invention;
fig. 3: the invention provides a schematic diagram for detecting the maximum voltage fluctuation component and local outlier of a battery cell of one embodiment of a battery cell fault detection method of an energy storage system;
fig. 4: the thermal runaway data of the energy storage system of one embodiment of the battery monomer fault detection method of the energy storage system is applied to an internal fault detection schematic diagram;
fig. 5: the invention provides a structural schematic diagram of an embodiment of a battery cell fault detection device of an energy storage system.
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, a flow chart of a method for detecting a battery cell failure of an energy storage system according to an embodiment of the invention is shown in fig. 2. The battery cell fault detection method comprises steps 101 to 105, wherein the steps are as follows:
step 101: and acquiring data of thermal runaway of each battery monomer in the energy storage system under the operating condition, and obtaining full life cycle data.
In this embodiment, data of thermal runaway of the battery under operating conditions is obtained from a data platform of the energy storage system. As an example, the data reset index is used to read the data such as the charge and discharge current and the SOC value obtained from the platform, and the obtained partial battery data is shown in the following table 1:
table 1 partial battery data obtained
It should be noted that, the cells 1 to 97 are battery cells of the energy storage system, and the numbers in the table represent the voltage values sampled at each time, and the unit is V. The insulation resistance is the resistance of the whole energy storage system at each sampling time, and the unit is KΩ. The SOC, i.e., state of charge, of a battery is used to reflect the remaining capacity of the battery, and is defined numerically as the ratio of the remaining capacity to the battery capacity, commonly expressed as a percentage.
Step 102: and (3) preprocessing the full life cycle data in a cleaning state to obtain a plurality of charge and discharge fragment data.
In this embodiment, the data of the full life cycle is obtained through the data platform of the energy storage system, and the full life cycle data of the battery is required to be segmented into the charge and discharge fragment data of a small sample due to huge data volume of the full life cycle, and the extracted data of the full life cycle of the battery of the energy storage system is cleaned and preprocessed in state division, so as to obtain the charge and discharge fragment data, wherein the charge and discharge fragment data comprises the charge fragment data and the discharge fragment data. The data of the whole life cycle of the power battery is divided into small sample data of charge and discharge, so that necessary data support is provided for the detection of subsequent abnormal single bodies and the fault diagnosis of potential internal short circuits/open circuits.
Optionally, step 102 specifically includes adopting a preset data cleaning mode to process data null values and abnormal values in full life cycle data to obtain cleaned full life cycle data; based on the positive and negative characteristics of current, monotonically increasing characteristics of charge state and data point continuous conditions, carrying out charge and discharge state division on the cleaned full life cycle data to obtain data of each charge and discharge segment; the continuous condition of the data points is that the number of the continuous data points is not smaller than a preset number value.
In this embodiment, the data null value and the abnormal value of the full life cycle are processed by adopting a data cleaning mode such as removing or difference value, and then the data are divided into the charging segment and the discharging segment according to the positive and negative of the current and the monotonically increasing characteristic of the state of charge SOC under the condition that the continuous data points are ensured. Wherein the continuous condition of the data points is that the number of the continuous data points is not less than a preset number value, such as: the data points are at least 10 or more in succession. As an example, whether the current is positive or negative and the SOC monotonically increases to be a null value or not is used, and at least 10 continuous data points are ensured, and finally all data information is extracted by recording index values of a starting point and an ending point, so that the charge and discharge fragment data are obtained.
Step 103: based on a pre-constructed successive variation modal model, the charge and discharge fragment data are subjected to successive variation modal decomposition by adjusting model parameters, and a maximum voltage dynamic fluctuation component and a voltage dynamic fluctuation component corresponding to the charge and discharge fragment data are obtained.
In this embodiment, the data of the charge and discharge segments are decomposed by using a Successive Variation Mode (SVMD) decomposition, the maximum dynamic voltage fluctuation component is obtained, and the maximum voltage fluctuation component is used, so that the adaptability is strong, and the accuracy of abnormal monomer detection is remarkably improved while the mode aliasing is reduced. And the parameters of the successive variation modes are adjusted, so that the phenomenon that the convergence speed is influenced by the parameter increase or decrease is avoided, and the overfitting or underfitting is caused.
Optionally, the pre-constructed successive variation modal model specifically includes:
the constrained optimization problem of the successive empirical mode structure is converted into the unconstrained optimization problem by introducing a quadratic penalty term and a Lagrange multiplier term, and a successive variation mode model constructed in advance is obtained, specifically:
wherein u is k (t) is the single component amplitude modulated FM signal, ω, obtained by the kth decomposition k Is the center frequency of the single-component amplitude modulation frequency modulation signal obtained by the kth decomposition, namely the iteration value, ω is a frequency parameter, ζ is a balance parameter,as a wiener filtering result of the current margin of the saddle point of the modal component after the Fourier transform,/>frequency domain values after fourier transformation after saddle points are found for the time series of modal components, +.>Saddle point is calculated for the original input signal and then the frequency domain value is subjected to Fourier transform for the 1 st time, ++>Saddle-point-determined frequency domain value after kth Fourier transform for original input signal, ++>For the filter, gamma is Lagrangian multiplier, k is the total number of modes, and infinity is the value increased by iterative optimization, from 1 to infinity,>for the frequency response of the ith filter, < +.>Frequency response of the original signal after fourier transformation, < >>Is the frequency response of the lagrangian multiplier.
In this embodiment, the maximum voltage dynamic fluctuation component is obtained by applying successive empirical mode decomposition, and based on the successive empirical mode structure, a constrained optimization problem is mainly converted into an unconstrained optimization problem to construct a successive variation mode model, and the constrained optimization problem has the following formula:
Subject to:u k (t)+f r (t)＝f signal
wherein: delta (t) is the dirac function, t is the time variable, j is the imaginary part of the complex number,representing the gradient operation procedure, u k (t) is the single-component amplitude modulated frequency modulated signal obtained by the kth decomposition; />Is the residual signal; u (u) i (t) is a modal component obtained by decomposition; f (f) u (t) is the unprocessed portion of the input signal; omega k Is the center frequency of the single-component amplitude modulation frequency modulation signal obtained by the kth decomposition; * Representing a convolution; ζ is the equilibrium parameter; beta k (t) and beta i (t) are all filtersImpulse response of (2); alpha is the frequency response coefficient; f (f) signal Is the original signal.
For the constrained optimization problem, a constrained optimization problem is converted into an unconstrained optimization problem by introducing a quadratic penalty term and a Lagrange multiplier term, and the unconstrained optimization problem conversion formula is as follows:
optionally, the model parameters are adjusted, specifically:
setting the input in the pre-constructed successive variation modal model as a single voltage sequence of a battery, setting a compact index of original data as a preset index value, setting Gaussian noise as 0, setting a standard tolerance of convergence as a preset tolerance value, and setting a stop type as 1.
In this embodiment, model parameters of successive variation modes are adjusted, inputs in the successive variation modes are respectively set as a single voltage sequence of a battery, an original data compact index is set as a preset index value (for example: 3000), gaussian noise tau is set as 0, a converged standard tolerance tol is set as a preset tolerance value (for example: 1 e-7), a stop type is set as 1, the parameters are set according to manual experience, the parameters are adjusted, overfitting or underfitting caused by the influence of parameter increase or decrease on convergence speed can be better avoided, the possibility of overfitting/underfitting is reduced by adjusting the parameters of the model, and the model decomposition accuracy is improved.
Step 104: and based on the selected outlier threshold, carrying out local outlier detection on each maximum voltage dynamic fluctuation component to obtain an abnormal battery cell detection result.
In this embodiment, the maximum voltage fluctuation component of each single unit sequence is obtained through successive variation modal decomposition, a box line graph and an outlier are drawn through the maximum voltage fluctuation component, a proper threshold is automatically selected according to the average value and the median of the maximum voltage dynamic fluctuation component, and the outlier and the box line graph are drawn, so that abnormal single units and the number are determined according to the pattern of the outlier, and an abnormal single unit detection result is obtained, namely, the abnormal single unit detection result comprises abnormal single units and the number of the abnormal single units. Since the abnormal unit includes a plurality of abnormal cases such as a unit inconsistency, an internal short-circuit fault, and an open-circuit fault, the internal short-circuit fault and the open-circuit fault are further diagnosed in step 105.
Optionally, step 104 specifically includes steps 1041 to 1044, where each step specifically includes the following steps:
step 1041: and obtaining a maximum dynamic voltage fluctuation component matrix according to each maximum voltage dynamic fluctuation component.
In this embodiment, the maximum voltage dynamic fluctuation component is obtained through successive variation modal decomposition, and the maximum dynamic voltage fluctuation component matrix is represented by the following formula:
wherein,maximum dynamic voltage ripple for nth cellThe component, U, is the maximum dynamic voltage fluctuation component matrix.
Step 1042: and calculating a mean matrix and a standard deviation matrix based on the selected second sliding window and the maximum dynamic voltage fluctuation component matrix.
In this embodiment, by setting the second sliding window to 10, the mean and standard deviation of the maximum dynamic fluctuation component are calculated as follows:
in the method, in the process of the invention,for the mean value of the maximum dynamic fluctuation component of the nth voltage sequence, mu is the mean matrix of the maximum dynamic fluctuation component,/for the n-th voltage sequence>The standard deviation of the maximum dynamic fluctuation component of the nth voltage sequence is shown, and sigma is the standard deviation matrix of the maximum dynamic fluctuation component.
Step 1043: according to the mean value matrix and the standard deviation matrix, an outlier threshold is selected to obtain outliers, and the formula is:
ο＝(U＞μ+W*σ)|(U＜μ-W*σ)
wherein o is an outlier, W is an outlier threshold, mu is a mean matrix, sigma is a standard deviation matrix, and U is a maximum dynamic voltage fluctuation component matrix.
In this embodiment, a box line outlier plot of the battery pack generation parameter is drawn, outliers are drawn through an improved local outlier algorithm of the box line plot, and a threshold value of the outliers is selected according to the following formula:
ο＝(U＞μ+W*σ)|(U＜μ-W*σ)
where o is an outlier and W is a defined outlier threshold, which is set according to the 3λ principle.
Step 1044: and drawing outliers and a box line graph, and judging abnormal data based on the box line graph to obtain an abnormal single battery detection result.
In this embodiment, a maximum voltage fluctuation component and a local outlier detection schematic diagram of the battery cell are shown in fig. 3, and a box line diagram outlier is drawn to find out an abnormal cell:
R IQ ＝Q 3 -Q 1
B L ＝Q 1 -1.5×R IQ
B U ＝Q 3 +1.5×R IQ
in which Q 3 And Q is equal to 1 Respectively upper and lower quartiles; r is R IQ The data is a quartile range; using R IQ And calculating the upper and lower whisker lines B from the upper and lower quartiles L And B is connected with U Used for judging whether the data is abnormal or not.
Step 105: and diagnosing the internal faults of the battery according to the selected first sliding window and the preset slope condition, and obtaining the internal fault detection result of the battery cell.
In this embodiment, in order to detect a battery cell sequence of an internal short circuit fault and an open circuit fault, thermal runaway data of the energy storage system is applied to an internal fault detection schematic diagram, as shown in fig. 4, the internal fault is the internal short circuit fault or the open circuit fault, a voltage dynamic fluctuation component is obtained after processing in step 103, then an absolute value of a characteristic difference value is obtained through dimensionless processing of kurtosis, then a suitable sliding window is selected, the slope of the highest peak and the lowest peak in the sliding window is calculated until the sliding is finished, the number of times of occurrence of the internal short circuit fault and the open circuit fault which potentially meet the slope condition is counted, a sliding total window of 5% (the upper threshold value of fault processing) is selected as a threshold value, and the internal short circuit fault or the open circuit fault is detected, so that the battery cell internal fault detection result including the battery cell sequence of the internal short circuit fault and the open circuit fault is obtained.
Optionally, step 105 specifically includes steps 1051 to 1056, each of which specifically includes:
step 1051: and carrying out dimensionless processing on each voltage dynamic fluctuation component to obtain the absolute value of each voltage mean value difference value.
In this embodiment, the absolute value of the characteristic difference (the absolute value of the voltage mean difference) is obtained through the dimensionless processing of the kurtosis, and the formula is as follows:
in the method, in the process of the invention,is the dimensionless characteristic value of the j-th battery cell voltage sequence vj, |v j I represents the amplitude of the signal, p (v) j ) The probability density distribution of the signal values is represented, i, M > 0 represents different minkowski constants, and M represents the total number of monomer voltage sequences. It should be noted that the voltage dynamic fluctuation component of a certain battery cell represents the voltage sequence value of the battery cell.
Step 1052: and according to the absolute value of the difference value of each voltage mean value, sliding based on the selected first sliding window, calculating a kurtosis factor, and calculating the slope between the highest peak value and the lowest peak value in the current window to obtain the slope of the current window.
In this embodiment, the kurtosis factor is calculated, third-order center distance and standard deviation four times Fang Bizhi:
wherein KI y The kurtosis of the difference y is the difference between the value of the monomer voltage sequence in a sliding window and the average value of all the monomer voltage sequences in the window, namely the absolute value of the characteristic difference, d is the standard deviation, and epsilon=3, eta=2.
The slope between the highest peak and the lowest peak within the sliding window is calculated as follows:
K＝[K 1 … k n ]
wherein K is the calculated sliding window slope matrix, K n Is the slope between the highest peak and the lowest peak within the nth sliding window.
Step 1053: if the slope of the current window meets the first slope condition, judging that the current battery cell is an internal short circuit fault; the first slope condition specifically includes:
fault1＝k c ＜0|((k c ≤0)&(0≤k n ＜1))
wherein k is c For the slope, k, of the current window n For the slope of the next window, fault1 is an internal short fault.
In this embodiment, the preset slope conditions include a first slope condition and a second slope condition, the internal short circuit fault1 is determined according to the slope k and the first slope condition, and the open circuit fault2 is determined according to the slope k and the second slope condition.
Step 1054: if the slope of the current window meets the second slope condition, judging that the current battery cell is an open circuit fault; wherein, the second slope condition specifically is:
fault2＝(0≤k c ＜1)|((0≤k c ＜1)&k n ＜0)
wherein fault2 is an open circuit fault.
Step 1055: and when the sliding of the selected first sliding window is finished, counting the occurrence times of short-circuit faults and open-circuit faults meeting the preset slope conditions, selecting a sliding total window with the upper threshold value of fault processing, calculating the slope of the window based on the sliding total window, and judging the internal short-circuit faults and open-circuit faults of the corresponding battery cells according to the preset slope conditions and the slope of the window.
In this embodiment, after the processing in step 103, a dynamic fluctuation component of voltage is obtained, then an absolute value of a characteristic difference value is obtained through dimensionless processing of kurtosis, then a suitable sliding window (a first sliding window) is selected, the slopes of the highest peak and the lowest peak in the sliding window are calculated until the sliding is finished, the times of occurrence of internal short-circuit faults and open-circuit faults which potentially meet the slope conditions are counted, a sliding total window of 5% (the upper threshold of fault processing) is selected as a threshold, an internal short-circuit fault or an open-circuit fault monomer is detected, and the battery cell sequence including the internal short-circuit faults and the open-circuit faults is counted to obtain the battery cell internal fault detection result.
Step 1056: and counting the battery cells which are judged to correspond to the internal short circuit fault and the open circuit fault, and obtaining the internal fault detection result of the battery cells.
In this embodiment, the slope generated by the sliding window is used to diagnose short/open faults in the battery:
internal short circuit fault: fault1=k c ＜0|((k c ≤0)&(0≤k n ＜1))
Open circuit failure: fault2 = (0.ltoreq.k) c ＜1)|((0≤k c ＜1)&k n ＜0)
Whether a fault occurs is determined based on a comparison between the number of potential faults that occur that meet the slope and a threshold. If the frequency of occurrence of the internal short circuit fault is larger than the frequency of occurrence of the open circuit fault, counting the monomer sequence of the frequency of occurrence of the internal short circuit. If the two faults are equal, counting the occurrence times of the internal short circuit fault and the open circuit fault.
By implementing the embodiment of the invention, the maximum voltage fluctuation component of each monomer is calculated through successive variation modal decomposition (SVMD decomposition), and abnormal monomers are detected through a box diagram and outliers. And secondly, obtaining the absolute value of the voltage mean value difference value through successive variation modal decomposition, calculating and counting the slope formed by the highest peak and the lowest peak of the current window and the next window, and detecting the potential internal short circuit/open circuit fault. Finally, the fault detection method provided by the invention is verified by using the operation data of the thermal runaway of the single battery of the energy storage system, and the early warning can be carried out 55 minutes before the thermal runaway occurs, so that the method has reliability and engineering application value.
By using different types of energy storage system data for verification and verifying the data of different energy storage system models and working conditions, through parameter input or model parameter adjustment, the internal short circuit/open circuit fault detection is higher through simulation. The accuracy and the effectiveness of the single battery fault detection method are verified by adopting different working conditions, energy storage system models and power battery models, and the single battery fault detection method can be well migrated to engineering application.
By implementing the embodiment of the invention, the data of thermal runaway of each battery monomer in the energy storage system under the operating condition is obtained, and full life cycle data is obtained; the full life cycle data is preprocessed in a cleaning state to obtain a plurality of charge and discharge fragment data; based on a pre-constructed successive variation modal model, carrying out successive variation modal decomposition on each charge and discharge fragment data by adjusting model parameters to obtain a maximum voltage dynamic fluctuation component and a voltage dynamic fluctuation component corresponding to each charge and discharge fragment data; based on the selected outlier threshold, carrying out local outlier detection on each maximum voltage dynamic fluctuation component to obtain an abnormal battery monomer detection result; and diagnosing the internal faults of the battery according to the selected first sliding window and the preset slope condition, and obtaining the internal fault detection result of the battery cell. The full life cycle data under the operation working condition is subjected to cleaning state pretreatment and gradual variation modal decomposition, and abnormal faults and internal faults of the battery monomers of the energy storage system are effectively diagnosed by utilizing the local outlier detection of the box diagram and the internal fault diagnosis of the battery, so that the method can be suitable for various working conditions, can rapidly and accurately diagnose the battery monomers of different types, and can further effectively explain the effectiveness of the fault detection of the battery monomers by verifying the data of the thermal runaway of the energy storage system, thereby improving the rapidity, the accuracy and the universality of the fault detection of the battery monomers.
Compared with the prior art, the invention has the advantages that:
(1) The abnormal battery monomer detection result is obtained by adjusting the model parameters of the pre-constructed successive variation modal model, the dilemma that the variation modal decomposition VMD has low convergence speed and long calculation time is solved, the uncertainty of the number and parameters of the modes needing to be set in advance is reduced, the position of the abnormal monomer can be accurately positioned, and a certain early warning effect can be achieved on the inconsistency of the monomers.
(2) The generation slope of the sliding window is used for realizing the detection of single internal faults, the slope calculation and statistics mode are adopted for internal short-circuit faults and open-circuit faults, potential internal short-circuit faults and open-circuit faults are detected through the change times of the slopes of the current sliding window and the next sliding window, the early warning time can be 55 minutes in advance at maximum, enough time is provided for enterprises and users to find and process fault single bodies in the energy storage system before thermal runaway occurs, and the stability of the electrochemical energy storage system is improved while life and property are saved.
(3) The battery single fault detection method is realized by utilizing successive variation modal decomposition, box diagram local outlier detection and battery internal fault diagnosis, so that the battery single fault detection method has the advantages of effectively diagnosing the battery single fault of the energy storage system, reducing the calculated amount, along with rapidness, accuracy and universality, and can be better applied to engineering practice.
Example two
Correspondingly, referring to fig. 5, fig. 5 is a schematic structural diagram of a second embodiment of a battery cell fault detection device of an energy storage system according to the present invention. As shown in fig. 5, a data acquisition module 501, a data preprocessing module 502, a modal decomposition module 503, an abnormal cell detection module 504, and a battery internal fault diagnosis module 505;
the data acquisition module 501 is configured to acquire data of thermal runaway of each battery cell in the energy storage system under an operation condition, so as to obtain full life cycle data;
the data preprocessing module 502 is configured to perform cleaning state preprocessing on full life cycle data to obtain a plurality of charge-discharge fragment data;
the modal decomposition module 503 is configured to perform a successive variation modal decomposition on each charge and discharge segment data by adjusting model parameters based on a successive variation modal model constructed in advance, so as to obtain a maximum voltage dynamic fluctuation component and a voltage dynamic fluctuation component corresponding to each charge and discharge segment data;
the abnormal battery cell detection module 504 is configured to perform local outlier detection on the box line graph on each maximum voltage dynamic fluctuation component based on the selected outlier threshold value, so as to obtain an abnormal battery cell detection result;
the battery internal fault diagnosis module 505 is configured to diagnose the internal fault of the battery for each voltage dynamic fluctuation component according to the selected first sliding window and the preset slope condition, and obtain a detection result of the internal fault of the battery cell.
By implementing the embodiment of the invention, the data of thermal runaway of each battery monomer in the energy storage system under the operating condition is obtained, and full life cycle data is obtained; the full life cycle data is preprocessed in a cleaning state to obtain a plurality of charge and discharge fragment data; based on a pre-constructed successive variation modal model, carrying out successive variation modal decomposition on each charge and discharge fragment data by adjusting model parameters to obtain a maximum voltage dynamic fluctuation component and a voltage dynamic fluctuation component corresponding to each charge and discharge fragment data; based on the selected outlier threshold, carrying out local outlier detection on each maximum voltage dynamic fluctuation component to obtain an abnormal battery monomer detection result; and diagnosing the internal faults of the battery according to the selected first sliding window and the preset slope condition, and obtaining the internal fault detection result of the battery cell. The full life cycle data under the operation working condition is subjected to cleaning state pretreatment and gradual variation modal decomposition, and abnormal faults and internal faults of the battery monomers of the energy storage system are effectively diagnosed by utilizing the local outlier detection of the box diagram and the internal fault diagnosis of the battery, so that the method can be suitable for various working conditions, can rapidly and accurately diagnose the battery monomers of different types, and can further effectively explain the effectiveness of the fault detection of the battery monomers by verifying the data of the thermal runaway of the energy storage system, thereby improving the rapidity, the accuracy and the universality of the fault detection of the battery monomers.
The battery cell fault detection device of the energy storage system can implement the battery cell fault detection method of the energy storage system in the method embodiment. The options in the method embodiments described above are also applicable to this embodiment and will not be described in detail here. The rest of the embodiments of the present application may refer to the content of the method embodiments described above, and in this embodiment, no further description is given.
In addition, the embodiment of the application further provides a computer device, which comprises a processor and a memory, wherein the memory is used for storing a computer program, and the computer program is executed by the processor to realize the steps in any of the method embodiments.
The present application further provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of any of the method embodiments described above.
The foregoing embodiments have been provided for the purpose of illustrating the general principles of the present invention, and are not to be construed as limiting the scope of the invention. It should be noted that any modifications, equivalent substitutions, improvements, etc. made by those skilled in the art without departing from the spirit and principles of the present invention are intended to be included in the scope of the present invention.
Claims (10)
1. The battery cell fault detection method of the energy storage system is characterized by comprising the following steps of:
acquiring data of thermal runaway of each battery monomer in the energy storage system under the operating condition, and acquiring full life cycle data;
preprocessing the full life cycle data in a cleaning state to obtain a plurality of charge and discharge fragment data;
based on a pre-constructed successive variation modal model, carrying out successive variation modal decomposition on each charge and discharge fragment data by adjusting model parameters to obtain a maximum voltage dynamic fluctuation component and a voltage dynamic fluctuation component corresponding to each charge and discharge fragment data;
based on the selected outlier threshold, carrying out local outlier detection on each maximum voltage dynamic fluctuation component to obtain an abnormal battery monomer detection result;
and diagnosing the internal faults of the battery according to the selected first sliding window and the preset slope condition, and obtaining the internal fault detection result of the battery cell.
2. The method for detecting a single battery fault of an energy storage system according to claim 1, wherein the cleaning state preprocessing is performed on the full life cycle data to obtain a plurality of charge-discharge fragment data, specifically:
processing the data null value and the abnormal value in the full life cycle data by adopting a preset data cleaning mode to obtain cleaned full life cycle data;
based on the positive and negative characteristics of current, monotonically increasing characteristics of charge state and data point continuous conditions, carrying out charge and discharge state division on the cleaned full life cycle data to obtain each charge and discharge fragment data; wherein the continuous condition of the data points is that the number of the continuous data points is not less than a preset number value.
3. The method for detecting a single battery fault of an energy storage system according to claim 1, wherein the pre-constructed successive variation mode model specifically comprises:
the constrained optimization problem of the successive empirical mode structure is converted into the unconstrained optimization problem by introducing a quadratic penalty term and a Lagrange multiplier term, and the pre-constructed successive variation mode model is obtained specifically as follows:
wherein u is k (t) is the single component amplitude modulated FM signal, ω, obtained by the kth decomposition k Is the center frequency of the single-component amplitude modulation frequency modulation signal obtained by the kth decomposition, ω is a frequency parameter, ζ is a balance parameter,as a wiener filtering result of the current margin of saddle points of the modal component after Fourier transformation, ++>Frequency domain values after fourier transformation after saddle points are found for the time series of modal components, +.>Saddle point is calculated for the original input signal and then the frequency domain value is subjected to Fourier transform for the 1 st time, ++>Saddle-point-determined frequency domain value after kth Fourier transform for original input signal, ++>For the filter, gamma is Lagrange multiplier, k is the total number of modes, infinity is the value added by iterative optimization, and +_>For the frequency response of the ith filter, < +.>Frequency response of the original signal after fourier transformation, < >>Is the frequency response of the lagrangian multiplier.
4. The method for detecting a battery cell failure of an energy storage system according to claim 1, wherein the adjusting model parameters specifically include:
setting the input in the pre-constructed successive variation modal model as a single voltage sequence of a battery, setting a raw data compact index as a preset index value, setting Gaussian noise as 0, setting a converged standard tolerance as a preset tolerance value, and setting a stop type as 1.
5. The method for detecting a single battery fault of an energy storage system according to claim 1, wherein the method is characterized in that based on the selected outlier threshold, each maximum voltage dynamic fluctuation component is subjected to box line graph local outlier detection to obtain an abnormal single battery detection result, and specifically comprises the following steps:
obtaining a maximum dynamic voltage fluctuation component matrix according to each maximum voltage dynamic fluctuation component;
calculating a mean matrix and a standard deviation matrix based on the selected second sliding window and the maximum dynamic voltage fluctuation component matrix;
according to the mean matrix and the standard deviation matrix, selecting the outlier threshold to obtain outliers, wherein the formula is as follows:
ο＝(U＞μ+W*σ)|(U＜μ-W*σ)
wherein o is the outlier, W is the outlier threshold, μ is the mean matrix, σ is the standard deviation matrix, and U is the maximum dynamic voltage fluctuation component matrix;
and drawing the outlier and a box line graph, and judging abnormal data based on the box line graph to obtain the abnormal single battery cell detection result.
6. The method for detecting a single battery fault of an energy storage system according to claim 1, wherein the internal fault diagnosis of the battery is performed on each voltage dynamic fluctuation component according to the selected first sliding window and a preset slope condition, so as to obtain a single battery internal fault detection result, specifically:
carrying out dimensionless treatment on each voltage dynamic fluctuation component to obtain the absolute value of each voltage mean value difference value;
sliding based on the selected first sliding window according to the absolute value of the voltage mean value difference value, calculating a kurtosis factor, and calculating the slope between the highest peak value and the lowest peak value in the current window to obtain the slope of the current window;
if the slope of the current window meets the first slope condition, judging that the current battery cell is an internal short circuit fault; the first slope condition specifically includes:
fault1＝k c ＜0|((k c ≤0)&(0≤k n ＜1))
wherein k is c K is the slope of the current window n For the slope of the next window, fault1 is the internal short circuit fault;
if the slope of the current window meets a second slope condition, judging that the current battery cell is an open circuit fault; wherein, the second slope condition specifically is:
fault2＝(0≤k c ＜1)|((0≤k c ＜1)&k n ＜0)
wherein fault2 is the open circuit fault;
and counting the battery cells which are judged to correspond to the internal short circuit fault and the open circuit fault, and obtaining the internal fault detection result of the battery cells.
7. The method for detecting a cell failure of an energy storage system according to claim 6, further comprising, before counting cells determined to correspond to the internal short circuit failure and the open circuit failure, obtaining a result of detecting an internal failure of the cell:
and when the sliding of the selected first sliding window is finished, counting the occurrence times of short-circuit faults and open-circuit faults meeting the preset slope conditions, selecting a sliding total window with the upper threshold value limit of fault processing, calculating the slope of the window based on the sliding total window, and judging the internal short-circuit faults and the open-circuit faults of the corresponding battery cells according to the preset slope conditions and the slope of the window.
8. A battery cell fault detection device of an energy storage system, comprising: the system comprises a data acquisition module, a data preprocessing module, a modal decomposition module, an abnormal battery monomer detection module and a battery internal fault diagnosis module;
the data acquisition module is used for acquiring data of thermal runaway of each battery monomer in the energy storage system under the operating condition to obtain full life cycle data;
the data preprocessing module is used for preprocessing the full life cycle data in a cleaning state to obtain a plurality of charge and discharge fragment data;
the modal decomposition module is used for carrying out successive variation modal decomposition on the charge and discharge fragment data by adjusting model parameters based on a successive variation modal model constructed in advance to obtain a maximum voltage dynamic fluctuation component and a voltage dynamic fluctuation component corresponding to the charge and discharge fragment data;
the abnormal battery cell detection module is used for carrying out local outlier detection on each maximum voltage dynamic fluctuation component based on the selected outlier threshold value to obtain an abnormal battery cell detection result;
the battery internal fault diagnosis module is used for carrying out battery internal fault diagnosis on each voltage dynamic fluctuation component according to the selected first sliding window and a preset slope condition, and obtaining a battery single internal fault detection result.
9. A computer device comprising a processor and a memory for storing a computer program which when executed by the processor implements the method of cell failure detection for an energy storage system according to any one of claims 1 to 7.
10. A computer readable storage medium, characterized in that it stores a computer program, which when executed by a processor implements the battery cell failure detection method of the energy storage system according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311832549.2A CN117554844A (en) | 2023-12-27 | 2023-12-27 | Battery monomer fault detection method and device of energy storage system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311832549.2A CN117554844A (en) | 2023-12-27 | 2023-12-27 | Battery monomer fault detection method and device of energy storage system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117554844A true CN117554844A (en) | 2024-02-13 |
Family
ID=89818639
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311832549.2A Pending CN117554844A (en) | 2023-12-27 | 2023-12-27 | Battery monomer fault detection method and device of energy storage system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117554844A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117741456A (en) * | 2024-02-20 | 2024-03-22 | 云储新能源科技有限公司 | Dynamic reconfigurable battery network fault diagnosis method, system and electronic equipment |
-
2023
- 2023-12-27 CN CN202311832549.2A patent/CN117554844A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117741456A (en) * | 2024-02-20 | 2024-03-22 | 云储新能源科技有限公司 | Dynamic reconfigurable battery network fault diagnosis method, system and electronic equipment |
| CN117741456B (en) * | 2024-02-20 | 2024-05-07 | 云储新能源科技有限公司 | Dynamic reconfigurable battery network fault diagnosis method, system and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107957562B (en) | Online prediction method for residual life of lithium ion battery | |
| CN108254696B (en) | Battery health state evaluation method and system | |
| JP5944291B2 (en) | Battery parameter estimation apparatus and method | |
| CN111426955B (en) | Lithium ion battery fault diagnosis method | |
| CN111965547B (en) | Battery system sensor fault diagnosis method based on parameter identification method | |
| CN112415414A (en) | Method for predicting remaining service life of lithium ion battery | |
| CN117554844A (en) | Battery monomer fault detection method and device of energy storage system | |
| CN111257753B (en) | Battery system fault diagnosis method | |
| CN113238157B (en) | Method for screening through AI detection on retired batteries of electric vehicles | |
| CN113459894B (en) | Electric automobile battery safety early warning method and system | |
| CN112686380A (en) | Neural network-based echelon power cell consistency evaluation method and system | |
| CN113093020A (en) | Method for predicting remaining service life of lithium ion battery based on LSTM neural network | |
| CN110850322B (en) | Method for estimating relative state of health of battery based on wavelet signal decomposition | |
| CN113406520A (en) | Battery health state estimation method for real new energy automobile | |
| CN113484771A (en) | Method for estimating wide-temperature full-life SOC and capacity of lithium ion battery | |
| CN115219905A (en) | On-line detection method and device for short circuit in battery and storage medium | |
| CN113791351B (en) | Lithium battery life prediction method based on transfer learning and difference probability distribution | |
| CN115219918A (en) | Lithium ion battery life prediction method based on capacity decline combined model | |
| CN116298936A (en) | Intelligent lithium ion battery health state prediction method in incomplete voltage range | |
| CN114720881A (en) | Lithium battery parameter identification method based on improved initial value forgetting factor recursive least square method | |
| CN113391214A (en) | Battery micro-fault diagnosis method based on battery charging voltage ranking change | |
| CN116679213A (en) | SOH estimation method for electric vehicle power battery based on integrated deep learning | |
| CN111965548A (en) | Battery system sensor fault diagnosis method based on state estimation method | |
| CN115097344A (en) | Battery health state terminal cloud collaborative estimation method based on constant voltage charging segments | |
| CN115469226A (en) | Real-time safety early warning method for electric vehicle power battery based on operation big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |