CN117648589A - Energy storage battery thermal runaway early warning method, system, electronic equipment and medium - Google Patents
Energy storage battery thermal runaway early warning method, system, electronic equipment and medium Download PDFInfo
- Publication number
- CN117648589A CN117648589A CN202410122784.9A CN202410122784A CN117648589A CN 117648589 A CN117648589 A CN 117648589A CN 202410122784 A CN202410122784 A CN 202410122784A CN 117648589 A CN117648589 A CN 117648589A
- Authority
- CN
- China
- Prior art keywords
- thermal runaway
- energy storage
- coefficient vector
- column
- matrix
- 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.)
- Granted
Links
- 238000004146 energy storage Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 51
- 239000013598 vector Substances 0.000 claims abstract description 67
- 239000011159 matrix material Substances 0.000 claims abstract description 66
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 41
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 32
- 239000000178 monomer Substances 0.000 claims description 19
- 238000010276 construction Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 4
- 238000010248 power generation Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 1
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 229910052744 lithium Inorganic materials 0.000 description 1
- 229910001416 lithium ion Inorganic materials 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Abstract
The invention discloses an energy storage battery thermal runaway early warning method, an energy storage battery thermal runaway early warning system, electronic equipment and a medium, and relates to the field of energy storage of new energy power systems, wherein the method comprises the following steps: acquiring actual operation data of a target energy storage system in a preset time period; constructing a voltage matrix according to actual operation data; decomposing each column of elements of the voltage matrix by applying a signal decomposition algorithm to obtain a plurality of modes after decomposing each column; selecting a preset target mode from a plurality of modes after each column of the voltage matrix is decomposed, and constructing a mode matrix; calculating a correlation coefficient vector and an autocorrelation coefficient vector of each column of elements of the modal matrix; respectively normalizing the correlation coefficient vector and the autocorrelation coefficient vector, and constructing a two-dimensional array; and clustering the two-dimensional data in the two-dimensional array by using a clustering algorithm to obtain an analysis result. The invention ensures the safe and stable operation of the energy storage system.
Description
Technical Field
The invention relates to the field of energy storage of new energy power systems, in particular to an energy storage battery thermal runaway early warning method, an energy storage battery thermal runaway early warning system, electronic equipment and a medium.
Background
With the continuous expansion of the installed scale of new energy power generation, the proportion of new energy power generation in a power grid is higher, but the new energy power generation single machine has the characteristics of small capacity, large quantity, distributed points, obvious intermittence, volatility, randomness and the like, and the high proportion new energy grid connection tends to bring unprecedented challenges to the balance of supply and demand, safety and stability control and the like of a power system. The energy storage system is a key ring for adjusting unbalance between new energy power generation and supply and demand of the power system and energy management and optimization. The core of the energy storage system is formed by connecting a large number of lithium ion batteries through a series-parallel structure, a large amount of heat can be generated in the operation process, and if the thermal runaway cannot be effectively controlled and prevented, serious safety problems such as overheating and burning loss of equipment and even fire disaster can be caused. By establishing a thermal runaway early warning system, potential problems can be detected in advance, measures are taken to prevent safety accidents, and the method has important significance in guaranteeing system safety, improving performance, prolonging equipment service life and reducing operation and equipment replacement cost.
The traditional thermal runaway early warning method for the energy storage system has the following defects: 1. the early warning of the thermal runaway is not timely, and an alarm can not be given in advance for the occurrence of the thermal runaway; 2. the traditional energy storage system thermal runaway early warning method is generally confused with faults such as large pressure difference, inconsistent voltage and the like, and has low prediction accuracy and higher false alarm rate; 3. the traditional energy storage system thermal runaway early warning method only considers time domain characteristics, but does not fully consider frequency domain characteristics, so that partial thermal runaway cannot be early warned in advance.
Disclosure of Invention
Aiming at the thermal runaway risk problem caused by a lithium battery in the operation of an energy storage system, the invention provides an energy storage battery thermal runaway early warning method, an energy storage battery thermal runaway early warning system, electronic equipment and a medium, and the energy storage system is ensured to run safely and stably by monitoring and early warning the thermal runaway risk possibly occurring in the operation process of the energy storage system by utilizing a data driving method.
In order to achieve the above object, the present invention provides the following solutions: an energy storage battery thermal runaway warning method, the warning method comprising: acquiring actual operation data of a target energy storage system in a preset time period; the length of the actual operation data in the preset time period is a preset length; the number of the battery modules in the target energy storage system is a first preset number; the number of the battery monomers in the battery module is a second preset number.
Constructing a voltage matrix according to the actual operation data; the elements of each row of the voltage matrix are the voltage values of all battery monomers at the same moment; the elements of each column of the voltage matrix are the voltage values of the same battery cell at different moments; the positions of the columns in the voltage matrix are determined according to the time sequence.
And decomposing each column of elements of the voltage matrix by applying a signal decomposition algorithm to obtain a plurality of modes after each column is decomposed.
And selecting a preset target mode from the modes after each column of the voltage matrix is decomposed, and constructing a mode matrix.
A correlation coefficient vector and an autocorrelation coefficient vector are calculated for each column of elements of the modal matrix.
Respectively normalizing the correlation coefficient vector and the autocorrelation coefficient vector, and constructing a two-dimensional array according to the normalized correlation coefficient vector and the corresponding normalized autocorrelation coefficient vector; the two-dimensional array comprises a plurality of two-dimensional data; the two-dimensional data includes normalized correlation coefficient vectors and corresponding normalized autocorrelation coefficient vectors.
Clustering the two-dimensional data in the two-dimensional array by using a clustering algorithm to obtain an analysis result; the analysis results show that the battery cell has a thermal runaway risk and the battery cell does not have a thermal runaway risk.
Optionally, the signal decomposition algorithm is a variation modal decomposition algorithm.
Optionally, a maximum-minimum normalization method is applied to normalize the correlation coefficient vector and the autocorrelation coefficient vector, respectively.
Optionally, the clustering algorithm is a DBSCAN algorithm.
Optionally, constructing a voltage matrix according to the actual operation data specifically includes: and sequencing the actual operation data according to a time sequence to obtain a sequenced data sequence.
Preprocessing the ordered data sequence to obtain a preprocessed data sequence; the preprocessing comprises deleting repeated numerical values and interpolating positions corresponding to the deleted repeated numerical values.
And traversing the preprocessed data sequence by using a sliding window to obtain a voltage matrix.
Optionally, clustering the two-dimensional data in the two-dimensional array by using a clustering algorithm to obtain an analysis result, which specifically includes: and clustering the two-dimensional data in the two-dimensional array by using a clustering algorithm to obtain a clustering result.
And judging whether the two-dimensional data which are not classified exist in the clustering result.
And when the two-dimensional data which are not classified exist in the clustering result, the analysis result shows that the battery cell has a thermal runaway risk.
And when the two-dimensional data which are not classified does not exist in the clustering result, the analysis result shows that the battery cell is free from thermal runaway risk.
Optionally, the early warning method further includes: and when the analysis result shows that the battery cell has the thermal runaway risk, determining the battery cell having the thermal runaway risk according to the battery cell corresponding to the unclassified two-dimensional data.
The energy storage battery thermal runaway early warning system comprises an acquisition module, a first construction module, a decomposition module, a second construction module, a calculation module, a third construction module and a clustering module.
The acquisition module is used for acquiring actual operation data of the target energy storage system in a preset time period; the length of the actual operation data in the preset time period is a preset length; the number of the battery modules in the target energy storage system is a first preset number; the number of the battery monomers in the battery module is a second preset number.
The first construction module is used for constructing a voltage matrix according to the actual operation data; the elements of each row of the voltage matrix are the voltage values of all battery monomers at the same moment; the elements of each column of the voltage matrix are the voltage values of the same battery cell at different moments; the positions of the columns in the voltage matrix are determined according to the time sequence.
And the decomposition module is used for decomposing each column of elements of the voltage matrix by applying a signal decomposition algorithm to obtain a plurality of modes after each column is decomposed.
The second construction module is used for selecting a preset target mode from the modes after each column of the voltage matrix is decomposed and constructing a mode matrix.
And the calculating module is used for calculating the correlation coefficient vector and the autocorrelation coefficient vector of each column of elements of the modal matrix.
The third construction module is used for respectively normalizing the correlation coefficient vector and the autocorrelation coefficient vector and constructing a two-dimensional array according to the normalized correlation coefficient vector and the corresponding normalized autocorrelation coefficient vector; the two-dimensional array comprises a plurality of two-dimensional data; the two-dimensional data includes normalized correlation coefficient vectors and corresponding normalized autocorrelation coefficient vectors.
The clustering module is used for clustering the two-dimensional data in the two-dimensional array by applying a clustering algorithm to obtain an analysis result; the analysis results show that the battery cell has a thermal runaway risk and the battery cell does not have a thermal runaway risk.
An electronic device comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor runs the computer program to enable the electronic device to execute the energy storage battery thermal runaway early warning method.
A computer readable storage medium storing a computer program which when executed by a processor implements the energy storage battery thermal runaway warning method described above.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects: according to the method, the actual operation data of the target energy storage system in a preset time period are obtained, a voltage matrix is constructed according to the actual operation data, and a signal decomposition algorithm is applied to decompose each column element of the voltage matrix to obtain a plurality of modes after decomposition of each column; then selecting a preset target mode from a plurality of modes after each column of the voltage matrix is decomposed, constructing a mode matrix, calculating a correlation coefficient vector and an autocorrelation coefficient vector of each column element of the mode matrix, respectively normalizing the correlation coefficient vector and the autocorrelation coefficient vector, and constructing a two-dimensional array; and finally, clustering the two-dimensional data in the two-dimensional array by using a clustering algorithm to obtain an analysis result. The invention utilizes a data driving method to monitor and early warn the thermal runaway risk possibly occurring in the operation process of the energy storage system, and ensures the safe and stable operation of the energy storage system.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of the energy storage battery thermal runaway early warning method in practical application.
FIG. 2 is a schematic diagram of voltage curves of the individual cells of a module of the present invention over a time window.
FIG. 3 is a flow chart of a case of decomposition of a single voltage sequence using variation modes according to the present invention.
FIG. 4 is a schematic diagram of a second mode curve of each cell of a module according to the present invention after decomposing the cell into three modes using a variation mode decomposition method in a time window voltage sequence.
FIG. 5 is a schematic diagram of the DBSCAN cluster recognition thermal runaway risk monomer results of the present invention.
FIG. 6 is a flow chart of a thermal runaway warning method for an energy storage battery according to the present invention.
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.
The invention aims to provide an energy storage battery thermal runaway early warning method, an energy storage battery thermal runaway early warning system, electronic equipment and a medium, which can monitor and early warn the thermal runaway risk possibly occurring in the operation process of an energy storage system by utilizing a data driving method, and ensure the safe and stable operation of the energy storage system.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Embodiment one: as shown in fig. 1 and 6, the invention provides an early warning method for thermal runaway of an energy storage battery, which comprises steps S1 to S7.
Step S1: acquiring actual operation data of a target energy storage system in a preset time period; the length of the actual operation data in the preset time period is a preset length; the number of the battery modules in the target energy storage system is a first preset number; the number of the battery monomers in the battery module is a second preset number.
Step S2: constructing a voltage matrix according to the actual operation data; the elements of each row of the voltage matrix are the voltage values of all battery monomers at the same moment; the elements of each column of the voltage matrix are the voltage values of the same battery cell at different moments; the positions of the columns in the voltage matrix are determined according to the time sequence.
Step S2 specifically includes steps S21 to S23.
Step S21: and sequencing the actual operation data according to a time sequence to obtain a sequenced data sequence.
Step S22: preprocessing the ordered data sequence to obtain a preprocessed data sequence; the preprocessing comprises deleting repeated numerical values and interpolating positions corresponding to the deleted repeated numerical values.
Step S23: and traversing the preprocessed data sequence by using a sliding window to obtain a voltage matrix.
Step S3: and decomposing each column of elements of the voltage matrix by applying a signal decomposition algorithm to obtain a plurality of modes after each column is decomposed.
Specifically, the signal decomposition algorithm is a variation modal decomposition algorithm.
Step S4: and selecting a preset target mode from the modes after each column of the voltage matrix is decomposed, and constructing a mode matrix.
Step S5: a correlation coefficient vector and an autocorrelation coefficient vector are calculated for each column of elements of the modal matrix.
Step S6: respectively normalizing the correlation coefficient vector and the autocorrelation coefficient vector, and constructing a two-dimensional array according to the normalized correlation coefficient vector and the corresponding normalized autocorrelation coefficient vector; the two-dimensional array comprises a plurality of two-dimensional data; the two-dimensional data includes normalized correlation coefficient vectors and corresponding normalized autocorrelation coefficient vectors.
Specifically, the correlation coefficient vector and the autocorrelation coefficient vector are normalized by applying a maximum-minimum normalization method, respectively.
Step S7: clustering the two-dimensional data in the two-dimensional array by using a clustering algorithm to obtain an analysis result; the analysis results show that the battery cell has a thermal runaway risk and the battery cell does not have a thermal runaway risk.
Specifically, the clustering algorithm is a DBSCAN algorithm.
Further, step S7 specifically includes steps S71 to S74.
Step S71: and clustering the two-dimensional data in the two-dimensional array by using a clustering algorithm to obtain a clustering result.
Step S72: and judging whether the two-dimensional data which are not classified exist in the clustering result.
Step S73: and when the two-dimensional data which are not classified exist in the clustering result, the analysis result shows that the battery cell has a thermal runaway risk.
Step S74: and when the two-dimensional data which are not classified does not exist in the clustering result, the analysis result shows that the battery cell is free from thermal runaway risk.
As a specific embodiment, the early warning method further includes: and when the analysis result shows that the battery cell has the thermal runaway risk, determining the battery cell having the thermal runaway risk according to the battery cell corresponding to the unclassified two-dimensional data.
In practical application, the actual operation data of the energy storage system with the length L is obtained, the number of battery modules of the energy storage system is M, and one module comprises the number of battery monomers N.
Step 1: data processing, namely sorting input data according to time fields from small to large, and for repeated values of the time fields, only keeping the row where the first repeated value is located and deleting the rows where other repeated values are located; for the field of recording the cell voltage, the value is converted into a unit of "v", 3-bit decimal is saved, and linear interpolation is performed on null or outliers.
For example, prior to linear interpolation:。
after linear interpolation:。
wherein nan indicates that the position is null.
Step 2: setting window lengthAnd window sliding step +.>Let k=1 denote the current calculation window start line index, and i=1 denote the current calculation module number.
Step 3: if i is larger than M, indicating that all modules of the current window have been traversed, setting k=k+s, updating the starting position of the window, and turning to step 4, otherwise turning to step 5 to continue calculating new modules.
Step 4: if k is more than L, the algorithm ends in step 11, otherwise, i=1 is set, and step 5 starts to traverse the new window from the first module.
Step 5: extracting voltage matrix of module i taking k as window starting position，/>Is->Matrix of N rows, each row represents voltage value of each monomer of module i at one moment, each column is a sequence of voltage values of one monomer in time direction, wherein ∈>Visualization is shown in FIG. 2, each curve and +.>Corresponding to each column of the plurality.
Step 6: as shown in fig. 3 and 4, forMake a variant modal decomposition of +.>Is decomposed into d=3 modalities +.>Combining the d=2nd mode after each column of mode decomposition to form a mode matrixWherein->Is->Column j uses the D-th modality when the variant modality is decomposed into D modalities.
The variation modal decomposition is a self-adaptive and completely non-recursive method for modal variation and signal processing, has the advantage of determining the number of modal decomposition, and is characterized in that the number of modal decomposition of a given sequence is determined according to actual conditions, the optimal center frequency and limited bandwidth of each modal can be adaptively matched in the subsequent searching and solving process, effective separation of inherent modal components, frequency domain division of signals and further obtaining effective decomposition components of given signals can be realized, and finally the optimal solution of the variation problem is obtained.
The core of the variational modal decomposition is to solve the following variational problems:。
。
wherein D is the number of modes to be decomposed,，/>respectively corresponding to d-th modal component and center frequency after decomposition, < ->As a dilichlet function->Is a convolution operator. The variational modal decomposition can be solved by calling the VMD method call parameters in the vmdpy library of Python.
Step 7: calculation ofIs>Wherein->Is a modal matrix->The correlation coefficient in the j-th column is calculated as follows.
。
Wherein,is a modal matrix->Column j, < >>Is->，/>Covariance of->Is->Is a variance of (c).
Step 8: calculation ofIs>Wherein->Is a modal matrix->The autocorrelation coefficient of the j-th column is calculated as follows.
。
Wherein,is a modal matrix->Front ∈of column j>Vectors of individual elements>Is a modal matrix->Post->The vector of elements, p=2, is the time delay parameter for calculating the autocorrelation coefficients.
Step 9:is>And autocorrelation coefficient vector->And (5) performing maximum and minimum value standardization, wherein the calculation formula is as follows.
。
。
Wherein,，/>respectively->Is>And autocorrelation coefficient vector->And (5) carrying out maximum and minimum value normalization on the vector.
Step 10: as shown in FIG. 5, a two-dimensional array is constructed from normalized correlation coefficient vectors and autocorrelation coefficient vectorsWherein->，/>Respectively->，/>Is the j-th element of (2); two-dimensional array +.>And mapping each element in the window into a point on a two-dimensional space, clustering by using a DBSCAN algorithm, judging if an unclassified point exists in a clustering result, outputting window starting time corresponding to k, module number corresponding to i and unclassified point number j, performing risk early warning to indicate that j monomer in the i module in the window corresponding to k has thermal runaway risk, and if the unclassified point does not exist in the clustering result, then the thermal runaway risk does not exist in the corresponding time window and the battery monomer in the module.
The DBSCAN algorithm is a density-based unsupervised clustering algorithm, and the data points are divided into core points, boundary points and abnormal points, so that clusters are identified, isolated points can be detected as anomalies, and the algorithm can be solved by calling a DBSCAN method in a scikit-learn library of Python.
Step 11: setting i=i+1, and turning to step 3.
Step 12: the algorithm ends.
The present invention has the following advantages.
1. A thermal runaway fault early warning method for an energy storage system is provided.
2. Solves the defects that the traditional thermal runaway fault early warning method has poor timeliness and is difficult to find the early manifestation of the thermal runaway fault.
3. The defect that the conventional thermal runaway fault early warning algorithm cannot accurately distinguish the general fault from the thermal runaway fault is overcome, the accuracy of the thermal runaway alarm is improved, and the false alarm rate is reduced.
4. The limitation that the traditional thermal runaway fault early warning algorithm only considers time domain characteristics and does not consider frequency domain characteristics is solved.
Embodiment two: in order to execute the corresponding method of the above embodiment to achieve the corresponding functions and technical effects, the following provides an energy storage battery thermal runaway early warning system, which includes an acquisition module, a first construction module, a decomposition module, a second construction module, a calculation module, a third construction module and a clustering module.
The acquisition module is used for acquiring actual operation data of the target energy storage system in a preset time period; the length of the actual operation data in the preset time period is a preset length; the number of the battery modules in the target energy storage system is a first preset number; the number of the battery monomers in the battery module is a second preset number.
The first construction module is used for constructing a voltage matrix according to the actual operation data; the elements of each row of the voltage matrix are the voltage values of all battery monomers at the same moment; the elements of each column of the voltage matrix are the voltage values of the same battery cell at different moments; the positions of the columns in the voltage matrix are determined according to the time sequence.
And the decomposition module is used for decomposing each column of elements of the voltage matrix by applying a signal decomposition algorithm to obtain a plurality of modes after each column is decomposed.
The second construction module is used for selecting a preset target mode from the modes after each column of the voltage matrix is decomposed and constructing a mode matrix.
And the calculating module is used for calculating the correlation coefficient vector and the autocorrelation coefficient vector of each column of elements of the modal matrix.
The third construction module is used for respectively normalizing the correlation coefficient vector and the autocorrelation coefficient vector and constructing a two-dimensional array according to the normalized correlation coefficient vector and the corresponding normalized autocorrelation coefficient vector; the two-dimensional array comprises a plurality of two-dimensional data; the two-dimensional data includes normalized correlation coefficient vectors and corresponding normalized autocorrelation coefficient vectors.
The clustering module is used for clustering the two-dimensional data in the two-dimensional array by applying a clustering algorithm to obtain an analysis result; the analysis results show that the battery cell has a thermal runaway risk and the battery cell does not have a thermal runaway risk.
Embodiment III: the embodiment of the invention provides an electronic device, which comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor runs the computer program to enable the electronic device to execute the energy storage battery thermal runaway early warning method in the first embodiment.
Alternatively, the electronic device may be a server.
In addition, the embodiment of the invention also provides a computer readable storage medium, which stores a computer program, and the computer program realizes the thermal runaway early warning method of the energy storage battery in the first embodiment when being executed by a processor.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.
Claims (10)
1. The energy storage battery thermal runaway early warning method is characterized by comprising the following steps of:
acquiring actual operation data of a target energy storage system in a preset time period; the length of the actual operation data in the preset time period is a preset length; the number of the battery modules in the target energy storage system is a first preset number; the number of battery monomers in the battery module is a second preset number;
constructing a voltage matrix according to the actual operation data; the elements of each row of the voltage matrix are the voltage values of all battery monomers at the same moment; the elements of each column of the voltage matrix are the voltage values of the same battery cell at different moments; the positions of all columns in the voltage matrix are determined according to the time sequence;
decomposing each column of elements of the voltage matrix by applying a signal decomposition algorithm to obtain a plurality of modes after decomposing each column;
selecting a preset target mode from the modes after each column of the voltage matrix is decomposed, and constructing a mode matrix;
calculating a correlation coefficient vector and an autocorrelation coefficient vector of each column of elements of the modal matrix;
respectively normalizing the correlation coefficient vector and the autocorrelation coefficient vector, and constructing a two-dimensional array according to the normalized correlation coefficient vector and the corresponding normalized autocorrelation coefficient vector; the two-dimensional array comprises a plurality of two-dimensional data; the two-dimensional data comprises normalized correlation coefficient vectors and corresponding normalized autocorrelation coefficient vectors;
clustering the two-dimensional data in the two-dimensional array by using a clustering algorithm to obtain an analysis result; the analysis results show that the battery cell has a thermal runaway risk and the battery cell does not have a thermal runaway risk.
2. The energy storage battery thermal runaway warning method of claim 1, wherein the signal decomposition algorithm is a variation modal decomposition algorithm.
3. The method of claim 1, wherein the correlation coefficient vector and the autocorrelation coefficient vector are normalized by a maximum-minimum normalization method.
4. The energy storage battery thermal runaway warning method of claim 1, wherein the clustering algorithm is a DBSCAN algorithm.
5. The energy storage battery thermal runaway warning method according to claim 1, wherein constructing a voltage matrix according to the actual operation data specifically comprises:
sorting the actual operation data according to a time sequence to obtain a sorted data sequence;
preprocessing the ordered data sequence to obtain a preprocessed data sequence; the preprocessing comprises deleting repeated numerical values and interpolating positions corresponding to the deleted repeated numerical values;
and traversing the preprocessed data sequence by using a sliding window to obtain a voltage matrix.
6. The energy storage battery thermal runaway early warning method according to claim 1, wherein the clustering algorithm is applied to cluster the two-dimensional data in the two-dimensional array to obtain an analysis result, and the method specifically comprises the following steps:
clustering the two-dimensional data in the two-dimensional array by using a clustering algorithm to obtain a clustering result;
judging whether the two-dimensional data which are not classified exist in the clustering result;
when the two-dimensional data which are not classified exist in the clustering result, the analysis result shows that the battery monomer has a thermal runaway risk;
and when the two-dimensional data which are not classified does not exist in the clustering result, the analysis result shows that the battery cell is free from thermal runaway risk.
7. The energy storage battery thermal runaway warning method of claim 6, further comprising:
and when the analysis result shows that the battery cell has the thermal runaway risk, determining the battery cell having the thermal runaway risk according to the battery cell corresponding to the unclassified two-dimensional data.
8. An energy storage battery thermal runaway warning system, characterized in that the warning system comprises:
the acquisition module is used for acquiring actual operation data of the target energy storage system in a preset time period; the length of the actual operation data in the preset time period is a preset length; the number of the battery modules in the target energy storage system is a first preset number; the number of battery monomers in the battery module is a second preset number;
the first construction module is used for constructing a voltage matrix according to the actual operation data; the elements of each row of the voltage matrix are the voltage values of all battery monomers at the same moment; the elements of each column of the voltage matrix are the voltage values of the same battery cell at different moments; the positions of all columns in the voltage matrix are determined according to the time sequence;
the decomposition module is used for decomposing each column of elements of the voltage matrix by applying a signal decomposition algorithm to obtain a plurality of modes after decomposition of each column;
the second construction module is used for selecting a preset target mode from the modes after each column of the voltage matrix is decomposed to construct a mode matrix;
the calculation module is used for calculating a correlation coefficient vector and an autocorrelation coefficient vector of each column of elements of the modal matrix;
the third construction module is used for respectively normalizing the correlation coefficient vector and the autocorrelation coefficient vector and constructing a two-dimensional array according to the normalized correlation coefficient vector and the corresponding normalized autocorrelation coefficient vector; the two-dimensional array comprises a plurality of two-dimensional data; the two-dimensional data comprises normalized correlation coefficient vectors and corresponding normalized autocorrelation coefficient vectors;
the clustering module is used for clustering the two-dimensional data in the two-dimensional array by applying a clustering algorithm to obtain an analysis result; the analysis results show that the battery cell has a thermal runaway risk and the battery cell does not have a thermal runaway risk.
9. An electronic device comprising a memory for storing a computer program and a processor that runs the computer program to cause the electronic device to perform the energy storage battery thermal runaway warning method 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 energy storage battery thermal runaway warning method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410122784.9A CN117648589B (en) | 2024-01-30 | Energy storage battery thermal runaway early warning method, system, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410122784.9A CN117648589B (en) | 2024-01-30 | Energy storage battery thermal runaway early warning method, system, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117648589A true CN117648589A (en) | 2024-03-05 |
| CN117648589B CN117648589B (en) | 2024-05-14 |
Family
ID=
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160149199A1 (en) * | 2014-11-25 | 2016-05-26 | American Lithium Energy Corporation | Rechargeable battery with voltage activated current interrupter |
| CN113569485A (en) * | 2021-07-30 | 2021-10-29 | 湖北工业大学 | Short-time abnormal battery identification method based on variational modal decomposition |
| US20220196720A1 (en) * | 2020-12-18 | 2022-06-23 | Wuhan University | Single-ended fault positioning method and system for high-voltage direct-current transmission line of hybrid network |
| WO2022151819A1 (en) * | 2021-01-18 | 2022-07-21 | 北京理工大学 | Clustering analysis-based battery system online fault diagnosis method and system |
| US20230040212A1 (en) * | 2021-08-03 | 2023-02-09 | GM Global Technology Operations LLC | Thermal runaway detection methods and warning systems |
| CN116192665A (en) * | 2022-12-27 | 2023-05-30 | 中移动信息技术有限公司 | Data processing method, device, computer equipment and storage medium |
| CN116451038A (en) * | 2023-03-27 | 2023-07-18 | 北京航空航天大学 | Power battery thermal runaway early warning method and system based on singular spectrum entropy |
| CN116799921A (en) * | 2023-07-03 | 2023-09-22 | 云储新能源科技有限公司 | Retired battery energy storage system considering risk and optimal scheduling method thereof |
| CN117113232A (en) * | 2023-08-22 | 2023-11-24 | 北京理工大学 | Thermal runaway risk identification method for lithium ion battery pack of electric automobile |
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160149199A1 (en) * | 2014-11-25 | 2016-05-26 | American Lithium Energy Corporation | Rechargeable battery with voltage activated current interrupter |
| US20220196720A1 (en) * | 2020-12-18 | 2022-06-23 | Wuhan University | Single-ended fault positioning method and system for high-voltage direct-current transmission line of hybrid network |
| WO2022151819A1 (en) * | 2021-01-18 | 2022-07-21 | 北京理工大学 | Clustering analysis-based battery system online fault diagnosis method and system |
| CN113569485A (en) * | 2021-07-30 | 2021-10-29 | 湖北工业大学 | Short-time abnormal battery identification method based on variational modal decomposition |
| US20230040212A1 (en) * | 2021-08-03 | 2023-02-09 | GM Global Technology Operations LLC | Thermal runaway detection methods and warning systems |
| CN116192665A (en) * | 2022-12-27 | 2023-05-30 | 中移动信息技术有限公司 | Data processing method, device, computer equipment and storage medium |
| CN116451038A (en) * | 2023-03-27 | 2023-07-18 | 北京航空航天大学 | Power battery thermal runaway early warning method and system based on singular spectrum entropy |
| CN116799921A (en) * | 2023-07-03 | 2023-09-22 | 云储新能源科技有限公司 | Retired battery energy storage system considering risk and optimal scheduling method thereof |
| CN117113232A (en) * | 2023-08-22 | 2023-11-24 | 北京理工大学 | Thermal runaway risk identification method for lithium ion battery pack of electric automobile |
Non-Patent Citations (4)
| Title |
|---|
| FENG YANG: "A fault-response approach for battery pack by reconfigurable topology using agents", 《2016 IEEE 28TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICAL INTELLIGENCE(ICTAI)》, 16 January 2017 (2017-01-16) * |
| MICHAEL SCHMID: "Active Model-Based Fault Diagnosis in Reconfigurable Battery Systems", 《IEEE TRANSACTIONS ON POWER ELECTRONICS》, 31 July 2020 (2020-07-31) * |
| 刘延超: "由VMD与DBSCAN在线检测锂离子电池热失控", 《电池》, 3 January 2023 (2023-01-03) * |
| 张淑清;邢婷婷;何红梅;董玉兰;张立国;姜万录;: "基于VMD及广义分形维数矩阵的滚动轴承故障诊断", 计量学报, no. 04, 22 July 2017 (2017-07-22) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022151819A1 (en) | Clustering analysis-based battery system online fault diagnosis method and system | |
| Li et al. | Fault diagnosis for lithium-ion batteries in electric vehicles based on signal decomposition and two-dimensional feature clustering | |
| CN110927606B (en) | Battery state monitoring method and device | |
| CN116154900B (en) | Active safety three-stage prevention and control system and method for battery energy storage power station | |
| CN114487856A (en) | Thermal runaway early warning method and system for battery replacement station | |
| CN112307623A (en) | Battery cell thermal runaway prediction method and device, medium, battery management system and vehicle | |
| CN109737045A (en) | Air compressor machine fault early warning method, system and relevant apparatus applied to chip production | |
| He et al. | Voltage abnormality-based fault diagnosis for batteries in electric buses with a self-adapting update model | |
| Li et al. | A novel method for lithium-ion battery fault diagnosis of electric vehicle based on real-time voltage | |
| CN117648589B (en) | Energy storage battery thermal runaway early warning method, system, electronic equipment and medium | |
| CN113487086A (en) | Method and device for predicting remaining service life of equipment, computer equipment and medium | |
| CN117318249A (en) | Battery charging cloud monitoring method and system | |
| CN117648589A (en) | Energy storage battery thermal runaway early warning method, system, electronic equipment and medium | |
| CN117169761A (en) | Battery state evaluation method, apparatus, device, storage medium, and program product | |
| CN116482540A (en) | Analysis and prediction method, device and system for battery voltage inconsistency | |
| Wang et al. | An inconsistency fault diagnosis method for lithium-ion cells in the battery pack based on piecewise dimensionality reduction and outlier identification | |
| CN116893366A (en) | Method and device for operating a system to detect anomalies in an electrical energy store of a device | |
| CN115508713A (en) | Battery system safety early warning method and device, storage medium and equipment | |
| CN115980585A (en) | Battery fault detection method and device, computer equipment and storage medium | |
| CN114839554A (en) | Battery alarm method and device, electronic equipment and storage medium | |
| CN113935423A (en) | Power battery fault early warning method and system for coupling fuzzy control rule with Elman neural network | |
| CN116047313B (en) | Quality detection and maintenance method and system for lithium battery energy storage box | |
| CN115829543B (en) | Method for determining validity of preventive test of power equipment based on fault detection interval | |
| CN116593905B (en) | Battery power state SOP calculation method, apparatus, electronic device and storage medium | |
| CN115825790B (en) | Early warning method, device and system for battery insulation fault and computer equipment |
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 |