METHOD AND APPARATUS FOR IDENTIFYING ABNORMAL BATTERY CELL, ELECTRONIC DEVICE, AND STORAGE MEDIUM
A method and apparatus for identifying abnormal battery cell, an electronic device, and a storage medium are provided. The method includes determining, based on target feature data of a battery cell, whether the battery cell has experienced abnormal polarization; where the target feature data includes feature data related to polarization of the battery cell generated during a formation process. On the one hand, as there is a clear distinction in target feature data between a battery cell with abnormal polarization and a battery cell without abnormal polarization during a battery cell formation process, accurate determination of whether a battery cell has experienced abnormal polarization can be achieved. On the other hand, the purpose of identifying a battery cell with abnormal polarization before loading can also be achieved, thereby reducing the risk of decreased battery system performance and battery pack scrapping caused by loading abnormal battery cells.
1 . A method for identifying abnormal battery cell, characterized by comprising:
determining, based on target feature data of a battery cell, whether the battery cell has experienced abnormal polarization; wherein
the target feature data comprises feature data related to polarization of the battery cell generated during a formation process.
2 . The method for identifying abnormal battery cell according to claim 1 , characterized in that the target feature data comprises feature data reflecting a polarization difference of the battery cell collected during the formation process.
3 . The method for identifying abnormal battery cell according to claim 2 , characterized in that the target feature data comprises:
a maximum target parameter value collected in a first stage of the formation process and/or a polarization elimination deviation of a target parameter in the first stage of the formation process.
4 . The method for identifying abnormal battery cell according to claim 2 , characterized in that the target feature data comprises:
a target parameter value collected in a second stage of the formation process.
5 . The method for identifying abnormal battery cell according to claim 4 , characterized in that the target parameter value collected in the second stage of the formation process comprises:
a first target parameter value corresponding to the first arrival of a parameter variation at a first process variation threshold and a second target parameter value corresponding to the first arrival of the parameter variation at a second process variation, during a process of collecting parameters in the second stage; wherein the first process variation and the second process variation are different.
6 . The method for identifying abnormal battery cell according to claim 4 , characterized in that the determining, based on target feature data, whether the battery cell has experienced abnormal polarization comprises:
determining whether the battery cell has experienced abnormal polarization by determining whether there is a target parameter value in the second stage that is greater than a preset target parameter threshold; wherein
under a condition that there is a target parameter value in the second stage that is greater than the preset target parameter threshold, it indicates that the battery cell has experienced abnormal polarization; under a condition that there is no target parameter value in the second stage that is greater than the preset target parameter threshold, it indicates that the battery cell has not experienced abnormal polarization.
7 . The method for identifying abnormal battery cell according to claim 1 , characterized in that the determining, based on target feature data, whether the battery cell has experienced abnormal polarization comprises:
inputting the target feature data into a preset identification model to obtain an identification result of whether the battery cell has experienced abnormal polarization.
8 . The method for identifying abnormal battery cell according to claim 6 , characterized in that the identification model is a two-dimensional Gaussian model; and
the determining, based on target feature data, whether the battery cell has experienced abnormal polarization comprises:
inputting the target feature data into the two-dimensional Gaussian model to obtain a probability density of the battery cell calculated by the two-dimensional Gaussian model; and
under a condition that the probability density of the battery cell is less than a preset probability density threshold, determining that the battery cell has experienced abnormal polarization.
9 . The method for identifying abnormal battery cell according to claim 1 , characterized in that the determining, based on target feature data of a battery cell, whether the battery cell has experienced abnormal polarization comprises:
determining, during the formation process of the battery cell based on the target feature data of the battery cell, whether the battery cell has experienced abnormal polarization.
10 . An apparatus for identifying abnormal battery cell, characterized by comprising
an identification module for determining, based on target feature data of a battery cell, whether the battery cell has experienced abnormal polarization; wherein
the target feature data comprises feature data related to polarization of the battery cell generated during a formation process.
11 . An electronic device, characterized by comprising a processor and a memory; wherein
the processor is configured to execute one or more instructions stored in the memory to implement the method for identifying abnormal battery cell according to claim 1 .
12 . A computer-readable storage medium characterized in that the computer-readable storage medium stores one or more instructions, the instructions being executable by the processor to implement the method for identifying abnormal battery cell according to claim 1 .