Abstract
For the consistency screening of lithium-ion batteries, the multi-parameter screening method is widely used due to its high accuracy. Clustering algorithms are commonly adopted in the screening process. In practice, it is usually necessary to screen a group of cells with high similarity of characteristic parameter and a specific number of cells from a batch of cells, which cannot be achieved by traditional clustering algorithms. Based on this, this paper proposes an improved fuzzy C-means (FCM) algorithm to achieve consistency screening. Principal component analysis is used to reduce the dimensionality of characteristic parameter of sample. Then the K-means algorithm is used to optimize the initial cluster center of the FCM algorithm. Finally, the membership matrix is processed. A specific number of samples with higher membership degrees are selected as the screening result to achieve the “more select less” function. The results show that compared with the traditional FCM algorithm, the improved algorithm can screen out cells with higher similarity of characteristic parameter and a specific number of cells, indicating that the screening effect is good.KeywordsMulti-parameter screeningFCM algorithmPrincipal component analysisInitial cluster centerMembership matrix
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have