Feature time series clustering for lithium battery based on SOM neural network

In this paper, we propose a method to construct eigenvectors based on global feature extraction and cluster analysis. Mainly for the k-means algorithm and self-organizing neural network has been studied, and the application of the two algorithms in battery grouping. At present, the main clustering algorithms include k-means clustering method, hierarchical clustering algorithm based on hierarchical method, neural network clustering algorithm based on model method and FCM algorithm based on fuzzy clustering. As the most classical clustering algorithm, k-means algorithm is widely used in clustering large-scale data because of its high efficiency. With the rapid development of artificial neural network, the application of artificial neural network is more and more widely. The self-organizing neural network in neural network is widely used in the fields of data analysis, classification clustering, pattern recognition and signal processing.