New energy automobile power battery system insulation abnormity detection method

The invention relates to the technical field of power batteries, in particular to a new energy automobile power battery system insulation anomaly detection method, which comprises the following steps: acquiring an original message, analyzing, extracting battery signal data, and performing data cleaning and normalization processing; feature selection is carried out on the battery signal data, and insulation resistance, voltage, current and temperature related to the insulation state are selected as feature data; solving first k modes of insulation resistance, voltage, current and temperature as initial values; classifying the feature data based on a k-means clustering algorithm to obtain k types of classification features; using the contour coefficient to evaluate the clustering effect of the clustering results obtained by different k; the k with the best clustering effect is selected, and the abnormal degrees of different categories are analyzed; and according to the difference of different k types of classif