The single-cell voltage inconsistency fault is a typical fault in the power battery system of electric vehicles, which not only significantly degrades the overall performance of the battery pack but also poses a serious threat to vehicle safety. To address this issue, this paper proposes a method for identifying single-cell voltage inconsistency faults in power batteries based on a dynamic HDBSCAN algorithm with joint feature enhancement, utilizing actual operational data from a big data supervision platform of an automotive enterprise. The method fully leverages the advantages of the dynamic HDBSCAN algorithm, such as not requiring a preset number of clusters and its ability to adaptively identify abnormal clusters with multiple density levels. First, to preserve the overall voltage deviation information and enhance the model"s sensitivity to extreme outliers, a joint feature matrix based on Manhattan distance and Chebyshev distance is constructed. Second, to improve the robustness and generalization capability of fault identification, an unsupervised adaptively optimized threshold determination mechanism for the mutual reachability distance is introduced, based on the ROC curve and Youden index. Finally, five faulty vehicles exhibiting "poor cell consistency" and one normal vehicle were randomly selected for analysis. The results indicate that, compared to the existing supervision platform"s detection method based on voltage difference thresholds, the proposed method identifies abnormal cells in the five faulty vehicles 9 days 6 hours 10 minutes, 19 days 20 hours 42 minutes, 12 days 22 hours 57 minutes, 12 days 11 hours 3 minutes, and 18 days 22 hours 35 minutes earlier, respectively. Further comparative experiments with OPTICS and DBSCAN clustering algorithms demonstrate that the proposed clustering algorithm achieves superior performance in terms of fault identification timeliness. Consequently, the method presented in this paper exhibits promising engineering application value in the field of electric vehicle power battery fault diagnosis.