As a key metering device in the smart grid, the clock battery status of smart meters directly affects the operational efficiency and economy of the grid. In response to the limitations of current evaluation methods in feature correlation analysis and model interpretability, this study proposes a knowledge-and-data-driven low battery voltage status prediction method. We systematically dissected the physical mechanisms underlying battery undervoltage faults and constructed a status features knowledge graph comprising 17 state features across four dimensions. By employing Pearson correlation analysis and association rule mining techniques, we achieved a quantitative correlation analysis between multi-source heterogeneous features and battery status. Building on this foundation, we developed an interpretable model framework based on XGBoost-SHAP. Empirical studies utilized a dataset of 939,000 faulty meters recalled by a provincial power company in 2023, with 9.87% of outlier samples eliminated using the Isolation Forest algorithm during preprocessing. Results demonstrate that the proposed model achieved an R2 of 0.851 and a Mean Squared Error (MSE) of 0.0088 on the test set. The prediction performance significantly surpassed that of Random Forest (R2 = 0.692) and MLP+BP neural networks (R2 = 0.583), thereby validating the effectiveness of the approach in combining predictive accuracy with decision transparency.
Liu et al. (Thu,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: