State Evaluation of GIS Equipment Based on Multi-sensor Information Fusion (Poster)

Due to the uncertainty and fuzziness of gas insulated switchgear (GIS) equipment faults, the accuracy and the anti-interference of GIS equipment state evaluation by using a single sensor is normally low. In order to solve that problem, a new multi-sensor information fusion method based on fuzzy theory and Dempster-Shafer (D-S) evidence theory is proposed in this paper. Temperature rise, partial discharge and internal relative humidity are selected as the basis information for fusion. The fuzzy membership degrees of each basis information are calculated by the designed fuzzy membership functions and the idea of weighted sensor reliability degrees are introduced. Then, the reliability degrees and the membership degrees of each measurement are converted into basic probability assignment functions (mass functions). Finally, the information of multiple measurements in a cycle is fused by D-S evidence theory for the evaluation result. Experimental results show that this method can improve the accuracy and anti-interference ability of the GIS equipment state evaluation, and the performance of this method is better than other similar methods.