Online fault identification of the potential information clustering based on resetting variance kalman filtering

A potential information clustering method based on resetting variance kalman filtering is proposed for online abrupt fault identification. To achieve online fault identification through potential information clustering method, the key is to obtain the accurate structural parameters of the system. Structure parameters are tracked quickly and accurately by resetting variance kalman filter, which varies with the change of the dynamic characteristic of the system in the case of abrupt faults. Resetting variance of the filter also guarantees the robustness and self-adaptability of online identification based on potential information clustering. In this paper, the accuracy and effectiveness of the algorithm are verified through the simulation of online abrupt fault identification of coupled-tank.