A Power System Fault Alarm Processing Method Based on ANN and FSM

摘要

Combined with Artificial Neural Network (ANN) and Finite State Machine (FSM), the substation alarm data is processed. Firstly, to reduce the complexity of ANN model construction, the alarm sequence is simplified by the signal processing method of homology and complementary events merging. Secondly, the ANN weight matrix model and learning algorithm are constructed, and the logic reasoning and knowledge expression of system fault and abnormalities of four types of circuit breaker, line, bus and transformer, are acquired by training and testing data samples. Thirdly, carry out correlation analysis of fault set and build FSM model for alarm process recording, and finally form comprehensive analysis results. The results show that the method has the characteristics of fast, fault tolerance and strong learning ability, and it is of great significance to solve the online fault diagnosis problem of large-scale power system.