基于人工神经网络与有限状态机的变电站告警处理系统

结合人工神经网络(Artificial Neural Network,ANN)和有限状态机(Finite State Machine,FSM),对变电站告警信息进行处理。首先构建ANN权矩阵模型和学习算法,通过对历史数据库的学习获取各种事故和异常状态的逻辑推理和知识表达;进一步地,设计FSM模型实现信号的排查和告警过程记录;最后形成告警原因分析和结果处理的综合分析结果。通过实际电网案例对所提算法进行验证,结果证明该方法对于电力系统通用故障告警判断具有快速、容错和学习能力强等特点,对应用于大规模电力系统的在线故障诊断问题的解决具有重要意义。

A Power System Fault Alarm Processing MethodBased on ANN and FSM

Combining artificial neural network(ANN) and finite state machine(FSM),the alarm information of power system is processed.Firstly,ANN is fully utilized to logically infer the static database of alarm information,and the fault hypothesis is put forward.Then,the FSM model is designed to record,to analysis the fault process based on the dynamic alarm information.The simulation results show that the method is fast,fault-tolerant and has strong learning ability for fault alarm judgment of power system,and it is of great significance for solving the problem of on-line fault diagnosis of large-scale power system.