改进人工鱼群优化粗糙集的水电机组故障诊断

Fault Diagnosis of Hydro-turbine Generating Unit using Modified AFSA-based Rough Set Theory

针对水电机组大量的现场监测数据信息,基于传统的人工智能方法对故障信息不能及时有效地分析的问题,提出了一种基于改进人工鱼群优化粗糙集的水电机组故障诊断方法.首先,利用鱼群的寻优聚群行为对连续属性进行离散化,然后采用粗糙集理论对离散化后的决策表进行约简,建立故障诊断规则决策表,再用提取的规则对水电机组故障进行诊断.仿真结果表明:与传统方法相比,该算法能够提高水电机组故障诊断的准确率.

Due to the fact that the traditional artificial intelligence methods cannot effectively and timely a-nalysis or can not be accurately diagnosed or misdiagnosed because of the ill-conditioned problem caused byinefficient discretization approaches, based on a large number of on-site monitoring data, a method basedon rough set theory integrated with improved artificial fish-swarm algorithm （AFSA） was presented in thispaper for fault diagnosis of hydro-turbine generating unit. Firstly, the improved artificial fish-swarm algo-rithm was used to discrete continuous attribute, and then the rough set theory was used to reduce the deci-sion table. Therefore, the rules could be ued to diagnose the faults. The simulation results indicated that themethod increased the diagnosis accuracy.