基于改进GEP的航空器故障数据挖掘研究与仿真

Simulation of Aircraft Fault Data Mining Algorithm Based on Mew GEP

航空器故障数据特征具有纬度高、冗余量大的特点,故障特征信号在向量空间中会呈现较大的波动性,导致形成的故障数据无法与故障特征形成稳定的关联性。传统的算法无法在数据形成混乱关联的情况下,挖掘故障特征,导致航空器的安全难以保证。为解决上述问题,提出改进GEP算法的航空器故障数据挖掘方法。利用锦标赛选择法对选择算子进行了改进;利用个体的适应度方差对适应度函数进行了改进,用来衡量种群的多样性;对变异算子进行了改进,使得改进后的变异率能够根据种群的多样性、迭代进化次数和个体的适应度值进行自适应改变,从而使种群的多样性得到保持,提高故障挖掘的准确性。仿真结果结果表明利用改进算法进行航空器故障数据检测,能够提高挖掘的效率。

A new data mining method of aircraft faults is presented based on the improved GEP algorithm. Tour- nament selection method is used to select improved operator. The fitness function is improved by using the individual fitness variance, which is used to measure the diversity of population. The mutation operator is improved, and the mutation rate can be improved according to the diversity of population, the iteration number and individual fitness value of adaptive evolution change. Then the diversity of population is keeping, and the accuracy of the fault mining is improved. The simulation results show that the improved algorithm can improve the efficiency of mining.