基于对数变换的六相永磁容错电机故障预测研究

Fault Prediction of Six-phase Permanent Magnet Fault Tolerant Motor Based on Logarithmic Transformation

研究电力作动系统用永磁容错电机故障预测问题,有利于准确监控飞行器健康状态,为飞机维修提供决策支持;TS(2*2永磁容错电机特征信号复杂无序,传统灰色模型故障预测精度不高,基于此,提出一种新的故障预测改进方法;TS(2*2首先对原始故障能量特征序列进行对数变换处理,对序列进行一次累加生成,建立GM(1,1)灰色模型,最后将得到的拟合还原成模拟值,得到预测数据;TS(2*2结果表明,故障原始序列经过对数函数变换处理后,预测误差相比于未经处理的基本灰色模型降低了4.63%,预测精度提高到96.5%以上,有效提高了永磁容错电机的故障预测精度。

This paper studies the fault prediction problem of permanent magnet fault-tolerant motor equipped in the electric actuation system,which is conducive to monitor aircraft health status accurately,and provide decision support for aircraft maintenance.For the characteristic signal of permanent magnet fault-tolerant motor system is complex and chaotic,the traditional grey model prediction accuracy is not high.Thus,a new improved forecast method based on grey theory is proposed in the paper.Firstly,we use a logarithmic transformation to deal with the original fault feature sequence,and then to deal with the sequence via accumulation generation of first degree.After establish the GM （1,1） grey model,fitting the data back into analog value,we can get the prediction data.The results show that the original se quence is processed by logarithmic transformation,the prediction accuracy increased to 96.5％ above,the prediction error is reduced by 4.63％ than the primitive sequence basic model,the fault prediction of the behavior is improved effectively.