涡轮泵故障检测的频段能量比SOM算法

Frequency-band-energy-ration-based SOM Algorithm for Turbopump Fault Detection

为了解决缺少故障样本情况下的涡轮泵健康状态判别问题,分析了涡轮泵振动信号的频谱,提取了频段能量比作为其故障检测特征,并讨论了自组织映射的竞争学习原理及聚类结果的U-矩阵表示,提出了一种基于频段能量比的自组织映射故障检测算法,并实现了该算法最佳匹配神经元的选择和权重向量的自适应更新。通过某型液体火箭发动机历史试车数据的验证,结果表明,健康涡轮泵数据利用该算法聚类时仅存在一个类别,相邻神经元距离小于0.1;反之,故障涡轮泵数据利用该算法聚类时明显存在两个或多个类别,且相邻神经元的最大距离大于0.1。因此,基于频段能量比的SOM算法能有效地判别涡轮泵的健康状况。

In order to detect the turbopump fault short of fault samples, the spectrums of turhopump vibration signals were analyzed, and the frequency band energy ratio was selected as the fault feature of those signals. After SOM competitive learning theory and U matrix description of clustering results were discussed, the frequency-band-energy-ratio-based SOM algorithm for turbopump fault detection is presented, and the selection of the best matching unit （BMU） and the adaptive upgrade of their weight vectors are also realized in this algorithm. With a liquid rocket engine （IRE） historical test data, this algorithm is validated. These results show that there is only one class when the algorithm is used to healthy turhopump vibratien data, and the distance between the neighboring neuron is less than 0.1 ; while there are two or more classes when the algorithm is used for faulty turhopump vibration data, and the distance between the neighboring neuron is greater than 0.1. Therefore the algorithm can effectively detect the turbopump fault.