基于支持向量机的航空发动机整机振动故障诊断技术研究

支持向量机是采用结构风险最小化原则代替传统统计学中的基于大样本的经验风险最小化原则的一种新型机器学习方法,由于它出色的学习分类能力和推广能力,广泛地应用于模式识别和函数拟合中。针对某型航空发动机整机振动过大的现象,提出了一种基于支持向量机（SVM）的整机振动故障诊断方法。首先介绍了SVM理论,然后根据SVM学习方法的结构风险最小化原则,对某型航空发动机已知的整机振动故障模式数据进行了训练和预测,并建立了基于SVM的航空发动机整机振动故障诊断模型。最后通过对已有故障模式进行诊断预测,证明该方法在航空发动机整机振动故障诊断方面具有良好效果。

Fault diagnosis research on aero-engine whole-body vibration based on support vector machine

Support vector machine（SVM） is a kind of new machine learning method which use structural risk minimization method instead of traditional empirical risk minimization based on large sample.SVM is widely used in pattern recognition and function fitting because of its excellent ability of learning,classification and generalization.A fault diagnosis method based on SVM is proposed in this paper concerning on the excessive whole-body vibration problem of a certain type aero-engine.At first,the theory of SVM is introduced,and then whole-body vibration data of a certain aero-engine fault mode are trained and predicted according to structural risk minimization,a whole-body vibration fault diagnosis model based on SVM is established.Finally,the validity of this method on fault diagnosis of aero-engine whole-body is proved to be effective by exist fault modes diagnosis results.