基于随机森林算法的航空发动机振动趋势预测

提出了基于随机森林算法的航空发动机振动趋势预测模型。阐述了随机森林算法的基本理论和计算步骤,采用C-C法计算了延迟时间和嵌入维数,对一维时间序列进行了相空间重构,并在此基础上建立了随机森林算法的预测模型。应用发动机振动试验数据进行了振动预测,并与利用相同训练数据建立的支持向量机预测模型的预测结果进行对比。结果表明,与支持向量机模型相比,随机森林算法预测模型的预测精度更高,泛化能力更强,操作方便,且计算效率更高。

Aero-engine vibration trend prediction based on random forest algorithm

A random forest model was proposed for aero-engine vibration prediction.Firstly,the basic prin?ciples and the process of random forest algorithm was introduced,and then C-C method was applied to cal?culate the delay time and embedding dimension,the time series was rebuilt by phase space reconstruction.Finally,the random forest prediction model was established,and used to forecast aero-engine vibration by applying test data.Based on the same data,the prediction results were compared with that of support vector machine.The results indicate that the random forest model has higher precision and better generalization.Compared with support vector machine prediction model,the random forest prediction model is much easier to operate,and has higher computational efficiency.