基于小波阈值去噪与t-SNE的船舶柴油机故障识别

Fault identification of marine diesel engine based on wavelet threshold denoising and t-SNE

通过对船舶柴油机振动信号的分析研究,文章提出一种基于小波阈值去噪和t分布随机邻域嵌入算法(t-SNE)结合的船舶柴油机故障识别方法。首先通过多种不同的阈值处理方式对采集的振动信号进行小波阈值去噪,使用小波能量谱对数据进行特征提取,并利用t-SNE对高维特征向量降维,最后使用GA-SVM进行故障分类。实验结果证明,文章提出的方法能够较正确地对柴油机的故障模式做出诊断。

Through the analysis and research on the vibration signal of marine diesel engine,this article proposes a marine diesel engine fault identification method based on the wavelet threshold denoising and t-distributed stochastic neighborhood embedding algorithm(t-SNE).First,perform wavelet threshold denoising on the collected vibration signals through a variety of different threshold processing methods,use wavelet energy spectrum to extract features of the data,and use t-SNE to reduce the dimension of high-dimensional feature vectors,and finally use GA-SVM to troubleshoot classification.The experimental results prove that the method proposed in the article can more accurately diagnose the failure mode of diesel engines.