基于组合预测模型的小样本轴承故障分类诊断

Small sample bearing fault diagnosis based on combined prediction model

滚动轴承是旋转机械内常出现问题的重要部件,其故障情况复杂且难以诊断。基于小样本故障数据学习环境,针对小样本学习在提取真实特征值与目标特征值时有较大差异且泛化能力较弱的问题,提出一种采用半监督变分自编码器与LightGBM分类模型相结合的小样本学习模型LSVAE,并利用基于高斯过程的贝叶斯优化改进算法对LightGBM的超参数进行了优化处理,有效地解决了小样本学习性能不稳定,提取特征能力弱,过拟合等问题,并在凯斯西储大学发布的轴承实验数据集上进行了对比实验,结果表明LSVAE模型在面向小样本数据空间时有着更优的诊断准确率。

Rolling bearings are an important part of problems that often occur in rotating machinery.Their fault conditions are complex and difficult to diagnose.Aiming at the problem that small sample learning has a large difference between the true feature value and the target feature value and the gene-ralization ability is weak,this paper proposes a small sample learning model that combines semi-supervised variational autoencoder and LightGBM classification model.The Bayesian optimization and improvement algorithm based on Gaussian process is used to optimize the LightGBM hyperparameters,thus effectively solving the defects such as unstable performance,weak ability of extracting features,and overfitting in small sample learning.Comparative verification on the bearing experimental data set released by the Western Reserve University in the United States shows that the method has better diagnostic accuracy when facing small sample data space.