A new hyper-parameter optimization method for machine learning in fault classification

被引：0
作者：
Xingchen Ye
Liang Gao
Xinyu Li
Long Wen
机构：
[1] Huazhong University of Science and Technology,The State Key Laboratory of Digital Manufacturing Equipment & Technology
[2] China University of Geosciences,School of Mechanical Engineering and Electronic Information
来源：
Applied Intelligence | 2023年 / 53卷
关键词：
Hyper-parameter optimization; Fault classification; Dimension reduction; Partial dependencies;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Accurate bearing fault classification is essential for the safe and stable operation of rotating machinery. The success of Machine Learning (ML) in fault classification is mainly dependent on efficient features and the optimal pre-defined hyper-parameters. Various hyper-parameter optimization (HPO) methods have been proposed to tune the ML algorithms’ hyper-parameters in low dimensions but ignore the hyper-parameters of Feature Engineering (FE). The hyper-parameter dimension is high because both FE and the ML algorithm contain many hyper-parameters. This paper proposed a new HPO method for high dimensions based on dimension reduction and partial dependencies. Firstly, the whole hyper-parameter space is separated into two subspaces of FE and the ML algorithm to reduce time consumption. Secondly, the sensitive intervals of hyperparameters can be recognized by partial dependencies due to the nonlinearity of the relationship between the hyperparameters. Then HPO is conducted in intervals to acquire more satisfactory accuracy. The proposed method is verified on three OpenML datasets and the CWRU bearing dataset. The results show that it can automatically construct efficient domain features and outperforms traditional HPO methods and famous ML algorithms. The proposed method is also very time efficient.
引用
收藏
页码：14182 / 14200
页数：18
相关论文
共 147 条
[11]  
Bie R(2014)Wavelet leaders multifractal features based fault diagnosis of rotating mechanism Mech Syst Signal Process 43 57-314
[12]  
Yu J(2021)Design of fault diagnosis algorithm for electric fan based on LSSVM and Kd-tree Appl Intell 51 804-41
[13]  
Gao Y(2019)A sparse stacked denoising autoencoder with optimized transfer learning applied to the fault classification of rolling bearings Measurement 146 305-6770
[14]  
Shen Y(2019)Bearing fault diagnosis method based on deep convolutional neural network and random forest ensemble learning Sensors 19 1088-297
[15]  
Kos A(2020)A high-speed D-CART online fault diagnosis algorithm for rotor systems Appl Intell 50 29-6
[16]  
Wang Z(2021)Feature selection and hyper parameters optimization for short-term wind power forecast App Intell: 1-19 51 6752-34
[17]  
Huang H(2019)Hyper-parameter optimization using mars surrogate for machine-learning algorithms IEEE Transac Emerging Top Computa Intell 4 287-4761
[18]  
Wang Y(2021)Cross-domain fault diagnosis of rolling bearing using similar features-based transfer approach Measurement 172 108900-1446
[19]  
Zhang X(2018)Differential evolution optimization for resilient stacked sparse autoencoder and its applications on bearing fault diagnosis Meas Sci Technol 29 125002-477
[20]  
Zhang Q(2020)Disease prediction via Bayesian hyper-parameter optimization and ensemble learning BMC Research Notes 13 1-134
12345678910