Train axle bearing fault detection using a feature selection scheme based multi-scale morphological filter. (15th February 2018)

• Record Type: Journal Article
• Authors: Li, Yifan; Liang, Xihui; Lin, Jianhui; Chen, Yuejian; Liu, Jianxin
• Is Part Of: Mechanical systems and signal processing. Volume 101(2018)
• Page Start: 435
• Page End: 448
• Publication Date: 2018-02-15
• Subjects: Morphology filter -- Scale -- Feature selection -- Grey relational grade -- Axle bearing -- Railway; Structural dynamics -- Periodicals; Vibration -- Periodicals; Constructions -- Dynamique -- Périodiques; Vibration -- Périodiques; Structural dynamics; Vibration; Periodicals; 621
• DOI: 10.1016/j.ymssp.2017.09.007
• Languages: English
• ISSNs: 0888-3270

Abstract

Highlights: An improved morphological filter is proposed. A feature section scheme is developed using grey relational analysis. The proposed method outperforms two current widely used methods. The proposed method is effective for three types of bearing fault detection. Abstract: This paper presents a novel signal processing scheme, feature selection based multi-scale morphological filter (MMF), for train axle bearing fault detection. In this scheme, more than 30 feature indicators of vibration signals are calculated for axle bearings with different conditions and the features which can reflect fault characteristics more effectively and representatively are selected using the max-relevance and min-redundancy principle. Then, a filtering scale selection approach for MMF based on feature selection and grey relational analysis is proposed. The feature selection based MMF method is tested on diagnosis of artificially created damages of rolling bearings of railway trains. Experimental results show that the proposed method has a superior performance in extracting fault features of defective train axle bearings. In addition, comparisons are performed with the kurtosis criterion based MMF and the spectral kurtosis criterion based MMF. The proposed feature selection based MMF method outperforms these two methods in detection of train axle bearing faults.