Multidimensional denoising of rotating machine based on tensor factorization

• Published in: Mechanical systems and signal processing 2019-05, Vol.122, p.273-289
• Main Authors: Hu, Chaofan, Wang, Yanxue
• Format: Article
• Language: English
• Subjects: Computer simulation; Data management; Factorization; Fault detection; Fault diagnosis; Filtration; High-order singular value decomposition; Multidimensional denoising; Noise reduction; Rotating machinery; Rotating machines; Rotation; Singular value decomposition; Tensor factorization; Tensors
• ISSN: 0888-3270; 1096-1216
• DOI: 10.1016/j.ymssp.2018.12.012

•A multidimensional denoising technique of rotating machinery is developed based on tensor factorization.•L-curve criterion is adopted to find the truncation parameters used in high order singular value decomposition.•Heterogeneous and multiaspect data is processed in the high dimensional space. A multidimensional de-noising technique of rotating machinery based on the tensor factorization is developed for solving multidimensional signal filtering. The vibration signal is first formulated as a 3-way tensor using temporal signal, frequency and channel information. Tensor model is then factorized via the truncated high-order singular value decomposition. The L-curve criterion is adopted to determine the truncation parameters used in the tensor factorization. The performance of the developed technique in detecting faults of rotating machinery has been thoroughly evaluated through simulated signals compared with three traditional techniques. The presented approach is then applied to reduce noise in vibration signal collected on bearing and gear test-rigs. Experimental results showed that it can well remove noise and retain the fine signatures as much as possible. This presented tensor based multidimensional signal filtering will broaden the view in dealing with heterogeneous and multiaspect data in an age of big data.