On experiments of a novel unsupervised deep learning based rotor balancing method

• Published in: Measurement and control (London) Vol. 55; no. 7-8; pp. 729 - 737
• Main Authors: Li, Liqing, Zhong, Shun, Chen, Huizheng, Lu, Zhenyong
• Format: Journal Article
• Language: English
• Published: London, England SAGE Publications 01.07.2022; Sage Publications Ltd; SAGE Publishing
• Subjects: Balancing; Coefficients; Deep learning; Rotors; Weight; weight trial; experimental rig; Rotor balancing; unsupervised deep learning; balancing experiment
• ISSN: 0020-2940; 2051-8730
• DOI: 10.1177/00202940221115744

Rotor dynamic balancing is essential in rotor industrial. The conventional balancing methods, including the influence coefficients method and modal balancing method, are effective, but lack economy and sufficient usage of the data. To overcome the disadvantages of the conventional balancing methods, a balancing method using unsupervised deep learning without weight trails had been proposed. The proposed network could identify the unbalanced forces from the data observed from just one run of the rotor and without labels. To validate the novel balancing method, an experimental rig is well-designed and established. Experimental validation and comparison with influence coefficients method are conducted. The experimental results show that the proposed balancing method gives consideration to both cost and accuracy. Compared with influence coefficients method, no extra weight trail process is needed and balancing performances are comparative. The experimental rig can be used for proving the scheme and for further same kind of research.