Blind separation of rotating machine sources: Bilinear forms and convolutive mixtures

Alexander Ypma*, Amir Leshem, Robert P.W. Duin

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

77 Scopus citations


We propose the use of blind source separation (BSS) for separation of a machine signature from distorted measurements. Based on an analysis of the mixing processes relevant for machine source separation, we indicate that instantaneous mixing may hold in acoustic monitoring. We then present a bilinear forms-based approach to instantaneous source separation. For simulated acoustic mixing, we show that this method may give rise to a more robust separation. For vibrational monitoring, a convolutive mixture model is more appropriate. The demixing algorithm by Nguyen Thi-Jutten allows for separation of the contributions of two coupled machines, both in an experimental setup and in a real-world situation. We conclude that BSS is a feasible approach for blind separation of distorted rotating machine sources.

Original languageAmerican English
Pages (from-to)349-368
Number of pages20
Issue number1-4
StatePublished - Dec 2002
Externally publishedYes

Bibliographical note

Funding Information:
This work is partially supported by the Dutch Technology Foundation STW, Project No. DTN-44.3584 “Machine diagnostics by neural networks”, by TNO-TPD b.v. (Delft) and the Dutch Ministry of Housing, Spatial planning and Environment (Depart. of VROM). We like to thank Ronald Ligteringen (TU Delft), TechnoFysica b.v. (Barendrecht) and Landustrie b.v. (Sneek) for assistance with measurements, and Willem Keijzer (RND Mechanical Engineering b.v. Delft) and Guillaume Gelle (Reims University, France) for fruitful discussions. Moreover, we thank the anonymous reviewers for many useful remarks.


  • Bilinear forms
  • Blind source separation
  • Condition monitoring
  • Convolutive mixture
  • Machine vibration


Dive into the research topics of 'Blind separation of rotating machine sources: Bilinear forms and convolutive mixtures'. Together they form a unique fingerprint.

Cite this