Journal Menu► ▼ Journal Menu
Journal Browser► ▼ Journal Browser
Special Issue "Diagnostics of Rotating Machinery through Vibration Monitoring: Signal Processing and Pattern Analysis"
A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Mechanical Engineering".
Deadline for manuscript submissions: closed (20 May 2023) | Viewed by 21167
Special Issue Editors
Interests: condition monitoring; vibration monitoring; diagnostics
Interests: modal analysis; nonlinear systems; identification; monitoring and diagnostics
Special Issue Information
Rotating machinery diagnostics is the discipline investigating possible causes of symptoms reflecting the presence of an unusual state in machines with rotating shafts. Through vibration monitoring (VM), particular patterns in the extracted features are related to departures from normal functioning, which can indicate a damaged state.
This kind of minimally invasive nondestructive testing (NDT) has the purpose of increasing the reliability of complex and expensive machines, switching from programmed maintenance to preventive maintenance regimes based on VM, so as to foster both safety and economic.
The problem of diagnosing damage is practically a data mining of the recorded datasets. Three fundamental steps are necessary:
- Signal processing to highlight the diagnostic information: e.g., enhancement of the signal of interest with respect to the background noise, estimation and compensation of nonstationarities induced by variable speed (instantaneous angular speed (IAS) estimation, computed order tracking, resampling, etc.), demodulation, filtering, etc.;
- Feature selection: quantities which summarize the dataset and whose behavior is correlated with the damage but, if possible, not with the operational and the environmental variables (confounders such as variable speed, load, temperature, humidity, etc.), which should be otherwise compensated with signal processing techniques;
- Diagnostics: producing knowledge about the health state of the machine, detecting the presence of incipient damage, tracking the damage evolution over time while understanding its severity, distinguishing between damage location and types and finally, switching to prognostics to predict the remaining useful life.
Works on available benchmark datasets will be preferred. Examples taken from the literature are:
- NASA Prognostics Data Repository, bearings datasets #4 (by IMS, University of Cincinnati, USA) and #10 (by FEMTO-ST Institute, Besançon, France)
- Case Western Reserve University Bearing Data Center
- PHM society challenge datasets, PHM’09 Gearbox dataset
- https://www.phmsociety.org/references/datasets (not available for download)
- The Politecnico di Torino rolling bearing open-access dataset, DOI: 10.5281/zenodo.3559553
- Bearing Vibration Data under Time-varying Rotational Speed Conditions, Ottawa, Canada, DOI: 10.17632/v43hmbwxpm.2
- CMMNO 2014 data planetary gearbox (provided by Maïa Eolis for the International Conference CMMNO 14 held in Lyon, France, on December, 15-16, 2014)
- https://cmmno2014.sciencesconf.org/resource/page/id/5 (not available)
- Surveillance 8 challenge dataset, civil aircraft engine vibration data measured in a transient operating mode (provided by Safran for the International Conference Surveillance 8, October 20-21, 2015, held at the Roanne Institute of Technology, France)
- https://surveillance8.sciencesconf.org/resource/page/id/17 (not available)
- CMMNO 14 dataset and part of the Surveillance 8 dataset can be found under the name Bearing Vibration Data under Time-varying Rotational Speed Conditions, DOI: 10.17632/s8jrrnnj9g.1
- National Renewable Energy Laboratory (NREL) wind turbine gearbox vibration condition monitoring benchmarking dataset
Prof. Dr. Luigi Garibaldi
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2300 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
- vibration monitoring
- machine diagnostics
- rotating shafts
- signal processing
- variable speed
- order tracking
- vibration features
- statistical learning
- pattern recognition
- damage detection
- damage identification
- damage classification