Next Article in Journal
Nonlinear Model Predictive Control Using Robust Fixed Point Transformation-Based Phenomena for Controlling Tumor Growth
Next Article in Special Issue
A Reliability-Centered Maintenance Study for an Individual Section-Forming Machine
Previous Article in Journal
Mathematical Model of New Type of Train Buffer Made of Polymer Absorber—Determination of Dynamic Impact Curve for Different Temperatures
Previous Article in Special Issue
Gas Path Fault and Degradation Modelling in Twin-Shaft Gas Turbines
Article Menu

Export Article

Open AccessFeature PaperArticle
Machines 2018, 6(4), 48; https://doi.org/10.3390/machines6040048

Experimental Evidence of the Speed Variation Effect on SVM Accuracy for Diagnostics of Ball Bearings

Department of Sciences and Methods of Engineering, University of Modena and Reggio Emilia, Via Amendola 2-Pad. Morselli, 42122 Reggio Emilia, Italy
*
Author to whom correspondence should be addressed.
Received: 15 September 2018 / Revised: 15 October 2018 / Accepted: 17 October 2018 / Published: 18 October 2018
Full-Text   |   PDF [1789 KB, uploaded 18 October 2018]   |  

Abstract

In recent years, we have witnessed a considerable increase in scientific papers concerning the condition monitoring of mechanical components by means of machine learning. These techniques are oriented towards the diagnostics of mechanical components. In the same years, the interest of the scientific community in machine diagnostics has moved to the condition monitoring of machinery in non-stationary conditions (i.e., machines working with variable speed profiles or variable loads). Non-stationarity implies more complex signal processing techniques, and a natural consequence is the use of machine learning techniques for data analysis in non-stationary applications. Several papers have studied the machine learning system, but they focus on specific machine learning systems and the selection of the best input array. No paper has considered the dynamics of the system, that is, the influence of how much the speed profile changes during the training and testing steps of a machine learning technique. The aim of this paper is to show the importance of considering the dynamic conditions, taking the condition monitoring of ball bearings in variable speed applications as an example. A commercial support vector machine tool is used, tuning it in constant speed applications and testing it in variable speed conditions. The results show critical issues of machine learning techniques in non-stationary conditions. View Full-Text
Keywords: condition monitoring; support vector machine; non-stationary conditions; ball bearings; speed variations condition monitoring; support vector machine; non-stationary conditions; ball bearings; speed variations
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Cavalaglio Camargo Molano, J.; Rubini, R.; Cocconcelli, M. Experimental Evidence of the Speed Variation Effect on SVM Accuracy for Diagnostics of Ball Bearings. Machines 2018, 6, 48.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Machines EISSN 2075-1702 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top