Effective Time Domain Features for Identification of Bearing Fault using LDA and NB Classifiers

Abstract

Recently, the mechanical fault detection of an induction motor (IM) from vibration signals using pattern recognition has proven to be an effective method. This paper has studied for the first time statistical time domain features mean absolute value (MAV), waveform length (WL), zero crossing(ZC), slope sign changes (SSC), simple sign integral(SSI) and Willison amplitude (WAMP) for identification of the mechanical faults using linear discriminant analysis (LDA) and naive Bayes (NB) classifiers. In this study, the effectiveness of the features is investigated using parameters like accuracy, sensitivity and specificity individually and in groups for a total of 63 combinations. Each feature set combination is investigated for 15datasets defined under 5 groups in different combinations of faulty and normal working conditions. The results indicate that the feature set of SSI, WL,SSC and ZC features outperform the conventional features in the identification of faults and is found to be computationally effective. Further, NB classifier is found to be better than LDA in identification of mechanical faults.

Authors and Affiliations

B R NAYANA, P GEETHANJALI

Keywords

Related Articles

Saturator Efficiency and Uncertainty of NIS Primary Standard for Relative Humidity Calibration

In the last ten years, there has been associate interest of makers and laboratories in having more accurate humidity measurements. Electrical relative humidity (RH) sensors have been widely used. These sensors need to be...

THE COMPARISON OF USED TEMPLE OIL BIODIESEL PRODUCTIVITIES WITH THE OTHER BIODIESEL

The present world is facing two serious problems, one global warming on account of environmental pollution and the other scarcity of fossil fuel. This has pointed to search alternative and sustainable energy sources whic...

Motion Control of Electro-Pneumatic System based on Directional Control Solenoid Valve

This work is concerned with the design and implementation of position control electro-pneumatic system using ON/OFF solenoid directional control valves. To realize this approach, it's required to set up a laboratory mech...

The Design and Fabrication of a Compound Die to Make Hexagonal Washer

Many parts and components used in mechanical industry are manufactured by cold pressing operations. Die is the main tool in these operations. There are different types of dies like progressive die, compound die and combi...

DESIGN AND FABRICATION OF AUTONOMOUS ROBOT FOR PRECISION AGRICULTURE

Autonomous robots are used for the ease of operation and automating the agricultural sector, which in turn helps in high yield and reduction in labor cost. Automated robots are being used in many of the fields such as Ag...

Download PDF file
  • EP ID EP281438
  • DOI 10.24247/ijmperdfeb2018135
  • Views 91
  • Downloads 0

How To Cite

B R NAYANA, P GEETHANJALI (2018). Effective Time Domain Features for Identification of Bearing Fault using LDA and NB Classifiers. International Journal of Mechanical and Production Engineering Research and Development (IJMPERD ), 8(1), 1135-1150. https://europub.co.uk/articles/-A-281438