Condition Monitoring Method of Mechanical Equipment Based on Data Boundary Morphology
- 1 December 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 970-975
Abstract
The traditional process of equipment state change is described by feature quantities, but the hidden knowledge of equipment contained in feature quantities is less, and the change of single feature is not enough to judge the change of equipment state. Therefore, it is very important to describe the operation status of equipment and visually display it, so as to establish the direct relationship between status and graphics. It is also an important way to improve the usability of equipment condition monitoring technology. Aiming at the above problems, the failure process of mechanical equipment is analyzed firstly, and then the distribution characteristics of plane representation of equipment status data are analyzed. Then, a method of condition monitoring of mechanical equipment based on data boundary shape after planarization is proposed to realize real-time tracking of equipment status. At the same time, a monitoring and alarming method for mechanical equipment based on the data boundary shape after planarization is proposed. Finally, the validity of the method is verified by bearing experimental data.Keywords
This publication has 2 references indexed in Scilit:
- Fault detection in rotating machines with beamforming: Spatial visualization of diagnosis featuresMechanical Systems and Signal Processing, 2017
- Constellation graphical method for representing multi-dimensional dataAnnals of the Institute of Statistical Mathematics, 1978