한국윤활학회:학술대회논문집 (Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference)
- 한국윤활학회 1998년도 제27회 춘계학술대회
- /
- Pages.83-90
- /
- 1998
신경회로망에 의한 마찰상태의 식별
Identification of Friction Condition with Neural Network
초록
The morphologies of the wear debris are directly indicative of wear processes occuring in machinery and their severity. The neural network was applied to identify friction condition from the lubricated moving system. The four parameter(50% volumetric diameter, aspect, roundness and reflectivity) of wear debris are used as inputs to the network and learned the friction coefficient. It is shown that identification results depend on the ranges of these shape parameter learned. The three kinds of the wear debris had a different pattern characteristic and recognized the friction condition and materials very well by neural network. We dicuss between the characteristic of wear debris and the friction coefficient and how the network determines difference in wear debris feature.