journal article·2015-09-02Open access

Neural Networks as a Tool to Characterise Oil State After Porous Bearings Prolonged Tests

Artur Król, Krzysztof Gocman, Bolesław Giemza

Materials Science· Volume 21· Issue 3

Abstract

The paper presents the results of research of durability tests of porous sleeves under differed conditions (600, 1000 and 1400 rpm, duration of the tests: 100, 200 and 1000 hours, temperature 60, 80 and 130˚C) of one oil. During the tests a temperature of the bearing and a moment of friction were measured. After each durability test oil samples were extracted from the bearings and some chosen properties were carried out (FTIR spectrums and total acid number). In the second stage the neural networks were used to describe achieved tribological characteristics. The data collected during the tests were used as an input to different neural networks models and as an output the investigative results of oil parameters were used. Different models of neural networks were checked to achieve the smallest training error and the best correlation between output from the network and the target. DOI: http://dx.doi.org/10.5755/j01.ms.21.3.7506
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Tribology and Lubrication Engineering · Lubricants and Their Additives · Surface Roughness and Optical Measurements

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References

Reference metadata was not supplied for this record.