Banca de QUALIFICAÇÃO: MAXWELL CAVALCANTE JÁCOME

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : MAXWELL CAVALCANTE JÁCOME
DATE: 28/02/2020
TIME: 14:00
LOCAL: Sala 414 do CTEC - UFRN
TITLE:

ANALYSIS OF WEAR IN TRIBOLOGICAL TESTS USING IMAGE PROCESSING

KEY WORDS:

wear analysis, image processing, tribology, Artificial Neural Networks

PAGES: 42
BIG AREA: Engenharias
AREA: Engenharia Mecânica
SUMMARY:

Friction occurs due to contact between two or more bodies and it is present in any mechanical system. Although, it is important to avoid unwanted relative movements, it acts as an energy dissipating force and promotes the wear of the components' surface. Tribological tests have been developed as a controlled way to evaluate the wear mechanism acting between metallic surfaces, as well as to observe the influence of the type of lubricant used. The assessment of the lubricity of a lubricant is standardized by the HFRR (High Frequency Reciprocating Rig) test, which is given by the sphere-disc tribological system in lubricated contact, and which produces as a result images from which the Wear Scar Diameter (WSD) is extracted. From a set of tests with different lubricants, images of the worn surfaces were extracted. Thus, it is proposed in this work to apply computer vision techniques that explore other characteristics of the images besides the WSD, thus allowing a better description of the wear and the type of lubricant used. With the images acquired in the HFRR tests, image processing techniques were applied using the Matlab software and the OpenCV library to obtain quantitative parameters. From this information, an Artificial Neural Network was built to classify new images according to the type of fluid applied in the lubrication, demonstrating the use of artificial intelligence to identify and classify wear patterns from the analysis of its images.

BANKING MEMBERS:
Presidente - 1640260 - JOSE JOSEMAR DE OLIVEIRA JUNIOR
Interno - 2266607 - FABIO JOSE PINHEIRO SOUSA
Interna - 1481705 - SALETE MARTINS ALVES