Using machine learning techniques in engineering applications

In the thesis, topics such as what machine learning is, why it is important, where it is used, how it works and its advantages and disadvantages were touched upon. The subject was introduced with the techniques of machine learning. In the thesis, what machine learning techniques are and how learning groups work were examined. It was analyzed how surface roughness works in machine learning and with what parameters the roughness-related parts of the techniques appear. The effects of surface roughness values on machine learning were investigated in terms of the consequences that would result in machine learning and use of the resulting data. Surface roughness calculations are measurements that examine whether the surface of the material is smooth or not. The intended use of machine learning algorithms in roughness is an industrially important issue. Surface roughness, which is an important structure in manufacturing and many other places, is an essential problem of the machine. Therefore, it is aimed to minimize the negative consequences caused by roughness with the models we mentioned in calculating surface roughness. Surface roughness is generally a statistical characterization of the height and fluctuations occurring on the surface. These analyzes are made through some parameters. To give examples of these parameters, topics such as Ra (average surface roughness), Rz (maximum surface roughness), Rq (root mean square height) were mentioned. As a result, in the thesis, the roughness values of three different materials examined with two surface roughness measuring machines and the materials used were examined. Results were obtained using experimental measuring devices and data.