Surface roughness classification of electro discharge machined surfaces with deep ensemble learning

Abstract

In this study, a CNN-based image processing technique was utilized for an EDM-machined tactile plate (VDI 3400) with 16 distinct surface roughness features. The images (1600 × 1200 px) were captured with an optical microscope at different magnifications (50×, 100×, and 200×). The dataset was augmented with various image processing techniques and then split into training, validation, and testing sets. The proposed prediction system is trained on the state-of-the-art ResNet18, EfficientNetB2, and EfficientNetv2s CNN models. Additionally, deep Ensemble Learning (EL) approaches, consisting Majority Voting (MV) and Average Voting (AV), were conducted. The accuracy scores of the deep EL model were verified using independent test data and provided superior performance at 50× (99.42%). However, the accuracy obtained at other magnifications were not very high at 100× (98.05%) and 200X (87.37%) optical zoom. The findings of this study show that EL techniques show great potential for stable and efficient determination of surface roughness characteristics.