Characterization of aluminum surface using image processing methods and artificial neural network methods

Heppi Familiana; Iyus Maulana; Aries Karyadi; Irwin Syahri Cebro; Agustami Sitorus

doi:10.1109/CED.2017.8308113

Characterization of aluminum surface using image processing methods and artificial neural network methods

Closed

Heppi Familiana, Iyus Maulana, Aries Karyadi, Irwin Syahri Cebro, Agustami Sitorus

2017 3rd International Conference on Computing, Engineering, and Design, ICCED 2017 Vol. 2018-March Conference paper Cited by 13

Abstract

The characterization of the material surface of the machine tool result should be known to assess quality of the product. Currently, the evaluation of product quality of machine tools is subjective. This study aims to characterize the surface of a metal, especially Aluminum based on image processing that metal displayed with computational approach using Artificial Neural Network (ANN). The specimen was worked by using several machines and different spindle rotation speeds and cutting speeds to obtain different surface roughness. The specimens were captured using a 4 mega pixel digital camera with the same source of illumination, with the same distance and pixel image. Aluminum image is further process to be identified with ANN. The results showed ANN 11 input 5 hidden model and 1 output; [11-5-1] showed the best results for identifying the surface of Aluminum with the smallest RMSE: 0.0038 for training and testing. © 2017 IEEE.

Affiliations

Dept. of Mechanical Engineering, STT Nusaputra, Sukabumi, Indonesia; Dept. of Mechanical Engineering, Lhokseumawe State Polytechnic, Lhokseumawe, Indonesia

View full text (DOI) →

Research at a Glance

Research at a Glance

Topics & SDG Alignment

Collaboration

Author Profile (Selected)

References Overview

Journal & Source

Metadata & Integrity