Detail The development of an ANN surface roughness prediction system of multiple materials in CNC turning (article of The International Journal of Advanced Manufacturing Technology 2023) Bibliografi Author: Huang, PoTsang B. ; Inderawati, Maria Magdalena Wahyuni ; Rohmat ; Sukwadi, Ronald Topik: Surface roughness prediction; CNC turning; Artificial neural network development; Multi-material; JABFUNG-FT-RS-2023-30 Bahasa: (EN )     Penerbit: Springer-Verlag     Tahun Terbit: 2023     Jenis: Article - diterbitkan di jurnal ilmiah internasional Fulltext: IJAMT2023.pdf (2.07MB; 1 download) Abstract As one of the critical output parameters in the machining process, surface roughness quality must be constantly monitored, including predictions. Many scholars have researched sensing technology to monitor surface roughness. However, most of the research applied in a single-material model; this research intended to explore the intelligent combination prediction system between two materials, namely stainless steel (SUS304) and aluminum (Al6061). The machining process used computer numerical control (CNC) turning and applied sensing technology to collect signals as input factors in the prediction model. The prediction model used an artificial neural network (ANN) with the learning curve to find a good fitting of root mean square error (RMSE ) in training and validation. This research obtains the best accuracy prediction in each material and multi-material model by developing a backpropagation neural network prediction model, in which the surface roughness (Ra) was output, and the signal factors were inputs. The precise prediction of the multi-material model was higher (96.74%) than the accurate predictions of the SUS304 model (93.75%) and Al6061 model (89.81%). An appropriate t-test was used to compare the error prediction results of every single-material and multi-material models. From the t-test result of the error model, there were significant differences between the single and multi-material. This result was highly recommended to be practically applied in the manufacturing industry with various materials. Further research was proposed for improvement. Opini Anda Klik untuk menuliskan opini Anda tentang koleksi ini! Lihat Sejarah Pengadaan  Konversi Metadata   Kembali

Copyright © 2006, 2007 Unika Atma Jaya, all rights reserved