Optimization of wood machining parameters using artificial neural network in CNC router


Cakmak A., Malkocoglu A., ÖZŞAHİN Ş.

MATERIALS SCIENCE AND TECHNOLOGY, vol.39, no.14, pp.1728-1744, 2023 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 39 Issue: 14
  • Publication Date: 2023
  • Doi Number: 10.1080/02670836.2023.2180901
  • Journal Name: MATERIALS SCIENCE AND TECHNOLOGY
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aerospace Database, Applied Science & Technology Source, Chemical Abstracts Core, Chimica, Communication Abstracts, Compendex, Computer & Applied Sciences, INSPEC, Metadex, Civil Engineering Abstracts
  • Page Numbers: pp.1728-1744
  • Keywords: Artificial neural network, optimal machining conditions, wood surface roughness, wood cutting power, SURFACE-ROUGHNESS PREDICTION, MEDIUM-DENSITY FIBERBOARD, EDGE-GLUED PANELS, POWER-CONSUMPTION, CUTTING FORCES, TREATED WOOD, QUALITY, MODEL, WEAR, L.
  • Karadeniz Technical University Affiliated: Yes

Abstract

This study aims to determine the optimal CNC (Computer Numerical Control) machining conditions using an artificial neural network. For this purpose, Fagus orientalis, Castanea sativa, Pinus sylvestris, and Picea orientalis wood samples at 8%, 12%, and 15% moisture content (MC) were machined on a CNC router in both across and along the grain directions. Based on the experimental data of surface roughness and cutting power analyses, a total of 16 models were used. These were selected in hundreds of models that have the lowest error. The spindle speed, feed rate, and the number of cutter teeth were chosen to be different with the literature based on the length of cutter mark. As a result, optimum machining parameters were determined for each wood MC.