The use of an artificial neural network for predicting the machining characterizing of wood materials densified by compressing

Authors : Mustafa TOSUN, Sait Dündar SOFUOĞLU

Pages : 55-62

Doi:10.30516/bilgesci.1240583

View : 26 | Download : 8

Publication Date : 2023-03-31

Article Type : Research Paper

Abstract :In this study, an approach for artificial neural network insert ignore into journalissuearticles values(ANN); was presented to predict and control arithmetical mean surface roughness value insert ignore into journalissuearticles values(Ra);, machining properties of wood materials densified by compressing in a computer numerical control insert ignore into journalissuearticles values(CNC); machine. Black poplar insert ignore into journalissuearticles values(Populus nigra L.); tree species were used as the experimental material. After specimens were densified by Thermo-Mechanical insert ignore into journalissuearticles values(TM); method at 0%, 20%, and 40% ratios, machining process of specimens were performed at 1000, 1500, and 2000 mm/min feed speeds and in 12000, 15000, 18000 rpm rotation speed on a CNC vertical wood machining center by using two different cutters. Data used for the training and testing of an ANN. Cutter type, compression ratio, feed rate, and spindle speed were selected as Four parameters. While hidden layer of the Ra model has ten neurons, one hidden layer was used, Compression ratio is the most significant parameter, followed by feed speed for Ra values. surface roughness increases with increased feed rate. Ra values in training, validation, and testing the data set for Ra were 0.97122, 0.8538, and 0.76685, respectively. The Mean Square Error insert ignore into journalissuearticles values(MSE); value was determined as 0.0019914 test of the network. The proposed ANN model came to agreement with the measured values in predicting surface roughness Ra values of MAPE. The MAPE value was calculated as 6.61, which can be considered a very good prediction insert ignore into journalissuearticles values(MAPE< 10 % = very good prediction);. The study showed that obtained ANN prediction model is a practical and efficient tool to model the Ra of wood. For reducing energy, time and cost in the wood industry insert ignore into journalissuearticles values(densification and CNC wood machining);, current research results can be implemented.
Keywords : Artificial neural networks, Thermo Mechanics, densification, black poplar, machining, roughness