Optimization of diode laser cutting parameters for wood veneers using artificial neural networks
Küçük Resim Yok
Tarih
2025
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Taylor & Francis Ltd
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
In this study, an artificial neural network (ANN) model was developed to estimate the heat-affected zone (HAZ) width in laser cutting of walnut (Juglans nigra L.) and acer (Acer pseudoplatanus L.) veneers using a diode laser. The model used input parameters such as material type, laser power, cutting speed, and angle. It achieved high prediction accuracy, with MAPE values of 4.44% (training) and 7.01% (test), and RMSE values of 0.60% and 0.70%, respectively. A strong correlation (R > 91%) and high R-2 values (> 94%) between predicted and observed HAZ widths confirmed the model's reliability. Visual analyses supported these results. The HAZ width was influenced by cutting speed and angle, especially when the material type was held constant. Generally, increasing the cutting speed reduced the HAZ width. Similarly, raising the laser power (1.67 W -> 6.66 W) also led to narrowing of the HAZ. Walnut veneer, being dark-colored, extractive-rich, and having large tracheal structure, exhibited wider HAZ due to higher heat absorption and pyrolysis. In conclusion, the ANN model effectively reflects parameter effects on the HAZ in laser cutting and serves as a reliable decision-support tool, offering both time and cost efficiency.
Açıklama
Anahtar Kelimeler
Diode Laser, Artificial Neural Network, Laser Cutting Parameters, Wood Veneers Marquetry
Kaynak
Wood Material Science & Engineering
WoS Q Değeri
Q2
Scopus Q Değeri
Q2












