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

Abstract

In this study, an approach for artificial neural network (ANN) was presented to predict and control arithmetical mean surface roughness value (Ra), machining properties of wood materials densified by compressing in a computer numerical control (CNC) machine. Black poplar (Populus nigra L.) tree species were used as the experimental material. After specimens were densified by Thermo-Mechanical (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 (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 (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 (densification and CNC wood machining), current research results can be implemented.

Keywords

• Artificial neural networks
• Thermo-Mechanics
• densification
• black poplar
• machining
• roughness

References

1. Avramidis, S. and Iliadis, L. (2005). Predicting wood thermal conductivity using Artificial Neural Networks. Wood and Fiber Science, 37(4), 682-690.
2. Ayanleye, S., Nasir, V., Avramidis, S., Cool, J. (2021). Effect of wood surface roughness on prediction of structural timber properties by infrared spectroscopy using ANFIS, ANN and PLS regression. European Journal of Wood and Wood Products, 79(1), 101-115. https://doi.org/10.1007/s00107-020-01621-x
3. Blomberg, J. and Persson, B. (2004). Plastic deformation in small clear pieces of Scots pine (Pinus sylvestris) during densification with the CaLignum process. Journal of Wood Science, 50(4), 307–314.
4. Esteban, L.G., Garcia Fernández, F., De Palacios, P., Conde, M. (2009). Artificial neural networks in variable process control: application in particleboard manufacture. Forest Systems, 18(1), 92-100.bhttps://doi.org/10.5424/FS/2009181-01053
5. Fernández, F.G., De Palacios, P., Esteban, L.G., Garcia-Iruela, A., Rodrigo, B.G., Menasalvas, E. (2012). Prediction of MOR and MOE of structural plywood board using an artificial neural network and comparison with a multivariate regression model. Composites Part B: Engineering, 43(8), 3528-3533. https://doi.org/10.1016/j.compositesb.2011.11.054
6. Gurgen, A., Cakmak, A., Yildiz, S., Malkocoglu, A. (2021). Optimization of CNC operating parameters to minimize surface roughness of Pinus sylvestris using integrated artificial neural network and genetic algorithm. Maderas. Ciencia y Tecnología, 24(1), 1-12. https://doi.org/10.4067/s0718-221x2022000100401
7. ISO 468 (1982). Surface roughness-parameters, their values and general rules for specifying requirements, International Organization for Standardization, Geneva, Switzerland.
8. ISO 13061 (2014). Wood - Determination of moisture content for physical and mechanical tests, International Organization for Standardization, Geneva, Switzerland.

9. ISO 13061-2 (2014). Wood - Determination of density for physical and mechanical tests, International Organization for Standardization, Geneva, Switzerland.
10. ISO 3274 (2017). Geometrical Product Specifications (GPS) - Surface texture: Profile method - Nominal characteristics of contact (stylus) instruments, International Organization for Standardization, Geneva, Switzerland.
11. ISO 21920-2 (2021). Geometrical product specifications surface texture profile method terms, definitions and surface texture parameters, International Organization for Standardization, Geneva, Switzerland.
12. Lin, R.J.T., Van Houts, J., Bhattacharyya, D. (2006). Machinability investigation of medium-density fibreboard. Holzforschung, 60(1), 71-77. https://doi.org/10.1515/HF.2006.013
13. Lopes, C.S.D., Nolasco, A.M., Tomazello Filho, M., Dias, C.T., Dos, S. (2014). Evaluation of wood surface roughness of eucalypt species submitted to cutterhead rotation. Cerne, 20(3), 471-476. https://doi.org/10.1590/0104776020142003875
14. Malkocoglu, A. (2007). Machining properties and surface roughness of various wood species planed in different conditions. Building and Environment, 42(7), 2562-2567. https://doi.org/10.1016/j.buildenv.2006.08.028
15. Malkocoglu, A., Ozdemir, T. (2006). The machining properties of some hardwoods and softwoods naturally grown in Eastern Black Sea Region of Turkey. Journal of Materials Processing Technology, 173(3), 315–320. https://doi.org/10.1016/j.jmatprotec.2005.09.031 Nazerian, M., Shirzaii, S., Gargarii, R. M., Vatankhah, E. (2020). Evaluation of mechanical and flame retardant properties of medium density fiberboard using artificial neural network. Cerne, 26(2), 279–292. https://doi.org/10.1590/01047760202026022725
16. Ozsahin, S., Singer, H. (2021). The use of an artificial neural network for predicting the gloss of thermally densified wood veneers. Baltic Forestry, 27(2). https://doi.org/10.46490/BF422
17. Ozsahin, S., Singer, H. (2022). Prediction of noise emission in the machining of wood materials by means of an artificial neural network. New Zealand Journal of Forestry Science, 52, 1-11. https://doi.org/10.33494/nzjfs522022x92x
18. Pan, L., Rogulin, R., Kondrashev, S. (2021). Artificial neural network for defect detection in CT images of wood. Computers and Electronics in Agriculture, 87. https://doi.org/10.1016/j.compag.2021.106312
19. Pelit, H., Sonmez, A., Budakci, M. (2017). Effects of ThermoWood® process combined with thermo-mechanical densification on some physical properties of scots pine (Pinus sylvestris L.). BioResources, 9(3). https://doi.org/10.15376/biores.9.3.4552-4567
20. Pinkowski, G., Szymański, W., Krauss, A., Stefanowski, S. (2018). Effect of sharpness angle and feeding speed on the surface roughness during milling of various wood species. BioResources, 13(3), 6952–6962. https://doi.org/10.15376/biores.13.3.6952-6962
21. Rautkari, L. (2012). Surface modification of solid wood using different techniques. Aalto University, Finland, PhD Thesis.
22. Samarasinghe, S., Kulasiri, D., Jamieson, T. (2007). Neural networks for predicting fracture toughness of individual wood samples. Silva Fennica, 41(1), 105-122. https://doi.org/10.14214/sf.309
23. Senol, S. (2018). Determination of physical, mechanical and technological properties of some wood materials treated with thermo-vibro-mechanical (TVM) process, Duzce University, Turkey, PhD. Thesis.
24. Senol, S., Budakci, M. (2016). Mechanical wood modification methods. Mugla Journal of Science and Technology, 2(2), 53-59. https://doi.org/10.22531/muglajsci.283619
25. Sofuoglu, S.D. (2015). Using artificial neural networks to Model the surface roughness of massive wooden edge-glued panels made of scotch pine (Pinus sylvestris L.) in a machining process with computer numerical control, BioResources, 10(4), 6798-6808. https://doi.org/10.15376/biores.10.4.6797-6808
26. Sofuoglu, S.D., Tosun, M., Atilgan, A. (2022). Determination of the machining characteristics of Uludağ fir (Abies nordmanniana Mattf.) densified by compressing. Wood Material Science & Engineering. https://doi.org/10.1080/17480272.2022.2080586
27. Tiryaki, S., Aydin, A. (2014). An artificial neural network model for predicting compression strength of heat treated woods and comparison with a multiple linear regression model. Construction and Building Materials, 62, 102-8. https://doi.org/10.1016/j.conbuildmat.2014.03.04
28. Tosun, M. (2021). The effect of thermo-mechanical densification on machining properties of massive wooden material, Kutahya Dumlupinar University, Turkey, Master’s thesis.
29. Wu, H., Avramidis, S. (2007). Drying technology prediction of timber kiln drying rates by neural networks, Drying Technology, 24(12), 1541-1545. https://doi.org/10.1080/07373930601047584
30. Zhang, J., Cao, J., Zhang, D. (2016). ANN-based data fusion for lumber moisture content sensors: Transactions of the Institute of Measurement and Control., 28(1), 69–79. https://doi.org/10.1191/0142331206TM163OA
31. Zhong, Z., Hiziroglu, S., Chan, C.T.M. (2013). Measurement of the surface roughness of wood based materials used in furniture manufacture. Measurement, 46(4), 1482-1487.