• Journal of the Korean Wood Science and Technology
• /
• v.32 no.4
• /
• pp.66-73
• /
• 2004

Three species of Italian poplar (Populus euramericana), red pine (Pinus densiflora) and oriental oak (Quercus variabilis) were selected for this study. They were cut so that the distances between each of tips and roots for a pair of fingers were 0, 0.15, 0.30 and 0.45 mm. Poly vinyl acetate (PVAc) and resorcinol-phenol resin (RPR) were used for finger-jointing. Compressive test parallel to the grain was conducted for the finger-jointed specimens. The results were as follows: The efficiency of compressive Young's modulus of finger-jointed timber to solid wood indicated low values, whereas the efficiency of compressive strength indicated high values of more than 90% in all species, especially, it was found that those of red pine indicated markedly high values of more than 97%. The efficiency of compressive displacement of Italian poplar finger-jointed timber was 2 times higher than solid wood, and it was 1.2 and 1.3 times higher than solid woods in red pine and oriental oak, respectively. Also, it was found that 0, the distance between each tip and root for the fingers, indicated the highest efficiency of compressive strength performance in Italian poplar finger-jointed timber, and for red pine and oriental oak finger-jointed timbers, the distances of 0.15 and 0.30 were found to indicate the highest efficiency.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.6
• /
• pp.469-484
• /
• 2021

Rock mass classification results have a great influence on construction schedule and budget as well as tunnel stability in tunnel design. A total of 3,526 tunnels have been constructed in Korea and the associated techniques in tunnel design and construction have been continuously developed, however, not many studies have been performed on how to assess rock mass quality and grade more accurately. Thus, numerous cases show big differences in the results according to inspectors' experience and judgement. Hence, this study aims to suggest a more reliable rock mass classification (RMR) model using machine learning algorithms, which is surging in availability, through the analyses based on various rock and rock mass information collected from boring investigations. For this, 11 learning parameters (depth, rock type, RQD, electrical resistivity, UCS, V_p, V_s, Young's modulus, unit weight, Poisson's ratio, RMR) from 13 local tunnel cases were selected, 337 learning data sets as well as 60 test data sets were prepared, and 6 machine learning algorithms (DT, SVM, ANN, PCA & ANN, RF, XGBoost) were tested for various hyperparameters for each algorithm. The results show that the mean absolute errors in RMR value from five algorithms except Decision Tree were less than 8 and a Support Vector Machine model is the best model. The applicability of the model, established through this study, was confirmed and this prediction model can be applied for more reliable rock mass classification when additional various data is continuously cumulated.