• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.1
• /
• pp.13-24
• /
• 2021

Tunnel boring machine (TBM) is widely used for tunnel excavation in hard rock and soft ground. In the perspective of TBM-based tunneling, one of the main challenges is to drive the machine optimally according to varying geological conditions, which could significantly lead to saving highly expensive costs by reducing the total operation time. Generally, drilling investigations are conducted to survey the geological ground before the TBM tunneling. However, it is difficult to provide the precise ground information over the whole tunnel path to operators because it acquires insufficient samples around the path sparsely and irregularly. To overcome this issue, in this study, we proposed a geological type classification system using the TBM operating data recorded in a 5 s sampling rate. We first categorized the various geological conditions (here, we limit to granite) as three geological types (i.e., rock, soil, and mixed type). Then, we applied the preprocessing methods including outlier rejection, normalization, and extracting input features, etc. We adopted a deep neural network (DNN), which has 6 hidden layers, to classify the geological types based on TBM operating data. We evaluated the classification system using the 10-fold cross-validation. Average classification accuracy presents the 75.4% (here, the total number of data were 388,639 samples). Our experimental results still need to improve accuracy but show that geology information classification technique based on TBM operating data could be utilized in the real environment to complement the sparse ground information.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.48 no.5
• /
• pp.59-66
• /
• 2020

Recently, cultivation and management technologies have been needed to adapt due to climate change, which is causing abnormal weather conditions. One technique is to increase the utilization of evergreen broad-leaved species with high ornamental value. A total of five treatments were installed (1m×22.5m), including 60g/㎡ and 80g/㎡ using two types mulching material with an overlapping and hole-drilling mulching method and these were compared to un-mulching treatment a total of planted 92㎡ attheWol-aTestSiteForestattheForestforBiomaterialsResearchCenterinJinju-si, Gyeongsangnam-dofor 10monthsusing3-years-oldQuercusglaucaThunb. In comparison with the control site, the 60g/㎡ overlapping method was about 1.9 times higher than the root collar diameter, but there was no statistical significance between the treatments. Healthy seedlings were found to meet these conditions due to high biomass values and below and T/R ratios of 3.0 or lower and H/D ratios of 7.0 or lower. Comparing the values of LWR, SWR, and RWR, which can be evaluated for seedling due to the mulching treatments, as compared to the control, the growth of the ground areas including leaves and stems was enhanced, but the growth of the underground areas containing roots tended to have high control values. Based on this, the SQI value, which can be evaluated for the comprehensive quality of seedlings, was found to be significantly different between the control site and the mulching treatment sites, confirming that the growth and growth improvement effects were achieved with mulching treatments. The chlorophyll content analysis showed that there was a significant difference from the control site, and it was judged that weed generation in the control acted as an environmental stress, causing a decrease in chlorophyll content. It was found that the overlapping 80g/㎡ of polypropylene mulching material generated about 4 times fewer weeds than the control, and the manpower required for the mulching test field and weeding were equal at 3.3 people/100㎡/1 day. Mulching treatments have demonstrated a significant difference in the promotion of growth and quality of the seedlings and are judged as an alternative that can reduce the economic burden incurred by the purchase of the supplies and the manpower required to weed forestry plantations.