• Journal of electromagnetic engineering and science
• /
• v.14 no.2
• /
• pp.79-81
• /
• 2014

In B-scan data measured by a pulse-type monostatic borehole radar, target signatures are seriously obscured by two clutters that differ in orientation and intensity. The primary clutter appears as a nearly constant time delay, which is caused by internal ringing between antenna and transceiver in the radar system. The secondary clutter occurs as an oblique time delay due to the guided borehole wave along the logging cable of the radar antenna. This issue led us to perform adaptive filtering processing for orientation-based clutter removal. This letter describes adaptive filtering processing consisting of a combination of edge detection, data rotation, and eigenimage filtering. We show that the hyperbolic signatures of a dormant air-filled tunnel target can be more distinctly enhanced by applying the proposed approach to the B-scan data, which are measured in a well-suited test site for underground tunnel detection.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2005.07a
• /
• pp.215-216
• /
• 2005

To decrease and remove of much noises that is detected in PD (partial discharge) measuring test. we forced on detection of those. We made W-LC filter for measuring PD. which adapted that to field test. We tested after design laboratory circumstances like field line. and then the phase change properties of detected signal in UHF sensor were measured by Lemke Probe and oscilloscope (TDS-3054. Tektronix). Eventually we checked decrement of noises from experimental result. Also from experimental result at the joint box of 22.9[kV] distribution line. we obtained reasonable data which enable noises to decrease. Hereafter those results will be adapted at ultra-high voltage for trouble prevention and on-line cable watch. diagnosis of those.

• Journal of the Korean Society for Environmental Technology
• /
• v.19 no.6
• /
• pp.576-585
• /
• 2018

Systematic management during the whole life cycle from construction to operation and maintenance is very important for the seven underground pipelines (waterworks, sewerage, electricity, telecommunications, gas, heating, oil including waterworks and sewerage). Especially, it is the construction process that affects the whole life cycle of underground buried pipeline. In order to construct a new city or to maintain different underground pipes, it is always necessary to dig the ground and carry out construction and related work. There is a possibility that secondary and tertiary breaks frequently occur in the pipeline construction process after the piping constructed first in this process. To solve this problem, a system is needed which can monitor damage in real time. However, the supply of electric power for continuous operation of the system is limited according to the environment of underground buried pipelines, so it is necessary to develop a stable electric power supply system using natural energy rather than existing electric power. In this study, we developed a system that can operate the pipeline monitoring system for long time (24 hours and 15 days) using natural energy using wind and solar light.

• Geophysics and Geophysical Exploration
• /
• v.9 no.4
• /
• pp.271-278
• /
• 2006

Investigations of underground cavities are required to provide useful information for the reinforcement design and monitoring of the ground subsidence areas. It is, therefore, necessary to develop integrated geophysical techniques incorporating different geophysical methods in order to accurately image and to map underground cavities in the ground subsidence areas. In this study, we conducted geophysical investigations for development of integrated geophysical techniques to detect underground cavities at the field test site in the ground subsidence area, located at Yongweol-ri, Muan-eup, Muan-gun, Jeollanam-do. We examined the applicability of geophysical methods such as electrical resistivity, electromagnetic, and microgravity to cavity detection with the aid of borehole survey results. The underground cavities are widely present within the limestone bedrock overlain by the alluvial deposits in the test site where the ground subsidences have occurred in the past. The limestone cavities are mostly filled with groundwater or clays saturated with water in the site. The cavities, thus, have low electrical resistivity and density compared to the surrounding host bedrock. The results of the study have shown that the zones of low resistivity and density correspond to the zones of the cavities identified in the boreholes at the site, and that the geophysical methods used are very effective to detect the underground cavities. Furthermore, we could map the distribution of cavities more precisely with the study results incorporated from the various geophysical methods. It is also important to notice that the microgravity method, which has rarely used in Korea, is a very promising tool to detect underground cavities.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.2
• /
• pp.129-152
• /
• 2024

In the application of deep learning object detection via CCTV in tunnels, a large number of false positive detections occur due to the poor environmental conditions of tunnels, such as low illumination and severe perspective effect. This problem directly impacts the reliability of the tunnel CCTV-based accident detection system reliant on object detection performance. Hence, it is necessary to reduce the number of false positive detections while also enhancing the number of true positive detections. Based on a deep learning object detection model, this paper proposes a false positive data training method that not only reduces false positives but also improves true positive detection performance through retraining of false positive data. This paper's false positive data training method is based on the following steps: initial training of a training dataset - inference of a validation dataset - correction of false positive data and dataset composition - addition to the training dataset and retraining. In this paper, experiments were conducted to verify the performance of this method. First, the optimal hyperparameters of the deep learning object detection model to be applied in this experiment were determined through previous experiments. Then, in this experiment, training image format was determined, and experiments were conducted sequentially to check the long-term performance improvement through retraining of repeated false detection datasets. As a result, in the first experiment, it was found that the inclusion of the background in the inferred image was more advantageous for object detection performance than the removal of the background excluding the object. In the second experiment, it was found that retraining by accumulating false positives from each level of retraining was more advantageous than retraining independently for each level of retraining in terms of continuous improvement of object detection performance. After retraining the false positive data with the method determined in the two experiments, the car object class showed excellent inference performance with an AP value of 0.95 or higher after the first retraining, and by the fifth retraining, the inference performance was improved by about 1.06 times compared to the initial inference. And the person object class continued to improve its inference performance as retraining progressed, and by the 18th retraining, it showed that it could self-improve its inference performance by more than 2.3 times compared to the initial inference.

• Tunnel and Underground Space
• /
• v.19 no.1
• /
• pp.1-10
• /
• 2009

Site characterization for structural stability in rock masses mainly involves the collection of joint property data, and in the current practice, much of this data is collected by hand directly at exposed slopes and outcrops. There are many issues with the collection of this data in the field, including issues of safety, slope access, field time, lack of data quantity, reusability of data and human bias. It is shown that information on joint orientation, spacing and roughness in rock masses, can be automatically extracted from LIDAR (light detection and ranging) point floods using the currently available Split-FX point cloud processing software, thereby reducing processing time, safety and human bias issues.

• Journal of Soil and Groundwater Environment
• /
• v.19 no.5
• /
• pp.18-25
• /
• 2014

Traditional investigation procedures of soil and groundwater contamination are followed by soil gas sampling, soil sampling, groundwater sampling, establishment of monitoring wells, and groundwater monitoring. It often takes several weeks to obtain the analysis reports, and sometimes, it needs supplemental sampling and analysis to delineate the polluted area. Laser induced fluorescence (LIF) system is designed for the detection of free-phase petroleum pollutants, and it is suitable for on-site real-time site investigation when coupling with a direct push testing tool. Petroleum products always contain polycyclic aromatic hydrocarbon (PAH) compounds possessing fluorescence characteristics that make them detectable through LIF detection. In this study, LIF spectroscopy of 5 major fuel products was conducted to establish the databank of LIF fluorescence characteristic spectra, including gasoline, diesel, jet fuel, marine fuel and low-sulfur fuel. Multivariate statistical tools were also applied to distinguish LIF fluorescence characteristic spectra among the mixtures of selected fuel products. This study successfully demonstrated the feasibility of identifying fuel species based on LIF characteristic fluorescence spectra, also LIF seemed to be uncovered its powerful ability of tracing underground petroleum leakages.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.6
• /
• pp.583-598
• /
• 2022

As human-based tunnel inspections are affected by the subjective judgment of the inspector, making continuous history management difficult. There is a lot of deep learning-based automatic crack detection research recently. However, the large public crack datasets used in most studies differ significantly from those in tunnels. Also, additional work is required to build sophisticated crack labels in current tunnel evaluation. Therefore, we present a method to improve crack detection performance by inputting existing datasets into a deep learning model. We evaluate and compare the performance of deep learning models trained by combining existing tunnel datasets, high-quality tunnel datasets, and public crack datasets. As a result, DeepLabv3+ with Cross-Entropy loss function performed best when trained on both public datasets, patchwise classification, and oversampled tunnel datasets. In the future, we expect to contribute to establishing a plan to efficiently utilize the tunnel image acquisition system's data for deep learning model learning.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.4
• /
• pp.253-263
• /
• 2021

Concrete structures are damaged by aging and external environmental factors. This type of damage is to appear in the form of cracks, to proceed in the form of spalling. Such concrete damage can act as the main cause of reducing the original design bearing capacity of the structure, and negatively affect the stability of the structure. If such damage continues, it may lead to a safety accident in the future, thus proper repair and reinforcement are required. To this end, an accurate and objective condition inspection of the structure must be performed, and for this inspection, a sensor technology capable of detecting damage area is required. For this reason, we propose a deep learning-based image processing algorithm that can detect spalling. To develop this, 298 spalling images were obtained, of which 253 images were used for training, and the remaining 45 images were used for testing. In addition, an improved loss function and data augmentation technique were applied to improve the detection performance. As a result, the detection performance of concrete spalling showed a mean intersection over union of 80.19%. In conclusion, we developed an algorithm to detect concrete spalling through a deep learning-based image processing technique, with an improved loss function and data augmentation technique. This technology is expected to be utilized for accurate inspection and diagnosis of structures in the future.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.5
• /
• pp.519-532
• /
• 2024

Anomaly detection for the penetration rate of tunnel boring machines (TBMs) is crucial for effective risk management in TBM tunnel projects. However, previous machine learning models for predicting the penetration rate have struggled with imbalanced data between normal and abnormal penetration rates. This study aims to enhance the performance of machine learning-based anomaly detection for the penetration rate by utilizing a data augmentation technique to address this data imbalance. Initially, six input features were selected through correlation analysis. The lowest and highest 10% of the penetration rates were designated as abnormal classes, while the remaining penetration rates were categorized as a normal class. Two prediction models were developed, each trained on an original training set and an oversampled training set constructed using SMOTE (synthetic minority oversampling technique): an XGB (extreme gradient boosting) model and an XGB-SMOTE model. The prediction results showed that the XGB model performed poorly for the abnormal classes, despite performing well for the normal class. In contrast, the XGB-SMOTE model consistently exhibited superior performance across all classes. These findings can be attributed to the data augmentation for the abnormal penetration rates using SMOTE, which enhances the model's ability to learn patterns between geological and operational factors that contribute to abnormal penetration rates. Consequently, this study demonstrates the effectiveness of employing data augmentation to manage imbalanced data in anomaly detection for TBM penetration rates.