• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.248-248
• /
• 2023

In recent years, the number of landslides in Korea has been increasing due to extreme weather events such as localized heavy rainfall and typhoons. Landslides often occur with debris flows, land subsidence, and earthquakes. They cause significant damage to life and property. 64% of Korea's land area is made up of mountains, the government wanted to predict landslides to reduce damage. In response, the Korea Forest Service has established a 'Landslide Information System' to predict the likelihood of landslides. This system selects a total of 13 landslide factors based on past landslide events. Using the LR technique (Logistic Regression) to predict the possibility of a landslide occurrence and the accuracy is known to be 0.75. However, most of the data used for learning in the current system is on landslides that occurred from 2005 to 2011, and it does not reflect recent typhoons or heavy rain. Therefore, in this study, we will apply a total of six machine learning techniques (KNN, LR, SVM, XGB, RF, GNB) to predict the occurrence of landslides based on the data of Inje, Gangwon-do, which was recently produced by the National Institute of Forest. To predict the occurrence of landslides, it is necessary to process converting landslide events and factors data into a suitable form for machine learning techniques through ArcGIS and Python. In addition, there is a large difference in the number of data between areas where landslides occurred or not. Therefore, the prediction was performed after correcting the unbalanced data using Tomek Links and Near Miss techniques. Moreover, to control unbalanced data, a model that reflects soil properties will use to remove absolute safe areas.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.133-144
• /
• 2021

This paper derives the fire risk of buildings in Seoul through the prediction of property damage and the occurrence of fires. This study differs from prior research in that it utilizes variables that include not only a building's characteristics but also its affiliated administrative area as well as the accessibility of nearby fire-fighting facilities. We use Ensemble Voting techniques to merge different machine learning algorithms to predict property damage and fire occurrence, and to extract feature importance to produce fire risk. Fire risk prediction was made on 300 buildings in Seoul utilizing the established model, and it has been derived that with buildings at Level 1 for fire risks, there were a high number of households occupying the building, and the buildings had many factors that could contribute to increasing the size of the fire, including the lack of nearby fire-fighting facilities as well as the far location of the 119 Safety Center. On the other hand, in the case of Level 5 buildings, the number of buildings and businesses is large, but the 119 Safety Center in charge are located closest to the building, which can properly respond to fire.

• Journal of the Korean Society of Industry Convergence
• /
• v.14 no.2
• /
• pp.45-52
• /
• 2011

Since the most exclusive machines of the modern industries which require the nano precision rates are evolved from the machine tools, the design of the stable machine tool structure is very critical. Exclusive machines for the modern industries such as semiconductor, solar cell and LED have surface machining processes which are similar to the face cutting and grinding of conventional machine tools. This study was initiated to stabilize a milling machine structure and further to help design those exclusive machines which have similar machining mechanisms. The vibrations inherent to the machine tool structures hurt the precision machining as well as damage the longevity of the structures. There have been numerous researches in order to suppress the vibrations of machine tool structures using the extra modules such as actuators and dampers. In this paper, the dynamic properties are analyzed to obtain the natural frequencies and mode shapes of a machine tool structure which reflect the main reasons of the biggest vibrations under the given operating conditions. And the feasibility of improving the stability of the structure without using any additional apparatus has been investigated with minor design changes. The result of the study shows that simple changes based on proper system identification can considerably improve the stability of the machine tool structure.

• Smart Structures and Systems
• /
• v.25 no.5
• /
• pp.605-617
• /
• 2020

The existence of damages in structures causes changes in the physical properties by reducing the modal parameters. In this paper, we develop a two-stages approach based on normalized Modal Strain Energy Damage Indicator (nMSEDI) for quick applications to predict the location of damage. A two-dimensional IsoGeometric Analysis (2D-IGA), Machine Learning Algorithm (MLA) and optimization techniques are combined to create a new tool. In the first stage, we introduce a modified damage identification technique based on frequencies using nMSEDI to locate the potential of damaged elements. In the second stage, after eliminating the healthy elements, the damage index values from nMSEDI are considered as input in the damage quantification algorithm. The hybrid of Teaching-Learning-Based Optimization (TLBO) with Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) are used along with nMSEDI. The objective of TLBO is to estimate the parameters of PSO-ANN to find a good training based on actual damage and estimated damage. The IGA model is updated using experimental results based on stiffness and mass matrix using the difference between calculated and measured frequencies as objective function. The feasibility and efficiency of nMSEDI-PSO-ANN after finding the best parameters by TLBO are demonstrated through the comparison with nMSEDI-IGA for different scenarios. The result of the analyses indicates that the proposed approach can be used to determine correctly the severity of damage in beam structures.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1220-1224
• /
• 2003

In this paper, we measured the radiation dose of a fuel handling machine of the CANDU type Wolsong nuclear reactor directly during operation, in spite of the high radiation level. In this paper we will describe the sensor development, measurement techniques, and results of our study. For this study, we used specially developed semiconductor sensors and matching dosimetry techniques for the mixed radiation field. MOSFET dosimeters with a thin oxide, that are tuned to a high dose, were used to measure the ionizing radiation dose. Silicon diode dosimeters with an optimum area to thickness ratio were used for the radiation damage measurements. The sensors are able to distinguish neutrons from gamma/X-rays. To measure the radiation dose, electronic sensor modules were installed on two locations of the fuel handling machine. The measurements were performed throughout one reactor maintenance cycle. The resultant annual cumulative dose of gamma/X-rays on the two spots of the fuel handling machine were 18.47 Mrad and 76.50 Mrad, and those of the neutrons were 17.51 krad and 60.67 krad. The measured radiation level is high enough to degrade certain cable insulation materials that may result in electrical insulation failure.

• Journal of Korean Society of Environmental Engineers
• /
• v.33 no.10
• /
• pp.748-755
• /
• 2011

After the Industrialization of 1960s, while it has greatly contributed to the industrial development owing to acceleration of mechanization, but it is real situation that the countermeasure to noise damage generating at the loud noise workshop is scarcely made. Especially, the machine noise made at factory and workplace is so shocking and repeatedly reiterating terrible noise that most of the spot workers are forcedly imposing such dangers as the severe unpleasant feeling and hearing impairments. On such point of view, this research has attempted to extract the proper rating vocabulary in order for evaluation on machine noise made at the high noisy workshop, therefore it is considering that those extracted vocabularies could be utilized as the useful psycho-acoustic experiment for evaluation on machine noise, also for establishment of regulation standard in domestic high noisy workshop.

• International Journal of Advanced Culture Technology
• /
• v.10 no.4
• /
• pp.499-510
• /
• 2022

This study examines the reporting factors of crime against business in Korea and proposes a corresponding predictive model using machine learning. While many previous studies focused on the individual factors of theft victims, there is a lack of evidence on the reporting factors of crime against a business that serves the public good as opposed to those that protect private property. Therefore, we proposed a crime prevention model for the willingness factor of theft reporting in businesses. This study used data collected through the 2015 Commercial Crime Damage Survey conducted by the Korea Institute for Criminal Policy. It analyzed data from 834 businesses that had experienced theft during a 2016 crime investigation. The data showed a problem with unbalanced classes. To solve this problem, we jointly applied the Synthetic Minority Over Sampling Technique and the Tomek link techniques to the training data. Two prediction models were implemented. One was a statistical model using logistic regression and elastic net. The other involved a support vector machine model, tree-based machine learning models (e.g., random forest, extreme gradient boosting), and a stacking model. As a result, the features of theft price, invasion, and remedy, which are known to have significant effects on reporting theft offences, can be predicted as determinants of such offences in companies. Finally, we verified and compared the proposed predictive models using several popular metrics. Based on our evaluation of the importance of the features used in each model, we suggest a more accurate criterion for predicting var.

• Structural Monitoring and Maintenance
• /
• v.7 no.1
• /
• pp.13-25
• /
• 2020

One of the most important aspects in structural health monitoring is the detection of fatigue damage. Structural components such as heavy-duty bolts work under high dynamic loads, and thus are prone to accumulate fatigue damage and cracks may originate. Those heavy-duty bolts are used, for example, in wind power generation and mining equipment. Therefore, the investigation of new and more effective monitoring technologies attracts a great interest. In this study the acoustic emission (AE) technology was employed to detect incipient damage during fatigue testing of a M36 bolt. Initial results showed that the AE signals have a high level of background noise due to how the load is applied by the fatigue testing machine. Thus, an advanced signal processing method in the time-frequency domain, the Hilbert-Huang Spectrum (HHS), was applied to reveal AE components buried in background noise in form of high-frequency peaks that can be associated with damage progression. Accordingly, the main contribution of the present study is providing insights regarding the detection of incipient damage during fatigue testing using AE signals and providing recommendations for further research.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.27 no.3
• /
• pp.440-449
• /
• 2003

Residual strength of fiber metal laminates after impact was studied. 3/4 lay up FML was fabricated using 4 ply prepreg, 2 ply aluminum sheets, and 1 ply steel sheet. Quasi isotropic ([0/45/90/-45]s) and orthotropic ([0/90/0/90]s) FRP were also fabricated to compare with FML. Impact test were conducted by using instrumented drop weight impact machine (Dynatup, Model 8250). Penetration load and absorbed energy of FML were superior to those of FRPs. Tensile tests were conducted to evaluate the residual strength after impact. Strength degradation of FML was less than that of FRP. This means that the damage tolerance of FML is excellent than that of FRP. Residual strength of each specimen was predicted by using Whitney and Nuismer(WN) Model. Impact damage area is assumed as a circular notch in WN model. Damage width is defined as the average of back face and top face damage width of each specimen. Average stress and point stress criterions were used to calculate the characteristic length. It is supposing that a characteristic length is a constant. The distribution of characteristic length shows that the assumption is reasonable. Prediction was well matched with experiment under both stress criterions.

• Composites Research
• /
• v.26 no.3
• /
• pp.195-200
• /
• 2013

This study aims to detecting and analyzing the defects of damaged carbon fiber reinforced composites after impacts, particularly focusing on barely visible impact damages. The impact test was progressed by a drop-weight machine and applied to introduce simulated damages on laminated composites used in aircrafts. Various nondestructive testing (NDT) techniques were applied to identify the defects on the specimens with different levels of impact energies. Based on the measurements data, the levels of the barely visible impacts, and the applicability and effectiveness of the detection methods were discussed. Generally, the results demonstrated that their inner damages contained bigger footprints than those on the surfaces. However, when the damage energy was low, it was found that the inner damage size could be smaller than those appeared on the surfaces.