• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.3
• /
• pp.242-250
• /
• 2019

In this paper, we propose a method to predict the failure of industrial robot using Seq2Seq (Sequence to Sequence) model, which is a model for transforming time series data among Artificial Neural Network models. The proposed method uses the data of the joint current and angular value, which can be measured by the robot itself, without additional sensor for fault diagnosis. After preprocessing the measured data for the model to learn, the Seq2Seq model was trained to convert the current to angle. Abnormal degree for fault diagnosis uses RMSE (Root Mean Squared Error) during unit time between predicted angle and actual angle. The performance evaluation of the proposed method was performed using the test data measured under different conditions of normal and defective condition of the robot. When the Abnormal degree exceed the threshold, it was classified as a fault, and the accuracy of the fault diagnosis was 96.67% from the experiment. The proposed method has the merit that it can perform fault prediction without additional sensor, and it has been confirmed from the experiment that high diagnostic performance and efficiency are available without requiring deep expert knowledge of the robot.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_3
• /
• pp.1037-1051
• /
• 2020

The accurate monitoring and forecasting of the intensity of tropical cyclones (TCs) are able to effectively reduce the overall costs of disaster management. In this study, we proposed a multi-task learning (MTL) based deep learning model for real-time TC intensity estimation and forecasting with the lead time of 6-12 hours following the event, based on the fusion of geostationary satellite images and numerical forecast model output. A total of 142 TCs which developed in the Northwest Pacific from 2011 to 2016 were used in this study. The Communications system, the Ocean and Meteorological Satellite (COMS) Meteorological Imager (MI) data were used to extract the images of typhoons, and the Climate Forecast System version 2 (CFSv2) provided by the National Center of Environmental Prediction (NCEP) was employed to extract air and ocean forecasting data. This study suggested two schemes with different input variables to the MTL models. Scheme 1 used only satellite-based input data while scheme 2 used both satellite images and numerical forecast modeling. As a result of real-time TC intensity estimation, Both schemes exhibited similar performance. For TC intensity forecasting with the lead time of 6 and 12 hours, scheme 2 improved the performance by 13% and 16%, respectively, in terms of the root mean squared error (RMSE) when compared to scheme 1. Relative root mean squared errors(rRMSE) for most intensity levels were lessthan 30%. The lower mean absolute error (MAE) and RMSE were found for the lower intensity levels of TCs. In the test results of the typhoon HALONG in 2014, scheme 1 tended to overestimate the intensity by about 20 kts at the early development stage. Scheme 2 slightly reduced the error, resulting in an overestimation by about 5 kts. The MTL models reduced the computational cost about 300% when compared to the single-tasking model, which suggested the feasibility of the rapid production of TC intensity forecasts.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.27 no.2
• /
• pp.61-77
• /
• 2024

The purpose of this study was to develop a method for rapidly diagnosing urban thermal comfort using Unmanned Aerial Vehicle (UAV) based data. The research was conducted at Changwon National University's College of Engineering site and Yongji Park, both located in Changwon, Gyeongsangnam-do. Baseline data were collected using field measurements and UAVs. Specifically, the study calculated field measurement-based thermal comfort indices PET and UTCI, and used UAVs to create and analyze vegetation index (NDVI), sky view factor (SVF), and land surface temperature (LST) images. The results showed that UAV-predicted PET and UTCI had high correlations of 0.662 and 0.721, respectively, within a 1% significance level. The explanatory power of the prediction model was 43.8% for PET and 52.6% for UTCI, with RMSE values of 6.32℃ for PET and 3.16℃ for UTCI, indicating that UTCI is more suitable for UAV-based thermal comfort evaluation. The developed method offers significant time-saving advantages over traditional approaches and can be utilized for real-time urban thermal comfort assessment and mitigation planning

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.205-205
• /
• 2012

국내에서 새로운 댐 저수지 건설을 통한 수자원의 안정적인 확보는 어려운 여건에 있다. 따라서 수자원의 효율적인 확보, 댐 하류하천의 수질 개선, 신규댐 건설 대체 효과를 기대하기 위해 기존 댐 저수지의 연계운영이 중요하게 인식되고 있다. 본 연구에서는 다수의 댐 저수지 수체를 연계하여 모델을 통해 해석하고자 안동-임하호를 연결한 2차원 모델(CE-QUAL-W2)을 구축하고, 2002년과 2006년 수문사상을 재현하였으며, 수리해석을 실시하였다. 안동호의 좌안인 임동면 마리와 임하호의 우안인 망천리를 연결하고, EL. 140 m 위치에 길이 2 km, 직경 5.5 m로 콘크리트 터널을 연결하는 것으로 가정하였다. 관내 바닥 마찰계수와 미소 마찰손실 값은 0.05를 입력하였다. 저수지 실측수위와 모의수위를 시계열로 비교한 결과, 2002년과 2006년 안동호와 임하호에서 여름철 유입량 증가에 따른 수위 상승을 잘 반영하였고, 결정계수값($R^2$)이 모두 0.9953 이상으로 나타나 모델은 두 저수지 물수지 계산에 있어서 높은 신뢰도를 보였다. 2006년을 대상으로 안동호와 임하호의 댐 앞에서 수심별 수온의 실측값과 모의값을 비교한 결과, 안동호는 4월부터 성층이 진행되어 5월에 수온약층이 EL. 130 m에 형성되었다. 7월 홍수가 중층 밀도류를 형성하여 수온 성층구조를 교란하였고, 기존의 수온약층이 EL. 120 m 로 하강하였으며, 표층 EL. 145 m에 새로운 수온약층이 형성되는 2단 성층 구조를 보였다. 여름철 동안 이러한 현상은 지속되었고, 10월부터 대기기온 강하와 함께 수직혼합이 시작되었다. 수온예측 오차는 AME $0.336{\sim}1.806^{\circ}C$, RMSE $0.415{\sim}2.271^{\circ}C$의 범위로 실측값을 잘 반영하는 것으로 나타났다. 임하호도 안동호와 유사한 경향을 보였고, 모델은 두 저수지에서 전 기간에 걸쳐 모두 안정적으로 저수지 수온 성층현상을 모의하였다. 2002년 수문사상에서 안동-임하 연계 운영시 안동호의 평균 수위는 1.38 m 상승하였고, 임하호는 3.75 m 낮아지는 것으로 모의되었다. 수위변동에 따른 유동 유량은 임하호에서 안동호로 3억 6천 4백만 톤, 안동호에서 임하호로 2억 9천 1백만 톤으로 임하호에서 안동호로 유동한 유량이 높게 나타났다. 유역면적에 비해 저수용량이 작은 임하호의 경우 두 저수지간 유량의 이동에 따라서 저수용량의 증가로 인한 홍수 저감 효과가 있을 것으로 판단된다. 반면, 안동-임하 연계 운영시 임하호의 차가운 물이 안동호로 유입되는 경우, 안동호의 수온 성층구조에 영향을 주었다. 안동호의 경우는 단독운영시보다 높은 위치에 수온약층(EL. 140 m)이 형성되었으며, 임하호는 반대로 저수위가 낮아지면서 단독운영시보다 수온약층의 위치가 약간 낮아졌다. 이러한 결과는 두 저수지 연결시 안동호의 탁수와 수질 환경에 변화가 있을 수 있음을 시사한다.

• Journal of Korea Water Resources Association
• /
• v.56 no.7
• /
• pp.439-449
• /
• 2023

Recent advancements in data measuring technology have facilitated the installation of various sensors, such as pressure meters and flow meters, to effectively assess the real-time conditions of water distribution systems (WDSs). However, as cities expand extensively, the factors that impact the reliability of measurements have become increasingly diverse. In particular, demand data, one of the most significant hydraulic variable in WDS, is challenging to be measured directly and is prone to missing values, making the development of accurate data generation models more important. Therefore, this paper proposes an adversarially trained autoencoder (ATAE) model based on generative deep learning techniques to accurately estimate demand data in WDSs. The proposed model utilizes two neural networks: a generative network and a discriminative network. The generative network generates demand data using the information provided from the measured pressure data, while the discriminative network evaluates the generated demand outputs and provides feedback to the generator to learn the distinctive features of the data. To validate its performance, the ATAE model is applied to a real distribution system in Austin, Texas, USA. The study analyzes the impact of data uncertainty by calculating the accuracy of ATAE's prediction results for varying levels of uncertainty in the demand and the pressure time series data. Additionally, the model's performance is evaluated by comparing the results for different data collection periods (low, average, and high demand hours) to assess its ability to generate demand data based on water consumption levels.

• Journal of the Society of Naval Architects of Korea
• /
• v.51 no.4
• /
• pp.274-282
• /
• 2014

Time series of the dynamic response of a slender marine structure was predicted using quadratic Volterra series. The wave-structure interaction system was identified using the NARX(Nonlinear Autoregressive with Exogenous Input) technique, and the network parameters were determined through the supervised training with the prepared datasets. The dataset used for the network training was obtained by carrying out the nonlinear finite element analysis on the freely standing riser under random ocean waves of white noise. The nonlinearities involved in the analysis were both large deformation of the structure under consideration and the quadratic term of relative velocity between the water particle and structure in Morison formula. The linear and quadratic frequency response functions of the given system were extracted using the multi-tone harmonic probing method and the time series of response of the structure was predicted using the quadratic Volterra series. In order to check the applicability of the method, the response of structure under the realistic ocean wave environment with given significant wave height and modal period was predicted and compared with the nonlinear time domain simulation results. It turned out that the predicted time series of the response of structure with quadratic Volterra series successfully captures the slowly varying response with reasonably good accuracy. It is expected that the method can be used in predicting the response of the slender offshore structure exposed to the Morison type load without relying on the computationally expensive time domain analysis, especially for the screening purpose.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.1A
• /
• pp.30-37
• /
• 2006

In this paper, we propose a QoS-aware efficient bandwidth re-provisioning scheme in a next generation wireless packet transport network. At the transport network layer, it classifies the traffic of the radio network layer into a real time class and a non-real time class. Using an auto-regressive time-series model and a given packet loss probability, our scheme predicts the needed bandwidth of the non-real time class at every re-provisioning interval. Our scheme increases the system capacity by releasing the unutilized bandwidth of the non-real time traffic class for the real-time traffic class while insuring a controllable upper bound on the packet loss probability of a non-real time traffic class. Through empirical evaluations using the real Internet traffic traces, our scheme is validated that it can increase the bandwidth efficiency while guaranteeing the quality of service requirements of the non-real time traffic class.

• Journal of Korean Society for Quality Management
• /
• v.48 no.3
• /
• pp.511-520
• /
• 2020

Purpose: The purpose of this study was to devise an accurate machine learning model for predicting silica concentrations following the addition of impurities, through time series analysis of mining data. Methods: The mining data were preprocessed and subjected to time series analysis using the machine learning model. Through correlation analysis, valid variables were selected and meaningless variables were excluded. To reflect changes over time, dependent variables at baseline were treated as independent variables at later time points. The relationship between independent variables and the dependent variable after n point was subjected to Pearson correlation analysis. Results: The correlation (R2) was strongest after 3 hours, which was adopted as a dependent variable. According to root mean square error (RMSE) data, the proposed method was superior to the other machine learning methods. The XGboost algorithm showed the best predictive performance. Conclusion: This study is important given the current lack of machine learning studies pertaining to the domestic mining industry. In addition, using time series analysis in mining data will show further improvement. Before establishing a predictive model for the proposed method, predictions should be made using data with time series characteristics. After doing this work, it should also improve prediction accuracy in other domains.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.2A
• /
• pp.97-108
• /
• 2012

Dynamic responses were measured using long-term monitoring system for Uldolmok tidal current pilot power plant which is one of jacket-type offshore structures. Among the dynamic quantities, the tilt angle was chosen because the low frequency response components can be precisely measured by dynamic tiltmeter, and the natural frequencies and modal damping ratio were successfully identified using proposed LS-FDD (least squared frequency domain decomposition) method. And the effects of tidal height and tidal current velocity on the variation of natural frequencies and modal damping ratios were investigated in time and frequency domain. Also the non-parametric models were tested to model the relationship between tidal conditions and modal properties such as natural frequencies and damping ratios.

• Journal of Soil and Groundwater Environment
• /
• v.20 no.3
• /
• pp.74-82
• /
• 2015

A method to filter out the effect of river stage fluctuations on groundwater level was designed using an artificial neural network-based time series model of groundwater level prediction. The designed method was applied to daily groundwater level data near the Gangjeong-Koryeong Barrage in the Nakdong river. Direct prediction time series models were successfully developed for both cases of before and after the barrage construction using past measurement data of rainfall, river stage, and groundwater level as inputs. The correlation coefficient values between observed and predicted data were over 0.97. Using the time series models the effect of river stage on groundwater level data was filtered out by setting a constant value for river stage inputs. The filtered data were applied to the hybrid water table fluctuation method in order to estimate the groundwater recharge. The calculated ratios of groundwater recharge to precipitation before and after the barrage construction were 11.0% and 4.3%, respectively. It is expected that the proposed method can be a useful tool for groundwater level prediction and recharge estimation in the riverside area.