• Journal of The Korean Society of Agricultural Engineers
• /
• v.66 no.1
• /
• pp.1-13
• /
• 2024

This study assessed the efficacy of improving the accuracy of reservoir water level prediction models by employing automated machine learning models and efficient cross-validation methods for time-series data. Considering the inherent complexity and non-linearity of time-series data related to reservoir water levels, we proposed an optimized approach for model selection and training. The performance of twelve models was evaluated for the Obong Reservoir in Gangneung, Gangwon Province, using the TPOT (Tree-based Pipeline Optimization Tool) and four cross-validation methods, which led to the determination of the optimal pipeline model. The pipeline model consisting of Extra Tree, Stacking Ridge Regression, and Simple Ridge Regression showed outstanding predictive performance for both training and test data, with an R² (Coefficient of determination) and NSE (Nash-Sutcliffe Efficiency) exceeding 0.93. On the other hand, for predictions of water levels 12 hours later, the pipeline model selected through time-series split cross-validation accurately captured the change pattern of time-series water level data during the test period, with an NSE exceeding 0.99. The methodology proposed in this study is expected to greatly contribute to the efficient generation of reservoir water level predictions in regions with high rainfall variability.

• Proceedings of the KSME Conference
• /
• 2008.11a
• /
• pp.576-580
• /
• 2008

Rubber material properties and useful life evaluation are very important in design procedure to assure the safety and reliability of the rubber components. In this paper, the evaluation of characteristics and useful life prediction of rubber component for elevator cabin were experimentally investigated. The material test and accelerated heat-aging test were carried. Rubber material constants were obtained by curve fittings of simple tension, pure shear and bi-axial tension test data. Heat aging test results changes as the threshold are used for assessment of the useful life and time to threshold value were plotted against reciprocal of absolute temperature to give the Arrhenius plot. By using the rubber material and component test several useful life prediction equations for rubber component were proposed. Predicted useful life of rubber component for elevator cabin agreed fairly with the experimental lives.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2000.07a
• /
• pp.775-778
• /
• 2000

In this paper, the life-time of macro interface between Epoxy/EPDM which consists in underground power cable joints is predicted. The electrode system of specimen is designed by FEM(finite elements method). The breakdown strength of specimens are observed by applying high AC voltage at the room temperature. The breakdown times under the constant voltage below the breakdown voltage were gained. As constant voltage is applied, the breakdown time is proportion to the breakdown strength. The life exponent n is gained by inverse power law, and the long breakdown life time can be evaluated.

• Proceedings of the KSME Conference
• /
• 2004.04a
• /
• pp.114-119
• /
• 2004

Endbeam is an important structural member of freight bogie for the support of service loading. In general, more than 25 years' durability is necessary. However, endbeam occur fatigue fracture in dynamic stress concentration location because comparatively strength and stiffness are low. Therefore, structure analysis is performed to evaluate structural problem of endbeam and local strain range as durability analysis. The number of cycles is extracted concerning the bogie in operation by measurement dynamic stress time history on critical part which is crack initiation in actual fact. At this time rainflow cycle counting is used to consider change of stress for operating condition. Based on the fatigue life curves and the stress analysis, the fatigue life of the endbeam is predicted and compared with the experimentally determined fatigue life, resulting in a fairly good correlation.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2008.04a
• /
• pp.1037-1040
• /
• 2008

In order to predict the remaining life of marine concrete structures under climatic loads, it is necessary to develop an analytical approach to predict the time and space dependent deterioration of concrete structures due to mainly chloride attack up to corrosion initiation and additional deterioration like cracking of cover concrete. This study aims to introduce FEM model for life-time simulation of concrete structures subjected to chloride attack. In order to consider uncertainties in materials as well as environmental parameters for the prediction, Monte Carlo Simulation is integrated in that FEM modeling for reliability-based remaining service life prediction. The paper is organized as follows: firstly general scheme for reliability-based remaining service life of concrete structures is introduced, then the FEM models for chloride penetration, corrosion product expansion and cover cracking are briefly explained, finally an example is demonstrated and the effects of localization of chloride concentration and corrosion product expansion on service life using above model are discussed.

• Journal of the Microelectronics and Packaging Society
• /
• v.22 no.2
• /
• pp.1-4
• /
• 2015

Qualification includes all activities to demonstrate that a product meets and exceeds the reliability goals. Manufacturers need to spend time and resources for the qualification processes under the pressure of reducing time to market, as well as offering a competitive price. Failure to qualify a product could result in economic loss such as warranty and recall claims and the manufacturer could lose the reputation in the market. In order to provide valid and reliable qualification results, manufacturers are required to make extra effort based on the operational and environmental characteristics of the product. This paper discusses optimal interval censoring design for reliability prediction of electronic packages under limited time and resources. This design should provide more accurate assessment of package capability and thus deliver better reliability prediction.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2010.05a
• /
• pp.229-230
• /
• 2010

The Carbonation, one of the main deterioration factors of concrete, reduces capacity of members with providing rebar corrosion environment. Consequently it suggested standards of all countries of world, carbonation depth prediction equation of respective researchers and time to rebar corrosion initiation. As a result of carbonation depth prediction equation calculation, difference of time to rebar corrosion initiation is 149 years and difference of carbonation depth prediction equation is 162 years when water cement ratio is 50%. So a study on rebar corrosion with carbonation depth will need existing reliable data and verifications by experiment.

• International Journal of Advanced Culture Technology
• /
• v.11 no.1
• /
• pp.325-331
• /
• 2023

In this paper, we propose a mixed neural network structure of CNN and LSTM that can be used to detect or predict odor occurrence, which is most required in manufacturing industry or real life, using odor complex sensors. In addition, the proposed learning model uses a complex odor sensor to receive four types of data such as hydrogen sulfide, ammonia, benzene, and toluene in real time, and applies this data to an inference model to detect and predict odor conditions. The proposed model evaluated the prediction accuracy of the learning model through performance indicators according to accuracy, and the evaluation result showed an average performance of 94% or more.

• Journal of Ocean Engineering and Technology
• /
• v.15 no.2
• /
• pp.94-98
• /
• 2001

fatigue life and nondestructive evaluation were examined experimentally using surface crack specimen and compact tension specimen of 5083 aluminium alloy. Acoustic emission signals emanated during failure of aluminum alloys has been the subject of numerous investigations. Possible sources of AE during deformation have been suggested as the dislocations, fracture of brittle particles and debonding of these particles from the alloy matrix. Fatigue life and penetration behavior of long surface crack can be evaluated quantitatively using K values proposed by authors. The influence of stress ratio on the frequency characteristics of AE signals were investigated.

• KOREAN JOURNAL OF PACKAGING SCIENCE & TECHNOLOGY
• /
• v.4 no.1
• /
• pp.23-32
• /
• 1997

The change in moisture content of moisture sensitive products in moisture-semipermeable packages was investigated for the purpose of predicting the shelf life of a product-package combination. A mathematical model, and a computer program based on the physiochemical properties of the product and the moisture permeability of the package was developed. The moisture content for products in moisture-semipermeable packages was determined under various environmental conditions and the results were compared with the predicted values by means of the simulation model. These experimental studies demonstrated that the prediction of the change in moisture content of packaged products over time by the simulation model is accurate, within a practical range of temperature and relative humidity values. The developed semi-empirical model is considered to have applications in industry, since it provides product shelf life information for a range of temperature and relative humidity conditions, with a limited number of experimentally obtained data points.