• 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.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.5 no.3
• /
• pp.15-21
• /
• 1996

This study is focused on the prediction of appropriate tool life by clarifying the correlation between progressive tool wear and AE(Acoustic Emission) signals, while cutting stainless steel by end mill on the machining center. The results of this study were that RMSAE tends to increase linearly along with the increase of the cutting speed, and it was more sensitive to depth of cut than to the variation of feed rate at the same cutting conditions, and RMSAE increases around 0.21mm flank wear hereby AE-HIT also increases. AE signals depend upon tool wear and fracture from the above results. Therefore, the AE signals can be utilized in order to monitor the tool condition.

• Journal of the Society of Naval Architects of Korea
• /
• v.33 no.4
• /
• pp.75-86
• /
• 1996

A fatigue life prediction program for multiple planar surface cracks in finite plates and T-fillet joints, based on linear elastic fracture mechanics was developed. This prediction technique include the crack coalescence, mutual interation and the stress intensity concentration effect in welded joints. Total of 44 cases were compared with lida's and Vosikovsky's experimental results and it was found that the present method was a reasonable tool for the predictioin of fatigue life.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.9
• /
• pp.111-117
• /
• 2002

In most machining companies, operators decide the cutting condition, a pair of spindle speed (5) and table federate (F) by experience and subjective judgment. As cutting conditions are determined by operators' experience and ability, inconsistent cutting conditions are given in same operating conditions. The objective of this study is to develop the cutting condition decision system which utilizes shop data and predicts tool life by neural network and eventually leads to the optimal cutting condition. The production time per piece is considered for an optimization object. We will discuss the process of an optimal cutting condition decision by neural network. By this process, a series of shop data is stored. And neural network is constructed for prediction of tool life and the optimal cutting condition is recommended from a cutting condition decision system using the stored shop data. The results show that the developed system is rational in searching the optimal cutting conditions on job operations.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.4 no.2
• /
• pp.31-37
• /
• 1995

This study is focused on the prediction of appropriate tool life by clarifying the correlation between progressive tool wear and AE signal. when rcutting SM45C by End mill in machining center. First of all, end mill have a problem that position of sensor sticking because it is revolution tool, but I think that it can be bained specific character according to sticking Sensor in the Vise. Consequently, the following results have been obtained; 1. Each cutting speed of feed rate over 0.1mm had a tendency to increase linearly according to the RMSAE 2. The level of AE signal at the same cutting area was more sensitive to depth of cut tharn the variation of feed rate 3. In the range of cutting duringqr about 75minqr atqr cutting speed 27m/min flankqr wear turns up aboutqr 0.21mm, aboutqr 0.29mm in the caseqr of about 65minqr at 33/min, qr hereby RMSAE increased rapidly at 0.2mm flank wear, also AE-HIT and CUM-CNTS.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.11 no.4
• /
• pp.54-61
• /
• 2002

Inconel 690 alloy has widely been used in power plant and high temperature facilities because it has high thermal resistance and toughness. But we have little design data about the creep behaviors of the alloy. Therefore, in this study, an apparatus has been designed and built for conducting creep tests under constant load conditions. A series of creep tests on Inconel 690 alloy have been performed to get the basic design data and life prediction of inconel products and we have gotten the following results. First, the stress exponents decrease as the test temperatures increase. Secondly, the creep activation energy gradually decreases as the stresses become bigger. thirdly, the constant of Larson-Miller Parameters on this alloy is estimated about 10. And last the fractographs at the creep rupture show both the ductile and the brittle fracture according to the creep conditions.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.10a
• /
• pp.248-253
• /
• 2003

Titanium alloy has widely been used as glasses rim material because it has high specific strength and also is light, harmless to men. But, we have little design data about the creep behaviors of the alloy. Therefore, in this study, an apparatus has been designed and built for conducting creep tests under constant load conditions. A series of creep tests on them have been performed to get the basic design data and life prediction of titanium products and we have gotten the following results. First, the stress exponents decrease as the test temperatures increase. Secondly, the creep activation energy gradually decreases as the stresses become bigger. Thirdly, the constant of Larson-Miller parameters on this alloy is estimated about 13. And last, the fractographs at the creep rupture show both the ductile and the brittle fracture according to the creep conditions.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.10a
• /
• pp.22-27
• /
• 2004

Super-duralumin has widely been used as the part materials of aerospace and automobile industry because it has high specific strength and also is light. But, we have little design data about the creep behaviors of the alloy. Therefore, in this study, every creep test under four constant stress conditions have been conducted for four temperature conditions. A series of creep tests had been performed to get the basic design data and life prediction of super-duralurnin products and we have gotten the following results. First, the stress exponents showed the descending trend as the test temperatures increase. Secondly, the creep activation energy gradually decreased as the stresses become bigger. Thirdly, the constant of Larson-Miller parameters on this alloy was estimated about 6. And last, the fractographs at the creep rupture showed both the brittle fracture due to the transgranular rupture.

• Advances in concrete construction
• /
• v.1 no.3
• /
• pp.201-213
• /
• 2013

While recognizing the problem of reinforcement corrosion and premature structural deterioration of reinforced concrete (RC) structures as a combined effect of mechanical and environmental actions (carbonation, ingress of chlorides), emphasis is given on the effect of the latter, as most severe and unpredictable action. In this study, a simulation tool, based on proven predictive models utilizing principles of chemical and material engineering, for the estimation of concrete service life is applied on an existing reinforced concrete bridge (${\O}$resund Link) located in a chloride environment. After a brief introduction to the structure of the models used, emphasis is given on the physicochemical processes in concrete leading to chloride induced corrosion of the embedded reinforcement. By taking under consideration the concrete, structural and environmental properties of the bridge investigated, an accurate prediction of its service life is taking place. It was observed that the proposed, and already used, relationship of service lifetime- cover is almost identical with a mean line between the lines derived from the minimum and maximum critical values considered for corrosion initiation. Thus, an excellent agreement with the project specifications is observed despite the different ways used to approach the problem. Furthermore, different scenarios of concrete cover failure, in the case when a coating is utilized, and extreme deicing salts attack are also investigated.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.04a
• /
• pp.93-98
• /
• 2004

A reasonable analysis of cutting force in end milling may give much advantage to improvement of productivity and cutting tool life. In order to analyze cutting force, the cutting dynamics was modelled mathematically by using chip load, cutting geometry, and the relationship between cutting forces and the chip load. Specific cutting constants of the cutting dynamics model were obtained by average cutting forces, tool diameter, cutting speed, feed, axial depth, and radial depth of cut. The effects of the cutting conditions on the specific cutting force constants in milling were studied. The model is verified through comparisons of model predicted cutting forces with measured culling forces obtained from machining experiments