• Smart Structures and Systems
• /
• v.30 no.6
• /
• pp.601-612
• /
• 2022

The prediction of structural mechanical behaviors is vital important to early perceive the abnormal conditions and avoid the occurrence of disasters. Especially for underground engineering, complex geological conditions make the structure more prone to disasters. Aiming at solving the problems existing in previous studies, such as incomplete consideration factors and can only predict the continuous performance, the deep attention fused temporal convolution network (DATCN) is proposed in this paper to predict the spatial mechanical behaviors of structure, which integrates both the temporal effect and spatial effect and realize the cross-time prediction. The temporal convolution network (TCN) and self-attention mechanism are employed to learn the temporal correlation of each monitoring point and the spatial correlation among different points, respectively. Then, the predicted result obtained from DATCN is compared with that obtained from some classical baselines, including SVR, LR, MLP, and RNNs. Also, the parameters involved in DATCN are discussed to optimize the prediction ability. The prediction result demonstrates that the proposed DATCN model outperforms the state-of-the-art baselines. The prediction accuracy of DATCN model after 24 hours reaches 90 percent. Also, the performance in last 14 hours plays a domain role to predict the short-term behaviors of the structure. As a study case, the proposed model is applied in an underwater shield tunnel to predict the stress variation of concrete segments in space.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.3
• /
• pp.609-618
• /
• 2024

System reliability prediction in the development stage is increasingly crucial to reliability growth management to satisfy its target reliability, since modern system usually takes a form of complex composition and various complicated functions. In most cases of development stage, however, the information available for system reliability prediction is very limited, making it difficult to predict system reliability more precisely as in the production and operating stages. In this study, a system reliability prediction process is considered when the reliability-related information such as SIL (Safety Integrity Level) and MTTFd (Mean Time to Dangerous Failure) is available in the development stage. It is suggested that when the SIL or MTTFd of a system component is known and the field operational data of similar system is given, the reliability prediction could be performed using the scaling factor for the SIL or MTTFd value of the component based on the similar system's field operational data analysis. Predicting a system reliability is then adjusted with the conversion factor reflecting the temperature condition of the environment in which the system actually operates. Finally, the case of applying the proposed system reliability prediction process to a high performance mooring platform is dealt with.

• ETRI Journal
• /
• v.37 no.2
• /
• pp.222-232
• /
• 2015

In this paper, we propose a dual-phase approach to improve the process of heart disease prediction in a mobile environment. Firstly, only the confident frequent rules are extracted from a patient's clinical information. These are then used to foretell the possibility of the presence of heart disease. However, in some cases, subjects cannot describe exactly what has happened to them or they may have a silent disease - in which case it won't be possible to detect any symptoms at this stage. To address these problems, data records collected over a long period of time of a patient's heart rate variability (HRV) are used to predict whether the patient is suffering from heart disease. By analyzing HRV patterns, doctors can determine whether a patient is suffering from heart disease. The task of collecting HRV patterns is done by an online artificial neural network, which as well as learning knew knowledge, is able to store and preserve all previously learned knowledge. An experiment is conducted to evaluate the performance of the proposed heart disease prediction process under different settings. The results show that the process's performance outperforms existing techniques such as that of the self-organizing map and gas neural growing in terms of classification and diagnostic accuracy, and network structure.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.4
• /
• pp.100-108
• /
• 1995

This study is aimed to show that revised prediction method in road traffic noise after comparing prediction method of National Institute of Environmental Research with that of the Acoustical Society of Japan. For this purpose, prediction equation and caluation procedure of each case was programmized and data predicted by each method were compared with those measured in the 14 fields. The result show that data predicted by 14 fields. The result show that data predicted by the method proposed in this study were closer to the data measured in the fields than those predicted by National Institute of Environmental Research and the Acoustical Society of Japan in the surroundings of urban express way (include highway) and general traffic road where the vehicle speed is higher than 40km/h.

• Computers and Concrete
• /
• v.19 no.6
• /
• pp.651-658
• /
• 2017

High-performance concrete, besides aggregate, cement, and water, incorporates supplementary cementitious materials, such as fly ash and blast furnace slag, and chemical admixture, such as superplasticizer. Hence, it is a highly complex material and modeling its behavior represents a difficult task. This paper presents an evolutionary system for the prediction of high performance concrete strength. The proposed framework blends a recently developed version of genetic programming with a local search method. The resulting system enables us to build a model that produces an accurate estimation of the considered parameter. Experimental results show the suitability of the proposed system for the prediction of concrete strength. The proposed method produces a lower error with respect to the state-of-the art technique. The paper provides two contributions: from the point of view of the high performance concrete strength prediction, a system able to outperform existing state-of-the-art techniques is defined; from the machine learning perspective, this case study shows that including a local searcher in the geometric semantic genetic programming system can speed up the convergence of the search process.

• Journal of Advanced Marine Engineering and Technology
• /
• v.28 no.6
• /
• pp.1026-1036
• /
• 2004

In this study, single-phase heat transfer experiments were conducted with Oblong Shell and Plate heat exchanger using water. An experimental water loop has been developed to measure the single-phase heat transfer coefficient and pressure drop in a vertical Oblong Shell and Plate heat exchanger. Downflow of hot water in one channel receives heat from the cold water upflow of water in the other channel. Similar to the case of a plate heat exchanger, even at a very low Reynolds number, the flow in the Oblong Shell and Plate heat exchanger remains turbulent. The present data show that the heat transfer coefficient and pressure drop increase with the Reynolds number. Based on the present data, empirical correlations of the heat transfer coefficient and pressure drop in terms of Nusselt number and friction factor were proposed. Also, performance prediction analyses for Oblong Shell and Plate heat exchanger were executed and compared with experiments. $\varepsilon$-NTU method was used in this prediction program. Independent variables are flow rates and inlet temperatures. Compared with experimental data, the accuracy of the program is within the error bounds of $\pm$5% in the heat transfer rate.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.21 no.11
• /
• pp.1796-1808
• /
• 1997

In order to perform leak-before-break design of nuclear piping systems and integrity evaluation of reactor vessels, full stress-strain curves and fracture resistance(J-R) curves are required. However it is time-consuming and expensive to obtain J-R curves experimentally. To resolve these problems, three different methods for predicting J-R curves from tensile data were proposed by the authors previously. The objective of this paper is to develop a computer program based on those J-R curve prediction methods. The program consists of two major parts ; the main program part for the J-R curve prediction and the database part. Several case studies were performed to verify the program, and it was shown that the predicted results were, in general, in good agreement with the experimental ones.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.16 no.3
• /
• pp.211-216
• /
• 2013

Most of hull resistance prediction methods which are used to calculate the towing force of disabled ships are very simple and old-fashioned. In particular, in cases of barge ships, a method similar to the US Navy Towing Manual is being used. This paper reviewed the US Navy Towing Manual and the notification method of Korea Ministry of Oceans and Fisheries and proved that these prediction methods are irrational and inaccurate. Furthermore, a new Modified-Yamagata-Barge method is introduced as a more rational and accurate resistance prediction method which can be applied in case of barge ships.

• Advances in materials Research
• /
• v.8 no.4
• /
• pp.295-311
• /
• 2019

In this study, a three-dimensional Finite Element Model has been developed to estimate the size of the weakened zone in a bi-material a ceramic bonded to metal. The calculations results were compared to those obtained using Scanning Electron Microscope (SEM). In the case of elastic-plastic behaviour of the structure, it has been shown that the simulation results are coherent with the experimental findings. This indicates that Finite Element modeling allows an accurate prediction and estimation of the weakening effect of residual stresses on the bonding interface of Alumina. The obtained results show us that the three-dimensional numerical simulation used by the Finite Element Method, allows a good prediction of the weakened zone extent of a ceramic, which is bonded with a metal.

• Journal of the Korean Society of Systems Engineering
• /
• v.12 no.2
• /
• pp.9-18
• /
• 2016

Machine switch type control panel is widely used for machine tools in Korea. They, however, have some difficulties in identifying the current operating status of machine tools especially when exposed to cutting oil. And also they have quality problems of operating failures. A new capacitor touch type machine control panel is developed and its reliability is predicted. MIL-HDBK-217F and Teclordia SR-332 are used for its reliability prediction and the prediction results are compared.