• IE interfaces
• /
• v.25 no.1
• /
• pp.52-63
• /
• 2012

Up-to-date enlargement of the scale of global outsourcing has brought about the need of systematic and efficient tools for competitive supplier discovery located in various areas. A web-based business supporting system, referred to as Excellent Manufacturer Scouting System(EMSS), is being developed to serve core business functions including supplier discovery, negotiation, and collaboration between overseas buyers and domestic suppliers throughout the process of supply chain formation. In this paper, a supplier assessment model devoted to evaluation of core manufacturing capability is proposed by targeting small and medium sized mold companies. The assessment model will eventually be loaded to EMSS. Even if many well-designed models for supplier assessment have been presented in literature, most of them limit the evaluation criteria to somewhat general information on a given supplier, such as cost, delivery time, quality, rather than core manufacturing capability itself. This research is pioneering work on supplier assessment from the viewpoint of manufacturability. The proposed assessment model classifies assessment indices into six criteria, which have been drawn by intensive survey and analysis of the mold industry. Actual assessment indices for each criterion are also presented along with an exemplary evaluation result.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.77-91
• /
• 2022

Various monitoring systems have been implemented in civil infrastructure to ensure structural safety and integrity. In long-term monitoring, these systems generate a large amount of data, where anomalies are not unusual and can pose unique challenges for structural health monitoring applications, such as system identification and damage detection. Therefore, developing efficient techniques is quite essential to recognize the anomalies in monitoring data. In this study, several machine learning techniques are explored and implemented to detect and classify various types of data anomalies. A field dataset, which consists of one month long acceleration data obtained from a long-span cable-stayed bridge in China, is employed to examine the machine learning techniques for automated data anomaly detection. These techniques include the statistic-based pattern recognition network, spectrogram-based convolutional neural network, image-based time history convolutional neural network, image-based time-frequency hybrid convolution neural network (GoogLeNet), and proposed ensemble neural network model. The ensemble model deliberately combines different machine learning models to enhance anomaly classification performance. The results show that all these techniques can successfully detect and classify six types of data anomalies (i.e., missing, minor, outlier, square, trend, drift). Moreover, both image-based time history convolutional neural network and GoogLeNet are further investigated for the capability of autonomous online anomaly classification and found to effectively classify anomalies with decent performance. As seen in comparison with accuracy, the proposed ensemble neural network model outperforms the other three machine learning techniques. This study also evaluates the proposed ensemble neural network model to a blind test dataset. As found in the results, this ensemble model is effective for data anomaly detection and applicable for the signal characteristics changing over time.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2531-2533
• /
• 2002

In this paper, we evaluate feasibility of an object-oriented method in a distributed real-time control environment through the prediction of delay expected. We adopt CAN as the distributed network and the application layer of the CAN is composed of client/server communication model of COM and surroundings for the support of real-time capability of the COM. Mathematical models formalizing delays which are predicted to invoke in the COM architecture are proposed. Sensors and actuators which are widely used in distributed network-based systems are represented by COM objects in this paper. It is expected that the mathematical models can be used to protect distributed network-based systems from violation of real-time features by the COM.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.395-398
• /
• 2000

The method of Variable Structure Control (VSC) design of windmill power systems is proposed. In the design of sliding mode control, we use Riccati equations arising in linear H$\^$$\infty$/ control to decide a stable sliding surface. Then the reachability to the sliding surface is realized by designing a nonlinear controller for the windmill power system. The capability of the proposed controller to damp out the oscillations of power and the robustness with respect to the system parameter variations and model errors are evaluated in the simulation study.

• Ocean Systems Engineering
• /
• v.11 no.1
• /
• pp.43-58
• /
• 2021

In the present work, a 3D numerical model is proposed to study local scouring around single vertical piers with different cross-section shapes under steady-current flow. The model solves the flow field and sediment transport processes using a coupled approach. The flow field is obtained by solving the Unsteady Reynolds Averaged Navier-Stokes (URANS) equations in combination with the k-ω SST turbulence closure model and the sediment transport is considered using both bedload and suspended load models. The proposed model is validated against the empirical measurements of local scour around single vertical piers with circular, square, and diamond cross-section shapes obtained from the literature. The measurement of scour depth in equilibrium condition for the simulations reveal the differences of 4.6%, 6.7% and 13.1% from the experimental measurements for the circular, square, and diamond pier cases, respectively. The model displayed a remarkable performance in the prediction of scour around circular and square piers where horseshoe vortices (HSVs) have a leading impact on scour progression. On the other hand, the maximum deviation was found in the case of the diamond pier where HSVs are weak and have minimum impact on the formation of local scour. Overall, the results confirm that the prediction capability of the present model is almost independent of the strength of the formed HSVs and pier cross-section shapes.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.7-13
• /
• 2021

Machine vision is a technology that helps the computer as if a person recognizes and determines things. In recent years, as advanced technologies such as optical systems, artificial intelligence and big data advanced in conventional machine vision system became more accurate quality inspection and it increases the manufacturing efficiency. In machine vision systems using deep learning, the image quality of the input image is very important. However, most images obtained in the industrial field for quality inspection typically contain noise. This noise is a major factor in the performance of the machine vision system. Therefore, in order to improve the performance of the machine vision system, it is necessary to eliminate the noise of the image. There are lots of research being done to remove noise from the image. In this paper, we propose an autoencoder based machine vision system to eliminate noise in the image. Through experiment proposed model showed better performance compared to the basic autoencoder model in denoising and image reconstruction capability for MNIST and fashion MNIST data sets.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.6
• /
• pp.445-452
• /
• 2016

This paper discusses the dynamics and control problem of an overhead shuttle system (OSS), which is a critical part of the automated container terminal at a port. The main purpose of the OSS is efficient automated transport function of containers, which also requires high precision and safety. A major difference between the OSS and the conventional container crane is the configuration of the cables for hoisting the spreader. A mathematical model of the OSS is developed here for the first time, which results in an eight-pole system. Also, open loop control methods (trapezoidal and notch-type velocity profiles) are investigated so that the command input to the overhead shuttle produces the minimum possible sway of the payload. Simulation results show that the vibration suppression capability of the OSS is superior to the conventional overhead container crane, which is partially due to the cable configuration.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2001.10a
• /
• pp.405-424
• /
• 2001

Many simulation models have been built to facilitate simulation technique in designing, evaluating, and optimizing supply chains. Simulation is preferred to deal with stochastic natures existing in the supply chain. Moreover simulation has a capability to find local optimum value within each component through entire supply chain. Most of supply chain simulation models have been developed on the basis of discrete-event simulation. Since supply chain systems are neither completely discrete nor continuous, the need of constructing a model with aspects of both discrete-event and continuous simulation is provoked, resulting in a combined discrete-continuous simulation. In this paper, an architecture of combined modeling for supply chain simulation is proposed, which includes the equation of continuous portion in supply chain and how these equations are used in the supply chain simulation models. A simple example of supply chain model dealing with the strategic level of supply chain presented in this paper shows the possibility and the prospect of this approach.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.16-26
• /
• 2024

Mobile edge computing (MEC) plays a crucial role in improving the performance of resource-constrained mobile devices by offloading computation-intensive tasks to nearby edge servers. However, existing methods often neglect the critical consideration of future task requirements when making offloading decisions. In this paper, we propose an innovative approach that addresses this limitation. Our method leverages recurrent neural networks (RNNs) to predict task sizes for future time slots. Incorporating this predictive capability enables more informed offloading decisions that account for upcoming computational demands. We employ genetic algorithms (GAs) to fine-tune fitness functions for current and future time slots to optimize offloading decisions. Our objective is twofold: minimizing total processing time and reducing energy consumption. By considering future task requirements, our approach achieves more efficient resource utilization. We validate our method using a real-world dataset from Google-cluster. Experimental results demonstrate that our proposed approach outperforms baseline methods, highlighting its effectiveness in MEC systems.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.35 no.11
• /
• pp.1199-1204
• /
• 2011

The capability to bilaterally telemanipulate soft-tissues for medical applications could increase the quality of telemanipulation systems. Since most soft-tissue manipulation tasks include constrained motion interacting with an unknown and dynamic bioenvironment through contact, bilateral telemanipulation raises problems due to stability and transparency issues. It is well understood that knowledge of environments plays an important role in pursuing transparent telemanipulation and achieving telepresence, and in particular, online estimation of environmental parameters with an explicit environment model can improve these systems' performance. In this study, a continuum mechanics-based environment model with an online environmental property estimation algorithm and an adaptive telemanipulation control scheme is proposed. The proposed method can improve the telemanipulation performance in terms of stability and transparency and can offer valuable information (e.g., elastic modulus of soft tissues) pertaining to diagnostic examinations.