• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.10a
• /
• pp.754-758
• /
• 2005

Optimization of process variables such as arc current, welding voltage and welding speed in terms of the weld characteristics desired is the key step in achieving high quality and improving performance characteristics without increasing the cost. Consequently, incorrect settings of those process variables give rise to deviations in the welding characteristics from the desired bead geometry. Therefore, trainee welders are referred to the tabulated information relating different metal types and thickness as to recommend the desired values of process variables. Basically, the bead geometry plays an important role in determining the mechanical properties of the weld. So that it is very important to select the process variables for obtaining optimal bead geometry. However, it is difficult for the traditional identification methods to provide an accurate model because the optimized welding process is non-linear and time-dependent. In this paper, the possibilities of the Infra-red sensor in sensing and control of the bead geometry in the automated welding process are presented. Infra-red sensor is a well-known method to deal with the problems with a high degree of fuzziness so that the sensor is employed to build the relationship between process variables and the quality characteristic the proposed above respectively. Based on several neural networks, the mathematical models are derived from extensive experiments with different welding parameters and complex geometrical features. The developed system enables to select the optimal welding parameters and control the desired weld dimensions during arc welding process.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.38 no.11
• /
• pp.925-933
• /
• 2014

Today, computational fluid dynamics (CFD) is widely used in industry because of the availability of high-performance computers. However, full-scale analysis poses problems owing to the limited resources and time. In this study, the performance and optimal size of a heat exchanger were calculated using the effectiveness-number of transfer units (${\varepsilon}-NTU$) method and a database of characteristics heat exchanger. Information about the geometry and performance of various heat exchangers is collected, and the performance of the heat exchanger is calculated under the given operating conditions. To determine the optimal size of the heat exchanger, a Genetic Algorithm (GA) is used, and MATLAB and REFPROP are used for the calculation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.11
• /
• pp.4121-4128
• /
• 2010

A probe card is used in testing semiconductor wafers. It must maintain a precise location tolerance for a fine pitch due to highly densified chips. However, high heat transferred from its lower chuck causes thermal deformations of the probe card. Vertical deformation due to the heat will bring contact problems to the pins in the probe card, while horizontal deformation will cause positional inaccuracies. Therefore, probe cards must be designed with proper materials and structures so that the thermal deformations are within allowable tolerances. In this paper, heat transfer analyses under realistic loading conditions are simulated using ANSYS$^{TM}$ finite element analysis program. Thermal deformations are calculated based on steady-state temperature gradients, and an optimal structure of the probe card is proposed by adjusting a set of relevant design parameters so that the deformations are minimized.

• Journal of Intelligence and Information Systems
• /
• v.13 no.4
• /
• pp.121-135
• /
• 2007

Constraint directed scheduling techniques, representing problem constraints explicitly and constructing schedules by constrained heuristic search, have been successfully applied to real world scheduling problems that require satisfying a wide variety of constraints. However, there has been little basic research on the representation and optimization of the objective value of a schedule in the constraint directed scheduling literature. In particular, the cost objective is very crucial for enterprise decision making to analyze the effects of alternative business plans not only from operational shop floor scheduling but also through strategic resource planning. This paper aims to explicitly represent and optimize the total cost of a schedule including the tardiness and inventory costs while satisfying non-relaxable constraints such as resource capacity and temporal constraints. Within the cost based scheduling framework, a cost propagation algorithm is presented to update cost information throughout temporal constraints within the same job.

• Journal of Power Electronics
• /
• v.17 no.4
• /
• pp.1014-1026
• /
• 2017

The traditional fault diagnosis method for photovoltaic (PV) inverters has a difficult time meeting the requirements of the current complex systems. Its main weakness lies in the study of nonlinear systems. In addition, its diagnosis time is long and its accuracy is low. To solve these problems, a hidden Markov model (HMM) is used that has unique advantages in terms of its training model and its recognition for diagnosing faults. However, the initial value of the HMM has a great influence on the model, and it is possible to achieve a local minimum in the training process. Therefore, a genetic algorithm is used to optimize the initial value and to achieve global optimization. In this paper, the HMM is combined with a genetic algorithm (GHMM) for PV inverter fault diagnosis. First Matlab is used to implement the genetic algorithm and to determine the optimal HMM initial value. Then a Baum-Welch algorithm is used for iterative training. Finally, a Viterbi algorithm is used for fault identification. Experimental results show that the correct PV inverter fault recognition rate by the HMM is about 10% higher than that of traditional methods. Using the GHMM, the correct recognition rate is further increased by approximately 13%, and the diagnosis time is greatly reduced. Therefore, the GHMM is faster and more accurate in diagnosing PV inverter faults.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.10
• /
• pp.57-64
• /
• 2019

In this paper, we study a polynomially solvable case of the inverse interval graph coloring problem. Given an interval graph associated with a specific interval system, the inverse interval graph coloring problem is defined with the assumption that there is no proper K-coloring for the given interval graph, where K is a fixed integer. The problem is to modify the system of intervals associated with the given interval graph by shifting some of the intervals in such a way that the resulting interval graph becomes K-colorable and the total modification is minimum with respect to a certain norm. In this paper, we focus on the case K = 1 where all intervals associated with the interval graph have length 1 or 2, and interval displacement is only allowed to the righthand side with respect to its original position. To solve this problem in polynomial time, we propose a two-phase algorithm which consists of the sorting and First Fit procedure.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.10
• /
• pp.486-492
• /
• 2019

The system-based approach is needed to select an optimal mix of weapon systems and ship platform among a variety of design alternatives with the uncertainties of the initial required operational capability. In the early-phase design, which included a feasibility study and concept design, it is possible to cause problems when a review of the operational concept, database development, and systematic design are not done, thereby producing uncertain and unstable requirements. To select the best solution without trial-and-error, the U.S. navy has applied the set-based method for the early-phase design of a new ship-to-shore connector. The ship synthesis model plays an important role in applying the set-based method, but only a few countries possess this model and have prohibited this model from being transferred to other countries. This paper suggests a set-based method using a genetic algorithm and decision-making theory through benchmarking existing ship data. The algorithm was verified using the DDG-51 class ship synthesis model to optimize the weapon system design, which has been released for research purposes.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.10 no.2
• /
• pp.180-187
• /
• 2018

Corrugated bulkhead has been adopted for cargo tank bulkheads of commercial vessels such as bulk carriers, product oil carriers and chemical tankers. It is considered that corrugated bulkhead is a preferred structural solution, compared to the flat stiffened bulkhead, due to several advantages such as lower mass, easier maintenance and smaller corrosion problems. Many researches to find the optimum shape of corrugated bulkhead have been mostly carried out for bulk carriers. Compared to corrugated bulkheads of bulk carriers, ones of chemical tankers are more complicated since they are composed of transverse and longitudinal bulkheads, and they are made of higher priced materials. The purpose of this study is the development of minimum weight design method for corrugated bulkhead of chemical tankers. Evolution strategy is applied as an optimization technique. It has been verified from many researches that evolution strategy searches global optimum point prominently by using multi-individual searching technique. Multi-individual searching methods need excessive time if they connect to 3-D finite element model for repetitive structural analyses. In order to resolve this issue, 2-D beam element connected to deck and lower stool is substituted for a corrugated structure in this study. To verify the reliability of the structural responses by idealized 2-D beam model, they have been compared with ones by 3-D finite element model. In this study, optimum design for corrugated bulkhead of 30 K chemical tanker has been carried out, and the results by developed optimum design program have been compared with design data of existing ship. It is found out that optimum design is about 9% lighter than one of existing ship.

• Journal of Digital Convergence
• /
• v.19 no.10
• /
• pp.253-263
• /
• 2021

Machine learning is the process of constructing a cost function using learning data used for learning and an artificial neural network to predict the data, and finding parameters that minimize the cost function. Parameters are changed by using the gradient-based method of the cost function. The more complex the digital signal and the more complex the problem to be learned, the more complex and deeper the structure of the artificial neural network. Such a complex and deep neural network structure can cause over-fitting problems. In order to avoid over-fitting, a weight decay regularization method of parameters is used. We additionally use the value of the cost function in this method. In this way, the accuracy of machine learning is improved, and the superiority is confirmed through numerical experiments. These results derive accurate values for a wide range of artificial intelligence data through machine learning.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.89-94
• /
• 2021

Recently, manufacturing companies are introducing many intelligent production processes that apply IIoT/ICT to improve competitiveness, and a system that maintains availability, improves productivity, and optimizes management costs is needed as a preventive measure using environmental data generated from air ejectors. Therefore, in this study, a dedicated control board was developed and LoRa communication module was applied to remotely control it to collect and manage information about compressors from cloud servers and to ensure that all operators and administrators utilize common data in real time. This dramatically reduced M/S steps, increased system operational availability, and reduced local server operational burden. It dramatically reduced maintenance latency by sharing system failure conditions and dramatically improved cost and space problems by providing real-time status detection through wired and mobile utilization by maintenance personnel.