• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.5
• /
• pp.61-71
• /
• 1998

Genetic Algorithm(GA) is a method of approaching optimization problems by modeling and simulating the biological evolution. GA needs large time-consuming, so ti had better do on a parallel computer architecture. Our proposed system has a VLSI-oriented interconnection network, which is constructed from a viewpoint of fractal geometry, so that self-similarity is considered in its configuration. The approach to Parallel Genetic Algorithm(PGA) on our proposed system is explained, and then, we construct the classifier system such that the set of samples is classified into weveral classes based on the features of each sample. In the process of designing the classifier system, We have applied PGA to the Traveling Salesman Problem and classified the sample set in the Euclidean space into several categories with a measure of the distance.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.22 no.4
• /
• pp.299-306
• /
• 2009

Design optimization is a method to find optimum point which minimizes the objective function while satisfying design constraints. The conventional optimization does not consider the uncertainty originated from modeling or manufacturing process, so optimum point often locates on the boundaries of constraints. Reliability based design optimization includes optimization technique and reliability analysis that calculates the reliability of the system. Reliability analysis can be classified into simulation method, fast probability integration method, and moment-based reliability method. In most generally used MPP based reliability analysis, which is one of fast probability integration method, if many MPP points exist, cost and numerical error can increase in the process of transforming constraints into standard normal distribution space. In this paper, multiplicative decomposition method is used as a reliability analysis for RBDO, and sensitivity analysis is performed to apply gradient based optimization algorithm. To illustrate whole process of RBDO mathematical and engineering examples are illustrated.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2003.05a
• /
• pp.514-519
• /
• 2003

The aircraft engine is usually supported by rolling element bearings and has a small damping rate, which is vol y sensitive to external force. The high-performance requirement of the rotors leads to complex assembly designs and are more flexible. Squeeze film dampers (SFDs) are introduced to provide damping while crossing the critical speeds and stability to the rotor s :stem. Hence, the focus of the present investigation is on the decision of an optimal size of the flexible rotor system supported by the squeeze film dampers to minimize the maximum transmitted load and unbalance response over a range operating speeds. The enhanced genetic algorithm (EGA), which was developed by authors, is used in the optimization process. This algorithm is based on the synthesis of a modified genetic algorithm and simplex method. The results show significant benefits in using EGA when compared with nonlinear programming (NLP).

• Journal of Korean Society of Steel Construction
• /
• v.13 no.5
• /
• pp.577-586
• /
• 2001

The objective of this study is the development of sizing and system shape discrete optime design algorithm which is based on the genetic algorithms (GAs). The algorithm can perform both size and shape optimum designs of space trusses. The developed algorithm was implemented in a computer program. The algorithm is known to be very efficient for the discrete optimization The genetic process selects the next design points based on the survivability of the current design points The evolutionary process evaluates the survivability of the design points selected from the genetic process in the genetic process of the simple genetic algorithms there are three basic operators : reproduction cross-over and mutation operators. The efficiency and validity of the developed discrete optimum design algorithm was verified by applying the algorithm to optimum design examples.

• Proceedings of the KIEE Conference
• /
• 1998.11a
• /
• pp.326-328
• /
• 1998

This paper presents an optimal fuzzy power system stabilizer to damp out low frequency oscillation. The fuzzy logic controllers has been applied to a power system stabilizing controllers. But the design of a fuzzy logic power system stabilizer relies on empirical and heuristic knowledge of human experts as well as many trial-and-errors in general. This paper presents the optimal design method of the fuzzy logic stabilizer using the genetic algorithm, which is the optimization method based on the mechanics of natural selection and natural genetics. The proposed method tunes the parameters of the fuzzy logic stabilizer in order to minimize the consuming time during the design process. In this paper, the proposed method tunes the shape of membership function of the fuzzy variables. The proposed system is applied to the one-machine infinite-bus model of a power system. Through the case study, the efficiency of the fuzzy stabilizing controller tuned by genetic algorithm is verified.

• International Journal of Automotive Technology
• /
• v.8 no.5
• /
• pp.599-603
• /
• 2007

An efficient optimum design process has been developed and applied to systematically design a lock-up clutch system for a torque converter used in an automatic transmission. A simulated annealing algorithm was applied to determine the parameters of the compressive helical damper springs in the clutch. The determination of the number, location, a number of turns, and deflection of damper springs plays an important role in reducing vibration and noise in the lock-up system. Next, FE-based shape optimization was coded to find the shape of the clutch disk that would satisfy the strength, noise and vibration requirements. Using the optimum code, parametric studies were performed to see how spring diameters and frequencies of clutch systems changed as the damper spring traveling angles and the torques were varied. Based on the optimum results, five different designs for clutches with different springs were fabricated and vibration analyses and tests were conducted to validate the accuracy of the proposed method. Results from the two methods show a good correlation.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.3
• /
• pp.36-40
• /
• 2023

Recently, in the problem of multi-order processing in logistics warehouses, multi-pickup systems are changing from the form in which workers walk around the warehouse to the form in which goods come to workers. These changes are shortening the time to process multiple orders and increasing production. This study considered the sequence problem of which warehouse the items to be loaded on each truck come first and which items to be loaded first when loading multiple pallet-unit goods on multiple trucks in an industrial smart logistics automation warehouse. To solve this problem efficiently, we use the mutant algorithm, which combines the GA algorithm and ACO algorithm, and compare with original system.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.3
• /
• pp.1099-1109
• /
• 2018

For practical consideration, economic dispatch (ED) problems in power system have non-smooth cost functions with equality and inequality constraints that makes the problems complex constrained nonlinear optimization problems. This paper proposes a new constraint handling method for equality and inequality constraints which is employed to solve ED problems, where the incremental rate is employed to enhance the modification process. In order to prove the applicability of the proposed method, the study cases are tested based on the classical particle swarm optimization (PSO) and differential evolution (DE) algorithm. The proposed method is evaluated for ED problems using six different test systems: 6-, 15-, 20-, 38-, 110- and 140-generators system. Simulation results show that it can always find the satisfactory solutions while satisfying the constraints.

• Journal of KIISE:Software and Applications
• /
• v.29 no.11
• /
• pp.785-794
• /
• 2002

Automatic stock trading systems should be able to solve various kinds of optimization problems such as market trend prediction, stock selection, and trading strategies, in a unified framework. But most of the previous trading systems based on supervised learning have a limit in the ultimate performance, because they are not mainly concerned in the integration of those subproblems. This paper proposes a stock trading system, called R-Trader, based on reinforcement teaming, regarding the process of stock price changes as Markov decision process (MDP). Reinforcement learning is suitable for Joint optimization of predictions and trading strategies. R-Trader adopts two popular reinforcement learning algorithms, temporal-difference (TD) and Q, for selecting stocks and optimizing other trading parameters respectively. Technical analysis is also adopted to devise the input features of the system and value functions are approximated by feedforward neural networks. Experimental results on the Korea stock market show that the proposed system outperforms the market average and also a simple trading system trained by supervised learning both in profit and risk management.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.20 no.6
• /
• pp.1-8
• /
• 2012

Multidisciplinary design optimization (MDO) for a suspension component of the vehicle front suspension was performed in this research. Shapes and thicknesses of the subframe were optimized to satisfy multi-disciplinary design requirements; weight, fatigue, crash, noise, vibration, and harshness (NVH), and kinematic and compliance (K&C). Analyses procedures of the performance disciplines were integrated and automated by using the process integration and design optimization (PIDO) technique, and the integrated and automated analyses environments enabled various types of analytic design methodologies for solving the MDO problem. We applied an approximate optimization technique which involves sequential sampling and metamodeling. Since the design variables for thicknesses should be dealt as discrete variables. the evolutionary algorithm is selected as optimization technique. The MDO problem was formulated three types of problems according to the order of priorities among the performance disciplines, and the results of MDO provided design alternatives for various design situations.