• Proceedings of the KSME Conference
• /
• 2000.11a
• /
• pp.699-704
• /
• 2000

The present paper deals with a multiobjective optimization method based on the co-evolutionary genetic strategy. The co-evolutionary strategy carries out the multiobjective optimization in such way that it optimizes individual objective function as compared with each generation's value while there are more than two genetic evolutions at the same time. In this study, the designs that are out of the given constraint map compared with other objective function value are excepted by the penalty. The proposed multiobjective genetic algorithms are distinguished from other optimization methods because it seeks for the optimized value through the simultaneous search without the help of the single-objective values which have to be obtained in advance of the multiobjective designs. The proposed strategy easily applied to well-developed genetic algorithms since it doesn't need any further formulation for the multiobjective optimization. The paper describes the co-evolutionary strategy and compares design results on the simple structural optimization problem.

• Journal of the Korean Society for Railway
• /
• v.6 no.3
• /
• pp.194-202
• /
• 2003

To make railway carbody light in weight has advantages at some aspects of both manufacturing and maintenance. Recently, railway carbodys of steel structure have been lightened their weight by using aluminum extrusion plate. for the additional lightening of railway carbody, an optimal design which maintains proper strength and minimizes weight must be achieved. Optimization which is used with finite element analysis for aluminum extrusion plate has the disadvantage of consuming much time. In this paper, the method of equivalent material property which is available to FEA code is established using the method of equivalent stiffness. This method for plate is expanded into the method for railway carbody structure with plates and shells. An objective function is established for maximum stiffness of unit aluminum extrusion plate using established method of equivalent material property. We performed an multi-objective optimization using the penalty function method. As a result, recommendable shapes and sizes of unit extrusion plate for under-frame of high speed train is presented.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06c
• /
• pp.358-363
• /
• 1994

This paper presents the improvement of the SCHMM using discrete VQ and One-Pass algorithm for keywords recognition in Korean continuous speech. The SCHMM using discrete VQ is a simple model that is composed of a variable mixture gaussian probability density function with dynamic mixture number. One-Pass algorithm is improved such that recognition rates are enhanced by fathoming any undesirable semisyllable with the low likelihood and the high duration penalty, and computation time is reduced by testing only the frame which is dissimilar to the previously testd frame. In recognition experiments for speaker-dependent case, the improved One-Pass algorithm has shown recognition rates as high as 99.7% and has reduced compution time by about 30% compared with the currently abailable one-pass algorithm.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.04a
• /
• pp.516-520
• /
• 1996

This paper focues on development of a timer selection algorithm for IEEE802.4 token bus networks to serve large-scale integrated manufacturing systems. Such factory automation networks have to satisfy delay constraints imposed on time-critical messages while maintaining as much network capacity as possible for non-time-critical messages. Therefore, the object of this paper is to develop timer selection algorithm to minimize a certain penalty function. This paper presents an algorithm based on Genetic Algorithm. The efficacy of the algorithm has been demonstrated by a series of simulation experiments.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.11a
• /
• pp.514-518
• /
• 1996

This paper focuses on automated generation of the knowledge base for a fuzzy network performance manager in order to satisfy delay constraints imposed on time-critical messages while maintaining as much network capacity as possible for non-time-critical messages. Therefore, the bowlegs base is formulated to minimize a certain penalty function by using a type of genetic algorithm. The efficacy of the formulation method has been demonstrated by a series of simulation experiments.

• Journal of Korean Society for Quality Management
• /
• v.18 no.2
• /
• pp.81-92
• /
• 1990

This paper considers a scheduling of a set of jobs on single and multiple processors, when all jobs have a common due date and earliness and lateness are penalized at different cost rates. The objective is to determine the optimal value of a common due date and an optimal scheduling to minimize a total penalty function. It is also shown that a schedule having minimum weighted completion time variances must be V-shaped. For identical processors, a polynomial scheduling algorithm with the secondary objectives of minimizing makespan and machine occupancy is developed and a numerical example is presented.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.19 no.3
• /
• pp.81-91
• /
• 1994

This paper is to build an economic production quantity model for situations, in which, during the stockout period, a fraction .betha.(backorder ratio) of the demand is backordered and remaining fraction (1-.betha.) is lost. This paper develops an objective function representing the average annual cost of a production system by defining a time-weighted backorder cost and a lost sales penalty cost per unit lost under the assumptions of deterministic demand rate and deterministic production rate, and provides an algorithm for its optimal solution. At the extreme .betha.= 1, the presented model reduces to the Fabrycky's model with complete backorders.

• Proceedings of the Korean Statistical Society Conference
• /
• 2004.11a
• /
• pp.123-128
• /
• 2004

A finite dam under $P_{\lambda,;,T}^M-policy$ is considered, where the input of water is formed by a Wiener process subject to random jumps arriving according to a Poisson process. Explicit expression is deduced for the stationary distribution of the level of water. And the long-run average cost per unit time is obtained after assigning costs to the changes of release rate, a reward to each unit of output, and a penalty which is a function of the level of water in the reservoir.

• Journal of Korean Society of Transportation
• /
• v.13 no.3
• /
• pp.19-33
• /
• 1995

Conventional traffic assignment techniques usually do not consider traveler's route choice behavior affected by hierachicla strucfture in urban highway system. This study realizes the route choice behavior such that travelers tend to choose more higher level of highway rather than lower level of highway for longer trops. Otherwise, for shorter trips, travelers tend to choose lower level of highway unless they can get sufficient travel time saving by using mojor arterial street or freeway (higher level of highway). Therefore, this study suggests a traffic assignment technique incorrporating route choice behavior related to hierachical highway structure by introducing some perception costs to generalized cost function such as perceptional preference measureemnt for higher level higheay and perceptional penalty when changing to different level of highway. Through simulation analysis, it is shown that the simulation results with the new traffic assignment echnique can be different a lot from the results with the convential method.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.44.2-44
• /
• 2001

This paper presents a new concept for controlling of under actuated robot manipulators with avoiding obstacles using switching computed torque method (SCTM). One fundamental approach of this algorithm is to use the partly stable controllers (PSCs) in order to fulfill the ultimate control objective. Here, we use genetic algorithms (GA)in order to employ the optimum control action for a given time frame with the available set of elemental controllers, depending on which links/variables are controlled, i.e. the selection of optimum switching sequence of the control actions. The proposed approach models links of the robot using evolving ellipses and then introduces a penalty scheme for the objective function of GA when it detects collisions. An under actuated robot manipulator, which has three detrees-of-freedom is taken into consideration so as to illustrate the design procedure. Simulation results show the e.ectiveness of the proposed method.