• The KIPS Transactions:PartB
• /
• v.14B no.5
• /
• pp.369-376
• /
• 2007

This paper proposes a hybrid genetic algorithm(HGA) for the classifier ensemble selection. HGA is added a local search operation for increasing the fine-turning of local area. This paper apply hybrid and simple genetic algorithms(SGA) to the classifier ensemble selection problem in order to show the superiority of HGA. And this paper propose two methods(SSO: Sequential Search Operations, CSO: Combinational Search Operations) of local search operation of hybrid genetic algorithm. Experimental results show that the HGA has better searching capability than SGA. The experiments show that the CSO considering the correlation among classifiers is better than the SSO.

• Journal of Navigation and Port Research
• /
• v.32 no.8
• /
• pp.597-602
• /
• 2008

T.S. HANBADA has a relatively large hull and superstructures above the water line, so she has much of leeway or turning of bow with the effect of winds. Especially on berthing, unberthing and/or sailing on low speed, these effects take place more significant. Therefore, it was carried out the numerical calculation of the wind force and moments acting on the T.S. HANBADA, and then calculated the leeway angle and counter rudder angle with the relative wind direction and velocity. Also, it was suggested the maximum wind velocity which could be berthed or unberthed used by bow thruster and the tugboat operations in strong winds. These results will be great helpful to the vessels with large superstructures on ship's handling in harbour or tugboat operations.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10b
• /
• pp.1570-1575
• /
• 1991

The feasibility of using an adaptive resonance network (ART2) with unsupervised learning capability for too] wear detection in turning operations is investigated. Specifically, acoustic emission (AE) and cutting force signals were measured during machining, the multichannel AR coefficients of the two signals were calculated and then presented to the network to make a decision on tool wear. If the presented features are significantly different from previously learned patterns associated with a fresh tool, the network will recognize the difference and form a new category m worn tool. The experimental results show that tool wear can be effectively detected with or without minimum prior training using the self-organization property of the ART2 network.

• Journal of Power System Engineering
• /
• v.3 no.4
• /
• pp.63-68
• /
• 1999

The determination of the optimal machining parameters in metal cutting, such as cutting speed, feed rate, and depth of cut, is an important aspect in an economic manufacturing process. The main objective in general is either to minimize the production cost or to maximize the production rate. Also there are constraints on all the machining operations which put restrictions on the choice of the machining parameters. In this paper as an objective function the production cost is considered with two constraints, surface finish and cutting power. Genetic Algorithm is applied to determine the optimum machining parameters, and the effectiveness of the applied algorithm is demonstrated by means of an example, turning operation.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.8
• /
• pp.43-49
• /
• 2004

The objective of this research is to investigate the effect of clearance angle on cutting performance in high speed end milling operation. The tool geometry parameters have complex relationship with cutting process parameter. In order to explain the effect of clearance angle, 2D turning operation in lathe and end milling operations are performed. Tools with different clearance angles are manufactured. Cutting forces, machining accuracy and tool life are examined according to the change of clearance angle. As clearance angle increases, cutting force decreases and machining accuracy improves. But it has been proved that there exists the optimal clearance angle according to the diameter of end mill for maximum tool life which is measured by frank wear.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.7
• /
• pp.59-65
• /
• 1996

A major problem in automation of turning operations is the difficulty in obtaining a sufficient and reliable chip control. Therefore it becomes desirable to find a method which can detect the chip form. Newly born chips in usual metal cutting radiate infrared rays. When such chips run out of cutting point quickly, the radiated energy from the zone around the tool is low compared with that of the case when long tangled chips are staying around the tool. The difference in chip pattern can be detected from the output of pyrometer. But, strictly speaking, only the output of pyrometer does not identify the chip form because that is the removal of chip. Therefore, in this paper, a method of the identification of chip form using output of pyrometer and fuzzy inference is developed.

• Bulletin of the Korean Mathematical Society
• /
• v.45 no.4
• /
• pp.651-661
• /
• 2008

Given binary operations "*" and "$\circ$" on a set X, define a product binary operation "$\Box$" as follows: $x{\Box}y\;:=\;(x\;{\ast}\;y)\;{\circ}\;(y\;{\ast}\;x)$. This in turn yields a binary operation on Bin(X), the set of groupoids defined on X turning it into a semigroup (Bin(X), $\Box$)with identity (x * y = x) the left zero semigroup and an analog of negative one in the right zero semigroup (x * y = y). The composition $\Box$ is a generalization of the composition of functions, modelled here as leftoids (x * y = f(x)), permitting one to study the dynamics of binary systems as well as a variety of other perspectives also of interest.

• Korean Journal of Agricultural Science
• /
• v.37 no.1
• /
• pp.113-121
• /
• 2010

Land consolidation ratio for rice paddy fields reached to 64.7% as of 2008 in Korea, and this also accelerated automation of field machinery. Especially, research on autonomous tractors has been continuously conducted. Tillage is one of the labor-, energy-, and time-consuming field operations. Most important requirements for autonomous tractors would be travelling path planning and electronic system to control the tractor to follow the path. The instruction of computer was required to conduct the tillage operation in field with unmanned traveling tractor. This instruction was coincidently used in the control of the traveling path and the motion of tractor. The objectives of the study were 1) to characterize and model tillage operating sequence, turning pattern, and 2) to develop tillage path formation programs for autonomous tractor and evaluate the performance.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.04a
• /
• pp.852-856
• /
• 1997

This paper describes a ultrasonic method for direct measurement of tool wear in turning operations. An integrated single ultrasonic transducer operating at a frequency of 10MHz is placed in contact with the insert tip. The change in amount of the reflected energy form the nose and flanks of the tool can be related to the level of tool wear and thr mechanical integrity of the tool. As a results, a correlation exists between the untrasonic measurement and tool wear and that it is tool dependent.

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.6
• /
• pp.795-801
• /
• 1998

In this paper, we propose a machine vision algorithm for inspecting inserts which are used for milling and turning operations. Major defects of the inserts are breakage and crack on insert surfaces. Among the defects, breakages on the face of the inserts can be detected through three stages of the algorithm developed in this paper. In the first stage, a multi-layer perceptron is used to recognize the inserts being inspected. Edge detection of the insert image is performed in the second stage. Finally, in the third stage breakages on the insert face are identified using Hough transform. The overall algorithm is tested on real specimens and the results show that the algorithm works fairly well.