• 제어로봇시스템학회논문지
• /
• 제22권4호
• /
• pp.293-300
• /
• 2016

The Voice recognition is one of convenient methods to communicate between human and robots. This study proposes a speech recognition method using speech recognizers based on Hidden Markov Model (HMM) with a combination of techniques to enhance a biped robot control. In the past, Artificial Neural Networks (ANN) and Dynamic Time Wrapping (DTW) were used, however, currently they are less commonly applied to speech recognition systems. This Research confirms that the HMM, an accepted high-performance technique, can be successfully employed to model speech signals. High recognition accuracy can be obtained by using HMMs. Apart from speech modeling techniques, multiple feature extraction methods have been studied to find speech stresses caused by emotions and the environment to improve speech recognition rates. The procedure consisted of 2 parts: one is recognizing robot commands using multiple HMM recognizers, and the other is sending recognized commands to control a robot. In this paper, a practical voice recognition system which can recognize a lot of task commands is proposed. The proposed system consists of a general purpose microprocessor and a useful voice recognition processor which can recognize a limited number of voice patterns. By simulation and experiment, it was illustrated the reliability of voice recognition rates for application of the manufacturing process.

• 한국측량학회지
• /
• 제37권3호
• /
• pp.119-127
• /
• 2019

본 연구에서는 1/1,000 수치지형도 및 정밀도로지도 제작에 있어서 도로 레이어를 구성하고 있는 교통안전표지 및 도로표지의 제작 공정에 있어서 딥러닝의 적용방안을 탐색하였다. 딥러닝의 이미지 분류에서 활용하는 전수학습을 이용하여 취득한 영상에 대한 학습자료 구축을 통해 도로 표지정보의 자동분류를 수행하였다. 분석결과 주의, 규제, 지시, 보조는 촬영된 이미지의 품질 및 형태 등 여러 가지 요소에 의해 정확도가 불규칙하게 나타났지만, 안내표지의 경우는 정확도가 97% 이상으로 높게 나타났다. 수치지도제작에 있어 전수학습을 이용한 이미지 자동분류 방식은 교통안전표지를 포함한 다양한 레이어들에 대한 자료 취득과 분류에 있어서 활용이 증가할 것으로 기대한다.

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 2010년도 춘계학술발표대회 초록집
• /
• pp.60-60
• /
• 2010

Since the curved hull plate was made by a series of manufacturing process including cold bending, manual local heating and correction work, the accuracy of curved plate strongly depends on the proficiency of worker. So the demands on the automatic local heating system for curved hull plate have continuously increased and the various researches relevant to it have been performed. Generally, the heat sources used for local heating were flame and induction heat. In terms of initial cost, flame heating is in a better favorable position than induction heating. However, from the viewpoint of the control of heat, induction heating has more advantage. So the various researches related to apply the induction heating to the automatic forming system has been performed. The purpose of this study is to establish the proper capacity of high frequency induction heating system for forming the curved hull plate. In order to do it, the proper coil shape for local heating was designed and the efficiency of induction heating system was determined by comparing of temperature results obtained by FEA and experiment. With the results, the extensive FEA was performed to identify the effect of heated plate dimension, cooling method and the capacity of induction heating system on the amount of heat loss introduced by induction heating. Based on the results, the proper capacity of high frequency induction heating system was proposed.

• 한국정밀공학회지
• /
• 제27권7호
• /
• pp.117-122
• /
• 2010

Recently, aspheric glass lens molding core is fabricated with tungsten carbide(WC). If molding core is fabricated with silicon carbide(SiC), SiC coating process, which must be carried out before the Diamond-Like Carbon(DLC) coating can be eliminated and thus, manufacturing time and cost can be reduced. Diamond Like Carbon(DLC) is being researched in various fields because of its high hardness, high elasticity, high durability, and chemical stability and is used extensively in several industrial fields. Especially, the DLC coating of the molding core surface used in the fabrication of a glass lens is an important technical field, which affects the improvement of the demolding performance between the lens and molding core during the molding process and the molding core lifetime. Because SiC is a material of high hardness and high brittleness, it can crack or chip during grinding. It is, however, widely used in many fields because of its superior mechanical properties. In this paper, the grinding condition for silicon carbide(SiC) was developed under the grinding condition of tungsten carbide. A silicon carbide molding core was fabricated under this grinding condition. The measurement results of the SiC molding core were as follows: PV of 0.155 ${\mu}m$(apheric surface) and 0.094 ${\mu}m$(plane surface), Ra of 5.3 nm(aspheric surface) and 5.5 nm(plane surface).

• 경영과정보연구
• /
• 제22권
• /
• pp.117-136
• /
• 2007

The characteristic of this study is to compare and analyze costing information from ABC cost accounting system after ABC cost accounting system is designed and implemented from the manufacturing company's traditional cost accounting system through field researches. This is different from previous researches which investigate surveys or adoption procedures and contents of some companies already adopting ABC cost accounting system. Statistically, differences between costing information are not really similar. However, the advantage of ABC cost accounting system is to reduce some activities which do not well contribute creating value after analyzing productions and supporting activities of the company, and dividing into two groups, activities creating value and non-creating value. Therefore, the cost accounting information of ABC cost accounting system is very useful system to offer valuable information for the management of the company. The accuracy of information of ABC cost accounting system depends on setting up the central point of activities and implementing cost drivers. In particular, when it comes to supporting activities, choosing cost accounting grivers which are highly relevant to producing products and collecting data for cost accounting drivers is really difficult. This is the limitation of this study. In other words, when implementing cost accounting drivers of ABC cost accounting system, aconceptual framework is different from applying to the real producing place. Therefore, when implementing on ABC cost accounting system, future researches are needed to find cost accounting drivers which are more close to the theoretical model, and implement ABC cost accounting system which can collects relevant data.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2014년도 춘계학술대회
• /
• pp.513-515
• /
• 2014

차세대 영상기술인 Ultra High Definition(이후 UHD)는 보다 높은 임장감을 향해온 제작자와 수용자의 오랜 요구 속에서 태동했다. 역사를 통해 입증되듯이 매체의 변화는 세계를 바라보는 관점과 구체적인 콘텐츠의 변화를 가져왔다. 따라서 UHD의 등장도 독자적인 제작기술이 요구되리라 예상되는 것이다. 이에 본 논문에서는 영상콘텐츠 가운데 다큐멘터리를 중심으로 UHD영상기술에 따른 제작과정의 변화를 연구하고자 한다. 보다 세부적으로 고해상도, 확장된 화면 등의 UHD영상기술이 다큐멘터리 영상제작에서 가져올 변화와 사실성의 전달이라는 다큐멘터리와의 합목적성에 대해 분석하고자 한다. 또한 문제점으로 예상되는 촬영소재의 선택, 방대해진 데이터에 따른 백업과 후반작업 상에서의 개선점에 대해서도 탐구하고자 한다. 이상의 연구계획을 통해 다큐멘터리 제작에서의 UHD영상기술이 가져올 수 있는 발전적 측면을 도출하여 기술의 발전에 따른 콘텐츠 제작의 발전에 기여하고자 한다.

• 한국광학회지
• /
• 제28권2호
• /
• pp.75-82
• /
• 2017

초정밀도를 요구하는 반도체 소자 공정에서 웨이퍼의 위치와 반복정밀도를 파장의 수백분의 일로 오차가 거의 없는 상태에서 제어하기 위해 위치변위 레이저 간섭계가 필요하다. 특히 제조공정에서는 생산단가의 인하압박으로 인해 웨이퍼의 대형화가 시도되고 있고 이에 따라 넓은 변위량을 측정하면서 나노미터 급의 위치 정밀도를 지닌 레이저 간섭계가 더욱 절실하게 요구된다. 이런 기술적인 문제를 해결하기 위해서 간섭계에 사용되는 송수신 광학계에도 특별한 광학적인 고안이 필요하게 된다. 본 논문에서는, 송수신 광학부로서 단순하게 콜리메이팅 렌즈만을 사용하는 기존의 방식 대신에, GRIN 렌즈-콜리메이팅 렌즈-무초점 광학계로 구성되는 새로운 형식의 조금 복잡한 형태의 광학구조를 제안하였고 이를 통해 반사된 후 되돌아와 간섭계로 결합되는 광신호의 효율을 약 100배 정도 높일 수 있었다.

• 한국자동차공학회논문집
• /
• 제23권4호
• /
• pp.388-395
• /
• 2015

The waste gate valve (WGV) for gasoline vehicles operate in a harsh high-temperature environment. Hence, WGVs are typically made of Inconel 713C, which is a type of Ni-based superalloy. Recently, the metal injection molding (MIM) process has attracted considerable attention for parts used under high-temperature conditions. In this study, an MIM analysis for the head and other parts of the WGV is conducted using a commercial CAE program Moldflow. Further, optimal manufacturing conditions are determined by analyzing flow characteristics at various injection times and locations. Moreover, to improve the accuracy of the analysis results, we compare the actual temperature of the mold during injection processing with that observed through the analysis. As the results, metal injection patterns of analysis are well in accord with these of short shot test. And the temperature variations of analysis is also very similar with those of feedstock when metal injection molding.

• 한국정보통신학회논문지
• /
• 제23권11호
• /
• pp.1384-1390
• /
• 2019

본 논문은 머신비전기반 자동검사를 위한 대상객체의 인식방향성 개선 연구로서, 영상카메라에 의한 자동 비전검사의 과정에서 제한성이 따르는 대상 객체의 인식방향성을 개선하는 방법을 제안한다. 이를 통하여 머신비전 자동검사에서 시험대상물의 위치와 방향에 상관없이 검사대상의 영상을 검출할 수 있게 함으로써 별도 검사지그의 필요성을 배제하고 검사과정의 자동화 레벨을 향상시킨다. 본 연구에서는 검사대상으로서 와이어 하네스 제조과정에서 실제 적용할 수 있는 기술과 방법을 개발하여 실제 시스템으로 구현한 결과를 제시한다. 시스템구현 결과는 공인기관의 평가를 통하여, 정밀도, 검출인식도, 재현률 및 위치조정 성공률에서 모두 성공적인 측정결과를 얻었고, 당초 설정하였던 10종류의 컬러구별 능력, 1초 이내 검사시간, 4개 자동모드 설정 등에서도 목표달성을 확인하였다.

• 산업경영시스템학회지
• /
• 제45권4호
• /
• pp.233-239
• /
• 2022

The injection molding process is a process in which thermoplastic resin is heated and made into a fluid state, injected under pressure into the cavity of a mold, and then cooled in the mold to produce a product identical to the shape of the cavity of the mold. It is a process that enables mass production and complex shapes, and various factors such as resin temperature, mold temperature, injection speed, and pressure affect product quality. In the data collected at the manufacturing site, there is a lot of data related to good products, but there is little data related to defective products, resulting in serious data imbalance. In order to efficiently solve this data imbalance, undersampling, oversampling, and composite sampling are usally applied. In this study, oversampling techniques such as random oversampling (ROS), minority class oversampling (SMOTE), ADASYN(Adaptive Synthetic Sampling), etc., which amplify data of the minority class by the majority class, and complex sampling using both undersampling and oversampling, are applied. For composite sampling, SMOTE+ENN and SMOTE+Tomek were used. Artificial neural network techniques is used to predict product quality. Especially, MLP and RNN are applied as artificial neural network techniques, and optimization of various parameters for MLP and RNN is required. In this study, we proposed an SA technique that optimizes the choice of the sampling method, the ratio of minority classes for sampling method, the batch size and the number of hidden layer units for parameters of MLP and RNN. The existing sampling methods and the proposed SA method were compared using accuracy, precision, recall, and F1 Score to prove the superiority of the proposed method.