가변 극성 플라즈마 아크 (VPPA) 용접 Part 1, 소개 및 이론적 배경

조정호,Jung-Ho, Cho 대한용접접합학회 2012 대한용접·접합학회지 Vol.30 No.3

A Segmentation Algorithm of the Connected Word Speech by Statistical Method

조정호,홍재근,김수중,Cho, Jeong-Ho,Hong, Jae-Keun,Kim, Soo-Joong 대한전자공학회 1989 전자공학회논문지 Vol. No.

本 論文에서는 音聲信號의 音素分割을 위한 統計的인 方法을 硏究하였다. 이 方法은 3個의 AR 모델을 使用하여, 이 中 2個의 모델은 音聲의 스펙트럼 變化前 및 變化後의 安定된 部分에서 求해지고 이들 間의 距離가 커지면 音素가 바뀐 것으로 간주된다. 다른 한 모델은 두 固定 모델 사이에 位置하며 音素間의 境界를 推定하는데 使用된다. 이 音素分割 알고리듬을 連結音에 對해 試驗해 본 結果, 從來의 方法에 비해 音素의 境界點을 좀더 正確히 찾을 수 있고, 또한 過度分割 誤謬도 줄일 수 있었다. A statistical approach for the segmentation of speed signals is described in this paper. The main idea of this algorithm is the use of three AR models. Two fixed models are identified at the stationary parts of the signal before and after the spectral change. Changes are detected when the distance between these two models is high. Another model is located between two fixed models and is used to estimate spectral change time. This segmentation algorithm has been tested with connected words and compared to classical methods. The results showed that it can provide more accurate locations of boundaries of segments and can reduce the amount of oversegmentation.

차체 이음 유발 용접 불량에 대한 분석과 해결 방안

조정호,이중재,배승환,이용기,박경배,김용준,문세민,Cho, Jungho,Lee, Jungjae,Bae, Seunghwan,Lee, Yongki,Park, Kyungbae,Kim, Yongjun,Moon, Semin 대한용접접합학회 2015 대한용접·접합학회지 Vol.33 No.2

The importance of emotional quality of car is getting higher in these days. Noise takes great portion in emotional quality because it is detectable problem with just a few rides. The sources of car noise during operation are various and the related technical issues are vast. Sometimes weldments of auto body are referred as the source of noise and the suspicious weldment shows unsatisfactory welding quality in most cases. In this research, cases of noise making weldments are investigated to figure out the solution for welding quality improvement. They are categorized into several groups in according to the inferred types of the error source then appropriate solutions are suggested. Auto body has weldments of resistance spot welding and gas metal arc welding in general. Therefore the solutions are suggested as adjustment of welding process variables and related machineries. Inevitable error source is also referred which is originated from thermal expansion rate difference between ultra high strength steel and mild steel. This new approach is validated through simple calculation then more concrete investigation with numerical analysis is remained as further works to be done.

신경망 알고리즘을 이용한 아크 용접부 품질 예측

조정호,Cho, Jungho 대한용접접합학회 2013 대한용접·접합학회지 Vol.31 No.3

Artificial neural network (ANN) model is applied to predict arc welding process window for automotive steel plate. Target weldment was various automotive steel plate combination with lap fillet joint. The accuracy of prediction was evaluated through comparison experimental result to ANN simulation. The effect of ANN variables on the accuracy is investigated such as number of hidden layers, perceptrons and transfer function type. A static back propagation model is established and tested. The result shows comparatively accurate predictability of the suggested ANN model. However, it restricts to use nonlinear transfer function instead of linear type and suggests only one single hidden layer rather than multiple ones to get better accuracy. In addition to this, obvious fact is affirmed again that the more perceptrons guarantee the better accuracy under the precondition that there are enough experimental database to train the neural network.

모바일 환경에서 의료 진단 정보 시스템의 구현 및 의료 영상의 적합성 평가

조정호,김광현,Cho, Chung-Ho,Kim, Gwang-Hyun 한국전자통신학회 2015 한국전자통신학회 논문지 Vol.10 No.6

모바일 환경이 널리 확산되면서 최근 의료진단시스템은 기존 시스템의 지역적 한계를 넘어 시공간의 제약을 받지 않고 제공되고 있다. 또한 무선 인터넷 기술과 모바일 이동 통신 기술이 의료 기술과 융합하며 빠르게 보급되어 발전하고 있다. 의료 서비스 이용자는 다양한 종류의 무선 단말기를 이용하여 이동 중 무선망을 통해 의료 서비스를 제공 받을 수 있다. 본 논문에서는 병원 의료영상 진단 정보를 병원내의 시공간을 벗어나 전송, 검색 및 갱신할 수 있는 의료 진단 정보 시스템을 구현하고 평가하였다. DICOM CT영상과 JPEG 2000 CT압축영상의 비교를 통하여 임상적으로 적합한 영상인지를 t-test를 실시하여 통계적으로 평가한 결과 DICOM CT영상의 경우 평균 평가 값이 비교적 임상적 진단에 적합한 영상임을 확인하였다. As the hand-held mobile devices are widely used, they are recently coming into convergence with medical diagnostic systems. Furthermore, the wireless mobile Internet and the various kinds of communication devices are rapidly coming into wide use converging with medical technology. The mobile communication environments can make people get more health care services beyond space and time. In this paper, we implement and evaluate the mobile client and the medical diagnostic information server for transmitting, searching and updating the medical diagnostic information. The DICOM CT image and the compressed JPEG 2000 CT image are statistically evaluated by t-test performance whether those images are clinically appropriate. In the case of the DICOM CT image, we realize that the average value is relatively more appropriate to the clinical diagnosis than the JPEG 2000 CT image.

신경망 알고리즘을 이용한 차체용 강판 아크 용접 조건 도출

조정호,Cho, Jungho 대한용접접합학회 2014 대한용접·접합학회지 Vol.32 No.2

Famous artificial neural network (ANN) is applied to predict proper process window of arc welding. Target weldment is variously combined lap joint fillet welding of automotive steel plates. ANN's system variable such as number of hidden layers, perceptrons and transfer function are carefully selected through case by case test. Input variables are welding condition and steel plate combination, for example, welding machine type, shield gas composition, current, speed and strength, thickness of base material. The number of each input variable referred in welding experiment is counted and provided to make it possible to presume the qualitative precision and limit of prediction. One of experimental process windows is excluded for predictability estimation and the rest are applied for neural network training. As expected from basic ANN theory, experimental condition composed of frequently referred input variables showed relatively more precise prediction while rarely referred set showed poorer result. As conclusion, application of ANN to arc welding process window derivation showed comparatively practical feasibility while it still needs more training for higher precision.

가변 극성 아크의 알루미늄 용접성 향상에 관한 연구

조정호,Cho, Jungho 대한용접접합학회 2014 대한용접·접합학회지 Vol.32 No.1

Low arc weldability of aluminum alloy is enhanced by applying variable polarity TIG and the result is theoretically investigated to figure out the mechanism. Conventionally, it is well known fact that DCEP (reverse polarity) arc is effective on aluminum welding. The reason is due to oxide layer removal by plasma ion bombardment and therefore it is named as cleaning effect. Another fact of polarity characteristic is that DCEN shows higher heat input efficiency therefore conventional variable polarity arc used to apply DCEP portion as small as possible. However, higher DCEP portion shows bigger weldment in this research and it is explained by adopting a theory of arc concentration on oxide layer with tunneling effect which was not clearly mentioned before in several variable polarity TIG welding research. Disagreement between variable polarity TIG welding result and conventional arc polarity theory is rationally explained for the first time with help of electron emission theory.

가변 극성 알루미늄 아크 용접의 이론적 배경 고찰

조정호,이중재,배승환,이용기,박경배,김용준,이준경,Cho, Jungho,Lee, Jungjae,Bae, Seunghwan,Lee, Yongki,Park, Kyungbae,Kim, Yongjun,Lee, Junkyung 대한용접접합학회 2015 대한용접·접합학회지 Vol.33 No.2

Cleaning effect is well known mechanism of oxide layer removal in DCEP polarity. It is also known that DCEN has higher heat input efficiency than DCEP in GTAW process. Based on these two renowned arc theories, conventional variable polarity arc for aluminum welding was set up to have minimum DCEP and maximum DCEN duty ratio to achieve the highest heat input efficiency and weldability increase. However, recent several variable polarity GTA research papers reported unexpected result of proportional relationship between DCEP duty ratio and heat input. The authors also observed the same result then suggested combination of tunneling effect and random walk of cathode spot to fill up the gap between experiment and conventional arc theory. In this research, suggested combinational work of tunneling effect and rapid cathode spot changing is applied to another unexpected phenomena of variable polarity aluminum arc welding. From previous research, it is reported that wider oxide removal range, narrower bead width and shallower penetration depth are observed in thin oxide layered aluminum compared to the case of thick oxide. This result was reported for the first time and it was hard to explain the reason at that time therefore the inference by the authors was hardly acceptable. However, the suggested combinational theory successfully explains the result of the previous report in logical way.

한국 국방 연구개발 프로젝트 일정 관리 및 예측을 위한 Earned Schedule 기법의 적용 효과와 한계 분석

조정호,임재성,Cho, Jungho,Lim, Jaesung 한국군사과학기술학회 2018 한국군사과학기술학회지 Vol.21 No.3

Earned Value Management(EVM) has been used to manage and forecast defense project schedule and cost over the last two decades in the world. However to support the lacking ability of schedule analysis in traditional EVM, earned schedule(ES) has been introduced as a tool to more accurately estimate schedule performance. This paper compares which method EVM or ES, provides more accurate schedule predictors in 32 Korean defense research and development projects. As a result of comparison, the ES method can predict the future schedule more reliably than the EVM method. We also analyze early warning function of schedule performance index considering project duration extension point. Through the analysis results, we confirm that both the EVM and the ES method lack the ability of the early warning in terms of the current schedule management criterion.

가변 극성 플라즈마 아크 (VPPA) 용접 -Part 2, 적용 사례 및 용접 물리

조정호,Cho, Jung-Ho 대한용접접합학회 2012 대한용접·접합학회지 Vol.30 No.4