This paper proposes a model predictive controller of robot manipulators using a genetic algorithm to secure the best performance by performing parameter optimization with the genetic algorithm. Genetic algorithm is a natural evolutionary process modeled as a computer algorithm and has excellent performance in global optimization, so it is useful for tuning control parameters. The sliding mode controller and inverse dynamics controller are included in the lower part of the model prediction controller to minimize the problems caused by non-linearity and uncertainty of the robot manipulator. The performance superiority of the proposed method as described above has been confirmed in detail through a simulation study.

PURPOSES : This study aims to develop an algorithm to solve the user equilibrium traffic assignment problem using soft link capacity constraints. This model is used to relax the hard capacity constraints model. METHODS : In the traffic assignment model that imposes the hard capacity constraints, the well-known solution algorithms used are the augmented Lagrange multiplier method and the inner penalty function method. The major drawback of using the hard-capacity constraint model is the feasible solution issue. If the capacities in the network are not sufficient to absorb the flow from the diverged flows through the hard capacity constraints, it might result in no solution; whereas, using a soft capacity constraint model guarantees a feasible solution because the soft capacity constraint model uses the penalization of constraint violation in the objective function. In this study, the gradient projection (GP) algorithm was adapted. RESULTS : Two numerical experiments were conducted to demonstrate the features of the soft capacity constraint model and the computational performance of the solution algorithm. The results revealed that imposing the soft link capacity constraints can ensure convergence. CONCLUSIONS : The proposed model can be easily extended by considering other traffic assignment models, for e.g., non-additive traffic equilibrium problem, stochastic traffic equilibrium model, and, elastic demand traffic equilibrium problem. Furthermore, the model can exist regardless of the sufficient capacity for each O-D pair to cater to their demands.

Recently, due to the aging of workers and the weakening of the labor base in the automobile industry, research on quality inspection methods through ICT(Information and Communication Technology) convergence is being actively conducted. A lot of research has already been done on the development of an automated system for quality inspection in the manufacturing process using image processing. However, there is a limit to detecting defects occurring in the automotive sunroof sealer application process, which is the subject of this study, only by image processing using a general camera. To solve this problem, this paper proposes a system construction method that collects image information using a infrared thermal imaging camera for the sunroof sealer application process and detects possible product defects based on the SVM(Support Vector Machine) algorithm. The proposed system construction method was actually tested and applied to auto parts makers equipped with the sunroof sealer application process, and as a result, the superiority, reliability, and field applicability of the proposed method were proven.

A tilted tall building is actively constructed as landmark structures around world to date. Because lateral displacement responses of a tilted tall building occurs even by its self-weight, reduction of seismic responses is very important to ensure structural safety. In this study, a smart tuned mass damper (STMD) was applied to the example tilted tall building and its seismic response control performance was investigated. The STMD was composed of magnetorheological (MR) damper and it was installed on the top floor of the example building. Control performance of the STMD mainly depends on the control algorithn. Fuzzy logic controller (FLC) was selected as a control algorithm for the STMD. Because composing fuzzy rules and tuning membership functions of FLC are difficult task, evolutionary optimization algorithm (EOA) was used to develop the FLC. After numerical simulations, it has been seen that the STMD controlled by the EOA-optimized FLC can effectively reduce seismic responses fo the tilted tall building.

본 연구에서는 게임 동영상의 고화질 변환이 가능한 초해상화 알고리즘을 제시한다. 본 알고리즘은 오픈 소 스 형태의 GPU에서 제공하는 MMU에서 구현될 수 있도록 희소 행렬 연산을 이용해서 설게된다. 이를 위해 서 일반적인 영상 해상도 향상 방법인 이중 일차 및 이중 삼차 보간 법과 심층 학습에 기반한 초해상화 모 델에서 사용하는 컨볼루션 연산을 희소 행렬 연산으로 변환하는 방법을 제시한다. 이는 각 픽셀에 적용되는 필터를 행렬 곱 형태로 표현하고, 이 행렬을 희소 행렬로 표현함으로써 수행되는데, 이러한 과정을 통해서 연산의 효율성을 추구함으로써 안정적인 초해상화 알고리즘을 제공한다. 이러한 희소행렬 연산 형태로 표현 되는 초해상화 알고리즘은 기존의 라이브러리를 이용해서 구현된 초해상화 알고리즘과 유사한 PSNR과 FPS 를 보인다.

The multi-layered heat source model is a model that can cover most of existing studies and can be defined with a simple formula. Based on the methodology performed in previous studies, the welding heat source was found through experiments and FEM under the welding power conditions of three cases and the parameters of the welding heat source were analyzed according to the welding power. In this study, parameters of fiber laser welding heat source according to welding power were searched through optimization algorithm and finite element analysis, and the correlation was analyzed. It was confirmed that the concentration of the welding heat source in the 1st layer was high regardless of the welding power, and it was confirmed that the concentration of the welding heat source in the 5th layer (last layer) increased as the welding power increased. This reflects the shape of the weld bead that appears during actual fiber laser welding, and it was confirmed that this study represents the actual phenomenon.

본 연구는 얼음결정체의 형성을 막고자 step-cooling 알고리즘을 적용하여 갈치를 과냉각 저장하였다. 저장의 신선도 유지효과를 확인하기 위해 냉장 및 냉동 저장된 갈치와의 신선도 비교평가를 실시하였다. 과냉각 저장은 냉장 저장과 비교하였을 때, 일반세균수와 단백질 부패로 인해 그 함량이 증가되는 VBN, TMA 값에서 비교적 작은 값을 보여 품질 유지에 효과를 나타내었다. 또한, 냉동 저장과 비교하였을 때, pH, VBN 및 TMA에서는 저장이 종료된 12일을 기준으로 차이를 크게 나타내지 않았다. 일반 세균수에서는 9일차까지 비슷한 값을 유지하였으며, 12일 차에서는 과냉각 시료가 높은 값을 보였다. 이를 통해, 과 냉각 저장이 미생물 생장을 최소화하고 단백질 부패를 지연시키는데 효과가 있다고 사료된다. 장기저장에서는 크게 영향을 미치지는 않았으나, 단기저장 관점에서는 냉장 저장보다 과냉각 저장이 갈치의 품질을 유지하는데 많은 장점을 가질 것으로 판단된다.

전역 최적화 문제의 해를 유전 알고리즘을 사용하여 얻어 완전파형역산을 수행하고 층상 반무한체의 물성치를 추정하는 기법을 제안한다. 조화 수직 하중이 작용하는 층상 반무한체의 동적 응답을 측정하고, 이를 추정 물성치를 사용하여 계산된 응답과 비교한다. 응답의 추정치는 mid-point integrated finite element와 perfectly matched discrete layer를 사용하여 구성된 thin-layer model로부터 얻는다. 전역 최적화 문제의 목적 함수는 응답의 관측치와 추정치의 차이에 대한 L2-norm으로 계산된다. 유전 알고리즘을 사용하여 전역 최적화 문제의 해를 구하여 완전파형역산을 수행한다. 제안된 기법을 기본 진동 모드 뿐만이 아니라 고차 진동 모드도 우세한 다양한 층상 반무한 매질에 적용하여, 측정치가 잡음을 포함하지 않는 경우와 포함하는 경우 모두에 대해서 제안된 완전파형역산 기법은 층상 반무한체의 재료 특성을 추정하는데 적합함을 확인할 수 있다.

PURPOSES : This study verifies the stability and uniqueness of the traffic assignment algorithm. METHODS : The traffic assignment step of the four-phase traffic demand model is an important step in determining the traffic volume of the link in the process of distributing the O/D traffic volume on each link. In this step, primarily, a link-based algorithm based on user equilibrium has been used. The typical link-based algorithm, FWA, is known to provide uniqueness and stability, in theory, regarding traffic assignment results. However, recent studies have raised the controversy that, in reality, the FWA is less stable and unique depending on the termination criterion applied to the FWA in the traffic assignment step. Stability tests and proportionality tests were conducted for the application of algorithms to widely used commercial software (for example, EMME, CUBE, and TransCAD). RESULTS : According to this study, the uniqueness and stability of the FWA were not followed in the process of actual traffic assignment, unlike the theory. CONCLUSIONS : The traffic assignment model has essentially the same result when the optimum level is reached, irrespective of the program and traffic allocation techniques used. Therefore, efforts will be required to recognize limitations in practice and to produce stable results at an appropriate level when predicting traffic demand, traffic volume, benefits, and feasibility studies using a traffic allocation model.

PURPOSES : This study aims to investigate the factors that affect the practical condition of the convergence and convergence behaviors of the asymmetric transportation equilibrium problem (ATEP). METHODS : To achieve this objective, a real network experiment is critical because the crux of the problem associated with the ATEP is the difficulty of verifying the unique condition in real networks owing to asymmetric modeling. The study employed a numerical approach to deal with this problem because analytical derivation based on small networks has a limitation in extending its findings to practical applications. The study addressed the problems using large real networks and different types of interactions, including links and modes. An investigation of the factors that have the potential to affect the convergence of the problem was conducted with the solution algorithm, which is the double projection method. RESULTS : The study presented a partial answer to the question of whether the ATEP's convergence condition is too strong. In link interactions, demand intensities and symmetric features within the cost function along with the network configuration were determined to relax the convergence condition. In mode interactions, the degree of overlap of the route composition and the controlled asymmetric interactions in the cost function were determined to affect the convergence condition. CONCLUSIONS : The results suggested that the modeling of link interactions for a more complicated transportation system design enabled the modeling of complex asymmetric interactions as long as the demand intensity of the network was not strong. In the case of mode interactions, whereas it was not possible to control the route composition, it was considered possible to a degree where the use of a distinct route was observed for each class (for example, designated truck lanes).

최근의 기후변화는 연안에서 더욱 가속화되고 있어 연안에서의 해양 환경변화 감시의 중요성이 커지고 있다. 클로로필-a 농도는 해양 환경 변화의 중요한 지표 중 하나로 수십년 동안 여러 해색 위성을 통해 전구 해양 표층의 클로 로필-a 농도가 산출되었으며 다양한 연구 분야에 활용되었다. 하지만 연안 해역의 탁한 해수는 외해의 맑은 해수와는 구별되는 구성 성분과 광학적 특성으로 인해 나타나는 심각한 오차 때문에 일반적으로 사용되는 전지구 대양을 위하여 만들어진 클로로필-a 농도 알고리즘은 연안 해역에 대입할 수 없다. 또한 연안 해역은 해역에 따라 성분과 특성이 크게 달라져 통일된 하나의 알고리즘을 제시하기 어렵다. 이러한 문제점을 극복하기 위하여 연안의 탁도가 높은 해역에서는 구성 성분과 광학적 변동 특성을 고려한 다양한 알고리즘들이 개발되어 사용되어 왔다. 클로로필-a 농도 산출 알고리즘은 크게 경험적 알고리즘, 반해석적 알고리즘, 기계학습을 활용한 알고리즘 등으로 나눌 수 있다. 해수의 반사 스펙트 럼에 기반한 청색-녹색 밴드 비율이 기본적인 형태로 주로 사용된다. 반면 탁한 해수를 위해 개발된 알고리즘은 연안 해역에 존재하는 용존 유기물과 부유물의 영향을 상쇄시키기 위한 방식으로 녹색-적색 밴드 비율, 적색-근적외 밴드 비 율, 고유한 광학적 특성 등을 사용한다. 탁한 해수에서의 신뢰성 있는 위성 클로로필-a 농도 산출은 미래의 연안 해역을 관리하고 연안 생태 변화를 감시하는데 필수적이다. 따라서 본 연구는 탁도가 높은 Case 2 해수에서 활용되어온 알고리즘들을 요약하고, 한반도 주변해역의 모니터링과 연구에 대한 문제점을 제시한다. 또한 다분광 및 초분광 센서의 개발로 더욱 정확하고 다양한 해색 환경을 이해할 수 있는 미래의 해색 위성에 대한 발전 전망도 제시한다.

A smart tuned mass damper (TMD) is widely studied for seismic response reduction of various structures. Control algorithm is the most important factor for control performance of a smart TMD. This study used a Deep Deterministic Policy Gradient (DDPG) among reinforcement learning techniques to develop a control algorithm for a smart TMD. A magnetorheological (MR) damper was used to make the smart TMD. A single mass model with the smart TMD was employed to make a reinforcement learning environment. Time history analysis simulations of the example structure subject to artificial seismic load were performed in the reinforcement learning process. Critic of policy network and actor of value network for DDPG agent were constructed. The action of DDPG agent was selected as the command voltage sent to the MR damper. Reward for the DDPG action was calculated by using displacement and velocity responses of the main mass. Groundhook control algorithm was used as a comparative control algorithm. After 10,000 episode training of the DDPG agent model with proper hyper-parameters, the semi-active control algorithm for control of seismic responses of the example structure with the smart TMD was developed. The simulation results presented that the developed DDPG model can provide effective control algorithms for smart TMD for reduction of seismic responses.

Most of the open-source decision tree algorithms are based on three splitting criteria (Entropy, Gini Index, and Gain Ratio). Therefore, the advantages and disadvantages of these three popular algorithms need to be studied more thoroughly. Comparisons of the three algorithms were mainly performed with respect to the predictive performance. In this work, we conducted a comparative experiment on the splitting criteria of three decision trees, focusing on their interpretability. Depth, homogeneity, coverage, lift, and stability were used as indicators for measuring interpretability. To measure the stability of decision trees, we present a measure of the stability of the root node and the stability of the dominating rules based on a measure of the similarity of trees. Based on 10 data collected from UCI and Kaggle, we compare the interpretability of DT (Decision Tree) algorithms based on three splitting criteria. The results show that the GR (Gain Ratio) branch-based DT algorithm performs well in terms of lift and homogeneity, while the GINI (Gini Index) and ENT (Entropy) branch-based DT algorithms performs well in terms of coverage. With respect to stability, considering both the similarity of the dominating rule or the similarity of the root node, the DT algorithm according to the ENT splitting criterion shows the best results.