• Earthquakes and Structures
• /
• 제16권6호
• /
• pp.679-690
• /
• 2019

This paper presents machine learning methods using Support Vector Machine (SVM) and Multilayer Perceptron (MLP) to analyze optimal damper distribution for structural vibration control. Regarding different building structures, a genetic algorithm based optimization method is used to determine optimal damper distributions that are further used as training samples. The structural features, the objective function, the number of dampers, etc. are used as input features, and the distribution of dampers is taken as an output result. In the case of a few number of damper distributions, multi-class prediction can be performed using SVM and MLP respectively. Moreover, MLP can be used for regression prediction in the case where the distribution scheme is uncountable. After suitable post-processing, good results can be obtained. Numerical results show that the proposed method can obtain the optimized damper distributions for different structures under different objective functions, which achieves better control effect than the traditional uniform distribution and greatly improves the optimization efficiency.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 춘계학술대회
• /
• pp.185-188
• /
• 2009

이 논문에서는 PID 알고리즘을 이용하여 시소 시스템의 균형을 위한 위치 제어기를 설계하고자 한다. 시소 시스템은(Seesaw System) 선박 및 항공 역학, 도립진자, 각종 분석, 로봇 시스템 등의 해석에 광범위하게 응용되는 시스템이자 현대 제어 시스템의 이론과 각종 응용문제를 취급할 수 있는 장치이다. 시소 시스템의 경우 시스템이 비선형성이 강한 제어 대상이므로 시스템의 이해와 해석, 그리고 파라미터의 정확한 선정이 필수요소이다. 사용할 시스템 제어 알고리즘에는 간단하고 오랜 역사를 통해 안정성이 보장된 PID 알고리즘과 정확하고 빠른 PID 파라미터 동조에 필요한 연산 최적화 알고리즘인 PSO(Particle Swarm Optimization) 통해 외란이나 제어기의 변화에 빠르게 적응할 수 있도록 하여 성능과 안정성을 보장한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권11호
• /
• pp.5209-5228
• /
• 2016

Device-to-device (D2D) communication underlaying cellular networks can bring significate benefits for improving the performance of mobile services. However, it hinges on elaborate resource sharing scheme to coordinate interference between cellular users and D2D pairs. We formulate a joint mode selection, link allocation and power control optimization problem for D2D communication sharing uplink resources in a multi-user cellular network and consider the efficiency and the fairness simultaneously. Due to the non-convex difficulty, we propose a three-step scheme: firstly, we conduct mode selection for D2D pairs based on a minimum distance metric after an admission control and obtain some cellular candidates for them. And then, a cellular candidate will be paired to each D2D pair based on fairness. Finally, we use Lagrangian Algorithm to formulate a joint power control strategy for D2D pairs and their reused cellular users and a closed-form of solution is derived. Simulation results demonstrate that our proposed algorithms converge in a short time. Moreover, both the sum rate of D2D pairs and the energy efficiency of cellular users are improved.

• Journal of Power Electronics
• /
• 제16권2호
• /
• pp.610-620
• /
• 2016

The compound active clamp zero voltage soft switching (CACZVS) three-phase power factor correction (PFC) converter has many advantages, such as high efficiency, high power factor, bi-directional energy flow, and soft switching of all the switches. Triple closed-loop PI controllers are used for the three-phase power factor correction converter. The control objectives of the converter include a fast transient response, high accuracy, and unity power factor. There are six parameters of the controllers that need to be tuned in order to obtain multi-objective optimization. However, six of the parameters are mutually dependent for the objectives. This is beyond the scope of the traditional experience based PI parameters tuning method. In this paper, an improved chaotic particle swarm optimization (CPSO) method has been proposed to optimize the controller parameters. In the proposed method, multi-dimensional chaotic sequences generated by spatiotemporal chaos map are used as initial particles to get a better initial distribution and to avoid local minimums. Pareto optimal solutions are also used to avoid the weight selection difficulty of the multi-objectives. Simulation and experiment results show the effectiveness and superiority of the proposed method.

• 한국가스학회지
• /
• 제3권2호
• /
• pp.70-76
• /
• 1999

이산화황 배출에 대한 대기 오염 방지법의 엄격한 규제로 인하여 황산제조 업체에서는 가능한 높은 전화율을 얻는 방법에 관심을 갖고 있다. 본 연구에서는 현재 가동하고 있는 황산공장의 이중 접촉식 전환탑 공정에서 전화율을 증가시키고 배출되는 이산화황 가스의 농도를 최소화하기 위하여 매개변수 분석과 공정최적화 방법을 사용하였다. 이중 접촉식 전환탑 공정에 대하여 공급되는 이산화황의 조성, 각 촉매층 도입부의 압력과 온도, 촉매층의 높이의 변화에 대한 전화율 변화를 살펴보기 위해 공정 모델링과 컴퓨터 모사 프로그램을 개발하였다. 이를 통해 삼산화황으로의 최대 전화율과 배출되는 잔여 이산화황 가스 농도의 최소를 위해 촉매층의 도입부의 온도와 촉매층 높이를 최적화하였다. 이 최적치는 높은 전화율을 유지하도록 하는 전환탑 설계와 조업 조건의 지침이 될 것이다.

• 드라이브 ㆍ 컨트롤
• /
• 제21권1호
• /
• pp.46-52
• /
• 2024

The advancement of autonomous driving technology has heightened the importance of Autonomous Mobile Robotics (AMR) within smart factories. Notably, in tasks involving the transportation of heavy objects, the consideration of weight in route optimization and path planning has become crucial. There is ongoing research on local path planning, such as Dijkstra, A^*, and RRT^*, focusing on minimizing travel time and distance within smart factory warehouses. Additionally, there are ongoing simultaneous studies on route optimization, including TSP algorithms for various path explorations and on minimizing energy consumption in mobile robotics operations. However, previous studies have often overlooked the weight of the objects being transported, emphasizing only minimal travel time or distance. Therefore, this research proposes route planning that accounts for the maximum payload capacity of mobile robotics and offers load-optimized path planning for multi-destination transportation. Considering the load, a genetic algorithm with the objectives of minimizing both travel time and distance, as well as energy consumption is employed. This approach is expected to enhance the efficiency of mobility within smart factories.

• Tribology and Lubricants
• /
• 제31권6호
• /
• pp.239-244
• /
• 2015

Chemical mechanical polishing (CMP) is one of the most important processes for enabling sub-14 nm semiconductor manufacturing. Moreover, post-CMP defect control is a key process parameter for the purpose of yield enhancement and device reliability. Due to the complexity of device with sub-14 nm node structure, CMP-induced defects need to be fixed in the CMP in-situ cleaning module instead of during post ex-situ wet cleaning. Therefore, post-CMP in-situ cleaning optimization and cleaning efficiency improvement play a pivotal role in post-CMP defect control. CMP in-situ cleaning module normally consists of megasonic and brush scrubber processes. And there has been an increasing effort for the optimization of cleaning chemistry and brush scrubber cleaning in the CMP cleaning module. Although there have been many studies conducted on improving particle removal efficiency by brush cleaning, these studies do not consider the effects of brush contamination. Depending on the process condition and brush condition, brush cross contamination effects significantly influence post-CMP cleaning defects. This study investigates brush cross contamination effects in the CMP in-situ cleaning module by conducting experiments using 300mm tetraethyl orthosilicate (TEOS) blanket wafers. This study also explores brush pre-treatment in the CMP tool and proposes recipe effects, and critical process parameters for optimized CMP in-situ cleaning process through experimental results.

• Structural Engineering and Mechanics
• /
• 제88권6호
• /
• pp.535-549
• /
• 2023

Deep extreme learning machine (DELM) and multi-verse optimization algorithms (MVO) are hybridized for designing an optimal and adaptive control framework for uncertain buildings. In this approach, first, a robust model predictive control (RMPC) scheme is developed to handle the problem uncertainty. The optimality and adaptivity of the proposed controller are provided by the optimal determination of the tunning weights of the linear programming (LP) cost function for clustered external loads using the MVO. The final control policy is achieved by collecting the clustered data and training them by DELM. The efficiency of the introduced control scheme is demonstrated by the numerical simulation of a ten-story benchmark building subjected to earthquake excitations. The results represent the capability of the proposed framework compared to robust MPC (RMPC), conventional MPC (CMPC), and conventional DELM algorithms in structural motion control.

• Journal of Computing Science and Engineering
• /
• 제9권2호
• /
• pp.39-50
• /
• 2015

Genetic algorithm (GA) and particle swarm optimization (PSO) are two excellent approaches to multimodal optimization problems. However, slow convergence or premature convergence readily occurs because of inappropriate and inflexible evolution. In this paper, a novel optimization algorithm with a flexible grid optimization (FGO) is suggested to provide adaptive trade-off between exploration and exploitation according to the specific objective function. Meanwhile, a uniform agents array with adaptive scale is distributed on the gird to speed up the calculation. In addition, a dominance centroid and a fitness center are proposed to efficiently determine the potential guides when the population size varies dynamically. Two types of subregion division strategies are designed to enhance evolutionary diversity and convergence, respectively. By examining the performance on four benchmark functions, FGO is found to be competitive with or even superior to several other popular algorithms in terms of both effectiveness and efficiency, tending to reach the global optimum earlier. Moreover, FGO is evaluated by applying it to a parameter decision in a least squares support vector machine (LS-SVM) to verify its practical competence.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2004년도 춘계학술대회 논문집
• /
• pp.19-22
• /
• 2004

A scheme of shape optimization by new approximation approach is applied to design of a flow guide in three-dimensional extrusion processes. The optimization scheme is presented to reduce computation time fur the optimization process and applied to an H-section extrusion problem for verifying the efficiency and the usefulness. The object of optimization is to minimize the deviation of exit velocity and control points of a Bezier curve describing the shape of the flow guide are regarded as design variables. The effectiveness of the proposed scheme is then demonstrated through the applied example.