• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 2001.09a
• /
• pp.373-380
• /
• 2001

In this research, a controller design method based on optimization is proposed that can satisfy constraints on maximum responses of building structures subject to ground excitation modeled by partially stationary stochastic process. The class of controllers to be optimized is restricted to LQR. Weighting matrix on controlled outputs is used as design variable. Objective function constraint functions and their gradients are computed parameterizing control gain with Riccati matrix. Full state feedback controllers designed by Proposed optimization method satisfy various design objectives and their necessary maximum control forces are computed fur the production of actuator. Probabilities of maximum responses match statistical data from simulation results well.

• Structural Engineering and Mechanics
• /
• v.24 no.5
• /
• pp.529-541
• /
• 2006

This work gives an application of stochastic techniques for the optimization of stiffened plates in vibration. The search strategy consists of substituting, for finite element calculations in the optimization process, an approximate response from a Rayleigh-Ritz method. More precisely, the paper describes the use of a Rayleigh-Ritz method in creating function approximations for use in computationally intensive design optimization based on genetic algorithms. Two applications are presented; their deal with the optimization of stiffeners on plates by varying their positions, in order to maximize some natural frequencies, while having well defined dimensions. In other words, this work gives the fundamental idea of using a Ritz approximation to the response of a plate in vibration instead of finite element analysis.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.4
• /
• pp.1426-1447
• /
• 2021

The payoff game between task publishers and users in the mobile crowdsensing environment is a hot topic of research. A optimal payoff selection model based on stochastic evolutionary game is proposed. Firstly, the process of payoff optimization selection is modeled as a task publisher-user stochastic evolutionary game model. Secondly, the low-quality data is identified by the data quality evaluation algorithm, which improves the fitness of perceptual task matching target users, so that task publishers and users can obtain the optimal payoff at the current moment. Finally, by solving the stability strategy and analyzing the stability of the model, the optimal payoff strategy is obtained under different intensity of random interference and different initial state. The simulation results show that, in the aspect of data quality evaluation, compared with BP detection method and SVM detection method, the accuracy of anomaly data detection of the proposed model is improved by 8.1% and 0.5% respectively, and the accuracy of data classification is improved by 59.2% and 32.2% respectively. In the aspect of the optimal payoff strategy selection, it is verified that the proposed model can reasonably select the payoff strategy.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.6
• /
• pp.1245-1255
• /
• 2017

The online learning is a process of obtaining the solution for a given objective function where the data is accumulated in real time or in batch units. The stochastic gradient descent method is one of the most widely used for the online learning. This method is not only easy to implement, but also has good properties of the solution under the assumption that the generating model of data is homogeneous. However, the stochastic gradient method could severely mislead the online-learning when the homogeneity is actually violated. We assume that there are two heterogeneous generating models in the observation, and propose the a new stochastic gradient method that mitigate the problem of the heterogeneous models. We introduce a robust mini-batch optimization method using statistical tests and investigate the convergence radius of the solution in the proposed method. Moreover, the theoretical results are confirmed by the numerical simulations.

• Proceedings of the Korean Radioactive Waste Society Conference
• /
• 2008.11a
• /
• pp.429-430
• /
• 2008

• Structural Engineering and Mechanics
• /
• v.42 no.3
• /
• pp.335-352
• /
• 2012

Particle Swarm Optimization (PSO) is a stochastic population based optimization algorithm which has attracted attentions of many researchers. This method has great potentials to be applied to many optimization problems. Despite its robustness the standard version of PSO has some drawbacks that may reduce its performance in optimization of complex structures such as laminated composites. In this paper by suggesting a new variation scheme for acceleration parameters and inertial weight factors of PSO a novel optimization algorithm is developed to enhance the basic version's performance in optimization of laminated composite structures. To verify the performance of the new proposed method, it is applied in two multi-objective design optimization problems of laminated cylindrical. The numerical results from the proposed method are compared with those from two other conventional versions of PSO-based algorithms. The convergancy of the new algorithms is also compared with the other two versions. The results reveal that the new modifications inthe basic forms of particle swarm optimization method can increase its convergence speed and evade it from local optima traps. It is shown that the parameter variation scheme as presented in this paper is successful and can evenfind more preferable optimum results in design of laminated composite structures.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.5 no.6
• /
• pp.37-46
• /
• 2001

In this research, a controller design method based on optimization is proposed that can satisfy constraints on maximum responses of building structures subject to around excitation modeled by partially stochastic process. The class of controllers to be optimized is restricted to LQR. Weighting matrix on controlled outputs is used as design variable. Objective function, constraint functions and their gradients are computed by the parameterization of control gain with Riccati matrix. Full state feedback controllers designed by proposed optimization method satisfy various design objectives and their necessary maximum control forces are computed for the production of actuator. LQG controllers composed of Kalman filter and LQR designed by proposed method perform well with little deterioration. So it is possible to design output feedback controllers satisfying constraints on various maximum responses of structures.

• Journal of the military operations research society of Korea
• /
• v.31 no.2
• /
• pp.28-44
• /
• 2005

The previous studies approach the field artillery fire scheduling problem as deterministic and do not explicitly include information on the potential scenario changes. Unfortunately, the effort used to optimize fire sequences and reduce the total time of engagement is often inefficient as the collected military intelligence changes. Instead of modeling the fire sequencing problem as deterministic model, we consider a stochastic artillery fire scheduling model and devise a solution methodology to integrate possible enemy attack scenarios in the evaluation of artillery fire sequences. The goal is to use that information to find robust solutions that withstand disruptions in a better way, Such an approach is important because we can proactively consider the effects of certain unique scheduling decisions. By identifying more robust schedules, cascading delay effects will be minimized. In this paper we describe our stochastic model for the field artillery fire sequencing problem and offer revised robust stochastic model which considers worst scenario first. The robust stochastic model makes the solution more stable than the general two-stage stochastic model and also reduces the computational cost dramatically. We present computational results demonstrating the effectiveness of our proposed method by EVPI, VSS, and Variances.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.9
• /
• pp.127-134
• /
• 2004

It is difficult to have the existing structural optimization using coupled field analysis from CFD to structure analysis when the structure is influenced of fluid. Therefore in an initial model of this study after doing parameter design from the background of shape using topology optimization. and it is making a approximation formula using by the CFD-structure coupled-field analysis and design of experiment. By using this result, we conducted multi-objective optimization. We could confirm efficiency of stochastic method applicable in the scene of structure reliability design to be needed multi-objective optimization. And we presented a way of design that could overcome the time and space restriction in structural design such as the butterfly valve with the less experiment.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.296-300
• /
• 1997

Recently, the genetic algorithm has been applied to the various types of optimization problems and these attempts have very successfully. However, in most cases on these approaches, there is not given by investigator about to the theoritical analysis. The reason that the analysis of the dynamics for genetic algorithm is not clear, is the probablitic aspect of genetic algorithm. In this paper, we investigate the analysis of the internal dynamics for genetic algorithm using stochastic differential method. In addition, we provide a new genetic algorithm, based on the study of the convergence property for the genetic algorithm.