• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.10
• /
• pp.819-826
• /
• 2001

Genetic algorithms are becoming more popular because of their relative simplicity and robustness. Genetic algorithms are global search techniques for nonlinear optimization. However, traditional genetic algorithms, though robust, are generally not the most successful optimization algorithm on any particular domain because they are poor at hill-climbing, whereas simulated annealing has the ability of probabilistic hill-climbing. Therefore, hybridizing a genetic algorithm with other algorithms can produce better performance than using the genetic algorithm or other algorithms independently. In this paper, we propose an efficient hybrid optimization algorithm named the adaptive random signal-based learning. Random signal-based learning is similar to the reinforcement learning of neural networks. This paper describes the application of genetic algorithms and simulated annealing to a random signal-based learning in order to generate the parameters and reinforcement signal of the random signal-based learning, respectively. The validity of the proposed algorithm is confirmed by applying it to two different examples.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.32 no.2
• /
• pp.109-121
• /
• 2007

This paper focuses on algorithms based on the evolution, which is applied to various optimization problems. Especially, among these algorithms based on the evolution, we investigate the simple genetic algorithm based on Darwin's evolution, the Lamarckian algorithm based on Lamark's evolution and the Baldwin algorithm based on the Baldwin effect and also Investigate the difference among them in the biological and engineering aspects. Finally, through this comparison, we suggest a new algorithm to find more various solutions changing the genotype or phenotype search space and show the performance of the proposed method. Conclusively, the proposed method showed superior performance to the previous method which was applied to the constrained minimum spanning tree problem and known as the best algorithm.

• ETRI Journal
• /
• v.43 no.3
• /
• pp.549-560
• /
• 2021

Cyberattacks are often difficult to identify with traditional signature-based detection, because attackers continually find ways to bypass the detection methods. Therefore, researchers have introduced artificial intelligence (AI) technology for cybersecurity analysis to detect malicious PowerShell scripts. In this paper, we propose a feature optimization technique for AI-based approaches to enhance the accuracy of malicious PowerShell script detection. We statically analyze the PowerShell script and preprocess it with a method based on the tokens and abstract syntax tree (AST) for feature selection. Here, tokens and AST represent the vocabulary and structure of the PowerShell script, respectively. Performance evaluations with optimized features yield detection rates of 98% in both machine learning (ML) and deep learning (DL) experiments. Among them, the ML model with the 3-gram of selected five tokens and the DL model with experiments based on the AST 3-gram deliver the best performance.

• Proceedings of the KSME Conference
• /
• 2001.06d
• /
• pp.771-776
• /
• 2001

By matching a well established fast throughflow code, with standard loss correlations, and an efficient optimization algorithm, a new design system has been developed, which optimizes inlet and exit flow-field parameters for each blade row of a multistage axial flow turbine. The compressible steady state inviscid throughflow code based on streamline curvature method is suitable for fast and accurate flow calculation and performance prediction of a multistage axial flow turbine. A general purpose hybrid constrained optimization package, iSIGHT has been used, which includes the following modules: genetic algorithm, simulated annealing, modified method of feasible directions. The design system has been demonstrated using an example of a 5-stage low pressure steam turbine for 800MW thermal power plant previously designed by HANJUNG. The comparison of computed performance of initial and optimized design shows significant improvement in the turbine efficiency.

• Journal of Electrical Engineering and Technology
• /
• v.4 no.4
• /
• pp.515-520
• /
• 2009

According to the operating characteristics of pump applications, they should exhibit high efficiency and energy saving capabilities throughout the whole operating process. A novel efficiency optimization control strategy is presented here to meet the high efficiency demand of a variable speed Permanent Magnet Synchronous Motor (PMSM). The core of this strategy is the excellent integration of mended maximum torque to the current control algorithm, based on the losses model during the dynamic and the grade search method with changed step by fuzzy logic during the steady. The performance experiments for the control system of a variable speed high efficiency PMSM have been completed. The test results verified that the system can reliably operate with a different control strategy during dynamic and steady operation, and the system exhibits better performance when using the efficiency-optimization control.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.40 no.8
• /
• pp.519-525
• /
• 2016

In a pump, from the performance point of view, it is very important to minimize the shock loss at the inlet of the rotor blades. In this study, the effects of shape and install angle of the inlet guide on the performance of an axial-flow pump are numerically simulated using commercial CFD code, Ansys CFX. Finally, to obtain the optimized shape of the vanes and the install angle of the vanes in the inlet guide under given operating conditions, optimization analysis is conducted using Analysis design exploration based on response surface optimization.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.4
• /
• pp.1417-1426
• /
• 2017

Power system analysis, Non-Convex Economic Dispatch (NED) is considered as an open and demanding optimization problem. Despite the fact that realistic ED problems have non-convex cost functions with equality and inequality constraints, conventional search methods have not been able to effectively find the global answers. Considering the great potential of meta-heuristic optimization techniques, many researchers have started applying these techniques in order to solve NED problems. In this paper, a new and efficient approach is proposed based on imperialist competitive algorithm (ICA). The proposed algorithm which is named multi-operator ICA (MuICA) merges three operators with the original ICA in order to simultaneously avoid the premature convergence and achieve the global optimum answer. In this study, the proposed algorithm has been applied to different test systems and the results have been compared with other optimization methods, tending to study the performance of the MuICA. Simulation results are the confirmation of superior performance of MuICA in solving NED problems.

• The KSFM Journal of Fluid Machinery
• /
• v.14 no.5
• /
• pp.55-62
• /
• 2011

Shape optimization of a Printed circuit heat exchanger (PCHE) has been performed by using three-dimensional Reynolds-Averaged Navier-Stokes (3-D RANS) analysis and surrogate modeling techniques. The objective function is defined as a linear combination of effectiveness of the PCHE term and pressure drop in the cold channels of the PCHE. The cold channel angle and the ellipse aspect ratio of the cold channel are used as design variables for the optimization. Design points are selected through Latin-hypercube sampling. The optimal point is determined through surrogate-based optimization method which uses 3-D RANS analyses at design points. The results of three types of surrogate model are compared each other. The results of the optimizations indicate improved performance in friction loss but low performance in effectiveness than the reference shape.

• Proceedings of the KSME Conference
• /
• 2001.06a
• /
• pp.752-757
• /
• 2001

To reduce stress concentration around the intersection between a spherical pressure vessel and a cylindrical nozzle under various load conditions using less material, the optimization for the distribution of reinforcement has researched. The ranked bidirectional evolutionary structural optimization(R-BESO) method is developed recently, which adds elements based on a rank, and the performance indicator which can estimate a fully stressed model. The R-BESO method can obtain the optimum design using less iteration number than iteration number of the BESO. In this paper, the optimized intersection shape is sought using R-BESO method for a flush and a protruding nozzle. The considered load cases are a radial compression, torque and shear force.

• Phonetics and Speech Sciences
• /
• v.8 no.2
• /
• pp.23-30
• /
• 2016

This paper describes some implementation schemes of CNN in view of mini-batch DNN training for efficient second order optimization. This uses same procedure updating parameters of DNN to train parameters of CNN by simply arranging an input image as a sequence of local patches, which is actually equivalent with mini-batch DNN training. Through this conversion, second order optimization providing higher performance can be simply conducted to train the parameters of CNN. In both results of image recognition on MNIST DB and syllable automatic speech recognition, our proposed scheme for CNN implementation shows better performance than one based on DNN.