• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.44 no.11
• /
• pp.989-996
• /
• 2016

This paper intends to develop the rotor track and balance (RTB) algorithm using the nonlinear RTB models and a real-coded hybrid genetic algorithm. The RTB response data computed using the trim solutions with variation of the adjustment parameters have been used to build nonlinear RTB models based on the quadratic interpolation functions. Nonlinear programming problems to minimize the track deviations and the airframe vibration responses have been formulated to find optimum settings of balance weights, trim-tab deflections, and pitch-link lengths of each blade. The results are efficiently resolved using the real-coded genetic algorithm hybridized with the particle swarm optimization techniques for convergence acceleration. The nonlinear RTB models and the optimized RTB parameters have been compared with those computed using the linear models to validate the proposed techniques. The results showed that the nonlinear models lead to more accurate models and reduced RTB responses than the linear counterpart.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.3
• /
• pp.215-222
• /
• 2001

Neural network based models of semiconductor manufacturing processes have been shown to offer advantages in both accuracy and generalization over traditional methods. However, model development is often complicated by the fact that back-propagation neural networks contain several adjustable parameters whose optimal values unknown during training. These include learning rate, momentum, training tolerance, and the number of hidden layer neurOnS. This paper presents an investigation of the use of genetic algorithms (GAs) to determine the optimal neural network parameters for the modeling of plasma-enhanced chemical vapor deposition (PECVD) of silicon dioxide films. To find an optimal parameter set for the neural network PECVD models, a performance index was defined and used in the GA objective function. This index was designed to account for network prediction error as well as training error, with a higher emphasis on reducing prediction error. The results of the genetic search were compared with the results of a similar search using the simplex algorithm.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.315-316
• /
• 2007

This paper presents a new methodology to improve movement database for a humanoid robot. The database is initially full of human motions so that the kinetics characteristics of human movement are immanent in it. then, the database is updated to the pseudo-optimal motions for the humanoid robot to perform more natural motions, which contain the kinetics characteristics of robot. for this, we use the evolutionary algorithm. the methodology consists of two processes : (1) the offline imitation learning of human movement and (2) the online generation of natural motion. The offline process improve the initial human motion database using the evolutionary algorithm and inverse dynamics-based optimization. The optimization procedure generate new motions using the movement primitive database, minimizing the joint torque. This learning process produces a new database that can endow the humanoid robot with natural motions, which requires minimal torques. In online process, using the linear combination of the motion primitive in this updated database, the humanoid robot can generate the natural motions in real time. The proposed framework gives a systematic methodology for a humanoid robot to learn natural motions from human motions considering dynamics of the robot. The experiment of catching a ball thrown by a man is performed to show the feasibility of the proposed framework.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.1
• /
• pp.560-567
• /
• 2020

Incremental Sheet Forming (ISF) is a unique sheet-forming technique. The process is a die-less sheet metal manufacturing process for rapid prototyping and small batch production. In the forming process, the critical parameters affecting the formability of sheet materials are the tool diameter, step depth, feed rate, spindle speed, etc. This study examined the effects of these parameters on the formability in the forming of the varying wall angle conical frustum model for a pure Al3004 sheet with 1mm in thickness. Using Minitab software based on Back Propagation Neural Network (BPNN) and Genetic Algorithm (GA), a second order mathematical prediction model was established to predict and optimize the wall angle. The results showed that the maximum forming angle was 87.071° and the best combination of these parameters to give the best performance of the experiment is as follows: tool diameter of 6mm, spindle speed of 180rpm, step depth of 0.4mm, and feed rate of 772mm/min.

• Journal of Microbiology and Biotechnology
• /
• v.31 no.5
• /
• pp.717-725
• /
• 2021

This study aimed to optimize medium composition and culture conditions for enhancing the biomass of Lactobacillus plantarum 200655 using statistical methods. The one-factor-at-a-time (OFAT) method was used to screen the six carbon sources (glucose, sucrose, maltose, fructose, lactose, and galactose) and six nitrogen sources (peptone, tryptone, soytone, yeast extract, beef extract, and malt extract). Based on the OFAT results, six factors were selected for the Plackett-Burman design (PBD) to evaluate whether the variables had significant effects on the biomass. Maltose, yeast extract, and soytone were assessed as critical factors and therefore applied to response surface methodology (RSM). The optimal medium composition by RSM was composed of 31.29 g/l maltose, 30.27 g/l yeast extract, 39.43 g/l soytone, 5 g/l sodium acetate, 2 g/l K₂HPO₄, 1 g/l Tween 80, 0.1 g/l MgSO₄·7H₂O, and 0.05 g/l MnSO₄·H₂O, and the maximum biomass was predicted to be 3.951 g/l. Under the optimized medium, the biomass of L. plantarum 200655 was 3.845 g/l, which was similar to the predicted value and 1.58-fold higher than that of the unoptimized medium (2.429 g/l). Furthermore, the biomass increased to 4.505 g/l under optimized cultivation conditions. For lab-scale bioreactor validation, batch fermentation was conducted with a 5-L bioreactor containing 3.5 L of optimized medium. As a result, the highest yield of biomass (5.866 g/l) was obtained after 18 h of incubation at 30℃, pH 6.5, and 200 rpm. In conclusion, mass production by L. plantarum 200655 could be enhanced to obtain higher yields than that in MRS medium

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2005.04a
• /
• pp.209-216
• /
• 2005

The controller that can control the smart base isolation system consisting of M damper and friction pendulum systems(FPS) is developed in this study. A fuzzy logic controller (FLC) is used to modulate the M damper force because the FLC has an inherent robustness and ability to handle non-linearities and uncertainties. A genetic algorithm (GA) is used for optimization of the FLC. When earthquake excitations are applied to the structures equipped with smart base isolation system, the relative displacement at the isolation level as well as the acceleration of the structure should be regulated under appropriate level. Thus, NSGA-II(Non-dominated Sorting Genetic Algorithm) is employed in this study as a multi-objective genetic algorithm to meet more than two control objectives, simultaneously. NSGA-II is used to determine appropriate fuzzy control rules as well to adjust parameters of the membership functions. Effectiveness of the proposed method for optimal design of the FLC is judged based on computed responses to several historical earthquakes. It has been shown that the proposed method can efficiently find Pareto optimal sets that can reduce both structural acceleration and base drift from numerical studies.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.2 no.2
• /
• pp.159-165
• /
• 2002

This paper proposes a GA and Gradient Descent Method-based method for choosing an appropriate set of fuzzy rules for classification problems. The aim of the proposed method is to fond a minimum set of fuzzy rules that can correctly classify all training patterns. The number of inference rules and the shapes of the membership functions in the antecedent part of the fuzzy rules are determined by the genetic algorithms. The real numbers in the consequent parts of the fuzzy rules are obtained through the use of the descent method. A fitness function is used to maximize the number of correctly classified patterns, and to minimize the number of fuzzy rules. A solution obtained by the genetic algorithm is a set of fuzzy rules, and its fitness is determined by the two objectives, in a combinatorial optimization problem. In order to demonstrate the effectiveness of the proposed method, computer simulation results are shown.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2853-2873
• /
• 2013

Over the last few years, one of the most common purposes of smart homes is to provide human centric services in the domain of u-healthcare by analyzing inhabitants' daily living. Currently, the major challenges in activity recognition include the reliability of prediction of each classifier as they differ according to smart homes characteristics. Smart homes indicate variation in terms of performed activities, deployed sensors, environment settings, and inhabitants' characteristics. It is not possible that one classifier always performs better than all the other classifiers for every possible situation. This observation has motivated towards combining multiple classifiers to take advantage of their complementary performance for high accuracy. Therefore, in this paper, a method for activity recognition is proposed by optimizing the output of multiple classifiers with Genetic Algorithm (GA). Our proposed method combines the measurement level output of different classifiers for each activity class to make up the ensemble. For the evaluation of the proposed method, experiments are performed on three real datasets from CASAS smart home. The results show that our method systematically outperforms single classifier and traditional multiclass models. The significant improvement is achieved from 0.82 to 0.90 in the F-measures of recognized activities as compare to existing methods.

• International Journal of Precision Engineering and Manufacturing
• /
• v.1 no.1
• /
• pp.62-70
• /
• 2000

The design of gear train is a kind of mixed problems which have to determine various types of design variables; i,e., continuous, discrete, and integer variables. Therefore, the most common practice of optimum design using the derivative of objective function has difficulty in solving those kinds of problems and the optimum solution also depends on initial guess because there are many sophisticated constrains. In this study, the Genetic Algorithm is introduced for the optimum design of gear trains to solve such problems and we propose a genetic algorithm based gear design system. This system is applied for the geometrical volume(size) minimization problem of the two-stage gear train and the simple planetary gear train to show that genetic algorithm is better than the conventional algorithm solving the problems that have continuous, discrete, and integer variables. In this system, each design factor such as strength, durability, interference, contact ratio, etc. is considered on the basis of AGMA standards to satisfy the required design specification and the performance with minimizing the geometrical volume(size) of gear trains

• Journal of the Optical Society of Korea
• /
• v.11 no.4
• /
• pp.162-172
• /
• 2007

Scanning Laser Optical Tweezers(SLOT) is an optical instrument frequently employed on a microscope with laser being delivered through its various ports. In most SLOT systems, a mechanical tilt stage with a mirror on top is used to dynamically move the laser focal point in two-dimensions. The focal point acts as a tweezing spot, trapping nearby microscopic objects. By adding a mechanical translational stage with a lens, SLOT can be expanded to work in three-dimensions. When two mechanical stages operate together, the focal point can address a closed three-dimensional volume that we call a workspace. It would be advantageous to have a large workspace since it means one can trap and work on multiple objects without interruptions, such as translating the microscope stage. However, previous studies have paid less consideration of the volumetric size of the workspace. In this paper, we propose a new method for designing a SLOT such that its workspace is maximized through optimization. The proposed method utilizes a matrix based ray tracing method and genetic algorithm(GA). To demonstrate the performance of the proposed method, experimental results are shown.