• Journal of Electrical Engineering and Technology
• /
• 제9권1호
• /
• pp.170-177
• /
• 2014

This paper presents a new method of classification of the induction machine faults using Time Frequency Representation, Particle Swarm Optimization and artificial neural network. The essence of the feature extraction is to project from faulty machine to a low size signal time-frequency representation (TFR), which is deliberately designed for maximizing the separability between classes, a distinct TFR is designed for each class. The feature vectors size is optimized using Particle Swarm Optimization method (PSO). The classifier is designed using an artificial neural network. This method allows an accurate classification independently of load level. The introduction of the PSO in the classification procedure has given good results using the reduced size of the feature vectors obtained by the optimization process. These results are validated on a 5.5-kW induction motor test bench.

• Archives of Metallurgy and Materials
• /
• 제64권3호
• /
• pp.1175-1182
• /
• 2019

In this study, we present a new method for obtaining the parameters of the Johnson-Mehl-Avrami-Kolmogorov equation for dynamic recrystallization grain size. The method consists of finite-element analysis and optimization techniques. An optimization tool iteratively minimizes the error between experimental values and corresponding finite-element solutions. Isothermal backward extrusion of the AA6060 aluminum alloy was used to acquire the main parameters of the equation for predicting DRX grain size. We compared grain sizes predicted using optimized and reference parameters with experimental values from the literature and found better agreement when the optimized parameters were applied.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2004년도 봄 학술발표회 논문집
• /
• pp.151-160
• /
• 2004

Genetic algorithm is the theory of grafting the principle of survival of the fittest in genetics on to the computer algorithm and it is used to solve the optimization problems, especially the shape and size optimization of the structure in Architectural problems. In the size optimization problem discrete variables are used, but series variables have to be used in the shape optimization problem because of the incongruenty. The purpose of this study is to obtain the optimum shape of cable domes by using the real coding genetic algorithm. Generally, the structural performance of the cable domes is influenced very sensitively by pre-stress, geometry and length of the mast because of its flexible characteristic. So, it is very important to decide the optimum shape to get maximum stiffness of cable domes. We use the model to verify the usefulness of this algorithm for shape optimization and analyze the roof system of Seoul Olympic Gymnastic Arena as analytical model of a practical structures. It is confirmed lastly that the optimum shape domes have more stiffness than initial shape ones.

• Structural Engineering and Mechanics
• /
• 제43권6호
• /
• pp.795-821
• /
• 2012

The size and topology of geometrically nonlinear dome structures are optimized thereby minimizing both its entire weight & joint (node) displacements and maximizing load-carrying capacity. Design constraints are implemented from provisions of American Petroleum Institute specification (API RP2A-LRFD). In accordance with the proposed design constraints, the member responses computed by use of arc-length technique as a nonlinear structural analysis method are checked at each load increment. Thus, a penalization process utilized for inclusion of unfeasible designations to genetic search is correspondingly neglected. In order to solve this complex design optimization problem with multiple objective functions, Non-dominated Sorting Genetic Algorithm II (NSGA II) approach is employed as a multi-objective optimization tool. Furthermore, the flexibility of proposed optimization is enhanced thereby integrating an automatic dome generating tool. Thus, it is possible to generate three distinct sphere-shaped dome configurations with varying topologies. It is demonstrated that the inclusion of brace (diagonal) members into the geometrical configuration of dome structure provides a weight-saving dome designation with higher load-carrying capacity. The proposed optimization approach is recommended for the design optimization of geometrically nonlinear dome structures.

• 한국공간구조학회:학술대회논문집
• /
• 한국공간구조학회 2005년도 춘계학술발표회 및 정기총회 2권1호(통권2호)
• /
• pp.246-253
• /
• 2005

The design of structural engineering optimization is to minimize the cost. This problem has many objective functions formulating section and shape as a function of the included discrete variables. simulated annealing, genetic algerian and TABU algorithm are searching methods for optimum values. The object of this reserch is comparing the result of TABU algorithm, and verifying the efficiency of TABU algorithm in structural optimization design field. For the purpose, this study used a solid truss of 25 elements having 10 nodes, and size optimization for each constraint and load condition of Geodesic one, and shape optimization of Cable Dome for verifying spatial structures by the application of TABU algorithm

• Steel and Composite Structures
• /
• 제26권2호
• /
• pp.163-170
• /
• 2018

The purpose of this paper is to present a new and efficient optimization algorithm called Jaya for optimum design of steel grillage structure. Constrained size optimization of this type of structure based on the LRFD-AISC is carried out with integer design variables by using cross-sectional area of W-shapes. The objective function of the problem is to find minimum weight of the grillage structure. The maximum stress ratio and the maximum displacement in the inner point of steel grillage structure are taken as the constraint for this optimization problem. To calculate the moment and shear force of the each member and calculate the joint displacement, the finite elements analysis is used. The developed computer program for the analysis and design of grillage structure and the optimization algorithm for Jaya are coded in MATLAB. The results obtained from this study are compared with the previous works for grillage structure. The results show that the Jaya algorithm presented in this study can be effectively used in the optimal design of grillage structures.

• 한국공간정보시스템학회:학술대회논문집
• /
• 한국공간정보시스템학회 2004년도 춘계 학술발표회 논문집 제1권1호(통권1호)
• /
• pp.43-52
• /
• 2004

The objective of this study is the development of size, shape and topology discrete optimum design algorithm which is based on the genetic algorithms. The algorithm can perform both shape and topology optimum designs of trusses. The developed algerian was implemented in a computer program. For the optimum design, the objective function is the weight of trusses and the constraints are stress and displacement. The basic search method for the optimum design is the genetic algorithms. The algorithm is known to be very efficient for the discrete optimization. The genetic algorithm consists of genetic process and evolutionary process. The genetic process selects the next design points based on the survivability of the current design points. The evolutionary process evaluates the survivability of the design points selected from the genetic process. The efficiency and validity of the developed size, shape and topology discrete optimum design algorithms were verified by applying the algorithm to optimum design examples

• 한국자동차공학회논문집
• /
• 제12권2호
• /
• pp.123-130
• /
• 2004

The automobile suspension system is composed of parts that affect performances of a vehicle such as ride quality, handling characteristics, straight performance and steering effort, etc. Moreover, by using the finite element analysis the cost for the initial design step can be decreased. In the design of a suspension system, usually system vibration and structural rigidity must be considered simultaneously to satisfy dynamic and static requirements simultaneously. In this paper, we consider the weight reduction and the increase of the first eigen-frequency of a suspension part, the upper control arm, especially using topology optimization and size optimization. Firstly, we obtain the initial design to maximize the first eigen-frequency using topology optimization. Then, we apply the multi-objective parameter optimization method to satisfy both the weight reduction and the increase of the first eigen-frequency. The design variables are varying during the optimization process for the multi-objective. Therefore, we can obtain the deterministic values of the design variables not only to satisfy the terms of variation limits but also to optimize the two design objectives at the same time. Finally, we have executed reliability based optimal design on the upper control arm using the Monte-Carlo method with importance sampling method for the optimal design result with 98％ reliability.

• 한국전산구조공학회논문집
• /
• 제14권3호
• /
• pp.277-286
• /
• 2001

자동차 경량화를 지향하는 초경량차체 기술 중에서 합체박판기술을 이용한 수 있는 일련의 최적설계 기법을 제안하고 기존의 자동차 도어 내판에 적용하여 경량화를 수행하였다. 먼저, 내판에 부착되는 보강재를 제거한 후 취약해진 강성을 보강하기 위한 파트 선정을 위해 위상 최적설계를 수행하여 대략적인 파트 분포를 결정하였다. 그 다음 상세설계 단계로서 각 파트의 두께는 치수 최적설계를 이용하여 정하고, 형상 최적설계로 최종 용접선을 결정하였다. 이러한 일련의 최적화를 위해 상용 소프트웨어인 GENESIS가 사용되었다.

• Advances in Computational Design
• /
• 제1권3호
• /
• pp.235-251
• /
• 2016

We have performed a design optimization of a stiffened panel with curvilinear stiffeners using an artificial neural network (ANN) residual kriging based surrogate modeling approach. The ANN residual kriging based surrogate modeling involves two steps. In the first step, we approximate the objective function using ANN. In the next step we use kriging to model the residue. We optimize the panel in an iterative way. Each iteration involves two steps-shape optimization and size optimization. For both shape and size optimization, we use ANN residual kriging based surrogate model. At each optimization step, we do an initial sampling and fit an ANN residual kriging model for the objective function. Then we keep updating this surrogate model using an adaptive sampling algorithm until the minimum value of the objective function converges. The comparison of the design obtained using our optimization scheme with that obtained using a traditional genetic algorithm (GA) based optimization scheme shows satisfactory agreement. However, with this surrogate model based approach we reach optimum design with less computation effort as compared to the GA based approach which does not use any surrogate model.