• ETRI Journal
• /
• 제44권5호
• /
• pp.805-815
• /
• 2022

The model-based evolutionary algorithms are divided into three groups: estimation of distribution algorithms, inverse modeling, and surrogate modeling. Existing inverse modeling is mainly applied to solve multi-objective optimization problems and is not suitable for many-objective optimization problems. Some inversed-model techniques, such as the inversed-model of multi-objective evolutionary algorithm, constructed from the Pareto front (PF) to the Pareto solution on nondominated solutions using a random grouping method and Gaussian process, were introduced. However, some of the most efficient inverse models might be eliminated during this procedure. Also, there are challenges, such as the presence of many local PFs and developing poor solutions when the population has no evident regularity. This paper proposes inverse modeling using random forest regression and uniform reference points that map all nondominated solutions from the objective space to the decision space to solve many-objective optimization problems. The proposed algorithm is evaluated using the benchmark test suite for evolutionary algorithms. The results show an improvement in diversity and convergence performance (quality indicators).

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.42.2-42
• /
• 2002

We discuss a neural network solver for the inverse optimization problem. The problem is that find functional relations between input and output data, which are include defects. Finding the relations, predictions of the defect parts are also required. The part of finding the defects in the input data is an inverse problem . We consider the meanings to solve the problem on the neural network system at first. Next, we consider the network structure of the system, the learning scheme of the network, and at last, examine the precision on the numerical calculations. In the paper, we proposed the high-precision learning method for plural three-layer neural network system that is series-connect...

• 대한기계학회논문집A
• /
• 제24권7호
• /
• pp.1753-1762
• /
• 2000

An inverse method is presented to obtain material's flow properties by using small punch test. This procedure employs, as the objective function of inverse analysis, the balance of measured load-di splacement response and calculated one during deformation. In order to guarantee convergence to global minimum, simulated annealing method was adopted to optimize the current objective function. In addition, artificial neural network was used to predict the load-displacement response under given material parameters which is the most time consuming and limits applications of global optimization methods to these kinds of problems. By implementing the simulated annealing for optimization along with calculating load-displacement curve by neural network, material parameters were identified irrespective of initial values within very short time for simulated test data. We also tested the present method for error-containing experimental data and showed that the flow properties of material were well predicted.

• Structural Engineering and Mechanics
• /
• 제45권3호
• /
• pp.391-410
• /
• 2013

A numerical method is presented here to detect and assess structural damages from changes in natural frequencies using Ant Colony Optimization (ACO) algorithm. It is possible to formulate the inverse problem in terms of optimization and then to utilize a solution technique employing ACO to assess the damage/damages of structures using natural frequencies. The laboratory tested data has been used to verify the proposed algorithm. The study indicates the potentiality of the developed code to solve a wide range of inverse identification problems in a systematic manner. The developed code is used to assess damages of beam like structures using a first few natural frequencies. The outcomes of the simulated results show that the developed method can detect and estimate the amount of damages with satisfactory precision.

• 대한기계학회논문집B
• /
• 제34권7호
• /
• pp.679-688
• /
• 2010

본 연구에서는 기존의 역열전달 문제(inverse heat transfer problem)와 같이 역해석(inverse analysis)을 통해 미지의 파라미터를 추정(estimation)하는 개념을 복잡한 연소문제에 도입하였다. 기존의 연구에서는 역해석 기법을 연소문제 자체에 보다는 대부분 연소현상을 동반한 복사열전달과 같은 역열전달 문제에 국한해서 적용하고 있기 때문에, 열전달 문제에 한정되어 사용되고 있는 기존의 역해석을 새로운 공학문제에 확장하여 적용함과 동시에 효율적인 연소기 설계 및 최적화 개념을 제시하는데 본 연구의 의의가 있다고 할 수 있다. 이를 위해 실제적으로 많이 사용하고 있는 축대칭 원통형 연소기 내부로 주입되는 메탄($CH_4$)과 산소($O_2$) 성분의 초기 질량분율 값을 연소기 입구 근방에서 측정한 개스의 온도 데이터를 이용하여 역추정하였다. 이때, 복잡한 확산지배 연소 현상을 효율적으로 역해석하기 위해 최적화 방법 중의 하나인 반발 입자 군집 최적화 방법을 역해석 기법으로 적용하였다.

• Journal of Advanced Marine Engineering and Technology
• /
• 제21권5호
• /
• pp.549-556
• /
• 1997

The inverse heat conduction problems is the calculation of surface heat transfer coefficients by utilizing measured temperature. The numerical technique of finite element analysis and optimizition is introduced to calculate temperatures and heat transfer coefficients. The calculated heat transfer coefficients and temperature distribution are good agreement with the results of direct analysis. The inverse method has been applied to the control valve of nuclear power plant.

• Management Science and Financial Engineering
• /
• 제19권1호
• /
• pp.25-28
• /
• 2013

Consider the inverse bin-packing number problem. Given a set of items and a prescribed number K of bins, the inverse bin-packing number problem, IBPN for short, is concerned with determining the minimum perturbation to the item-size vector so that all the items can be packed into K bins or less. It is known that this problem is NP-hard (Chung, 2012). In this paper, we investigate some special cases of IBPN that can be solved in polynomial time. We propose an optimal algorithm for solving the IBPN instances with two distinct item sizes and the instances with large items.

• Journal of applied mathematics & informatics
• /
• 제23권1_2호
• /
• pp.461-470
• /
• 2007

Parameter identification is studied in viscoelastic rods by solving an inverse problem numerically. The material properties of the rod, which appear in the constitutive relations, are recovered by optimizing an objective function constructed from reference strain data. The resulting inverse algorithm consists of an optimization algorithm coupled with a corresponding direct algorithm that computes the strain fields given a set of material properties. Numerical results are presented for two model inverse problems; (i)the effect of noise in the reference strain fields (ii) the effect of minimal reference data in space and/or time data.

• 한국유체기계학회 논문집
• /
• 제14권1호
• /
• pp.34-41
• /
• 2011

Fire characteristics can be analyzed more realistically by using more accurate properties related to the fire dynamics and one way to acquire these fire properties is to use one of the inverse property estimation techniques. In this study two optimization algorithms which are frequently applied for the inverse heat transfer problems are selected to demonstrate the procedure of obtaining pyrolysis properties of charring material with relatively simple thermal decomposition. Thermal decomposition is occurred at the surface of the charring material heated by receiving the radiative energy from external heat sources and in this process the heat transfer through the charring material is simplified by an unsteady 1-dimensional problem. The basic genetic algorithm(GA) and repulsive particle swarm optimization(RPSO) algorithm are used to find the eight properties of a charring material; thermal conductivity(virgin, char), specific heat(virgin, char), char density, heat of pyrolysis, pre-exponential factor and activation energy by using the surface temperature and mass loss rate history data which are obtained from the calculated experiments. Results show that the RPSO algorithm has better performance in estimating the eight pyrolysis properties than the basic GA for problems considered in this study.

• Journal of Magnetics
• /
• 제16권3호
• /
• pp.240-245
• /
• 2011

A new hybrid ON/OFF method is presented for the fast solution of electromagnetic inverse problems in high frequency domains. The proposed method utilizes both topological sensitivity (TS) and material sensitivity (MS) to update material properties in unit design cells. MS provides smooth design space and stable convergence, while TS enables sudden changes of material distribution when MS slows down. This combination of two sensitivities enables a reduction in total computation time. The TS and MS analyses are based on a variational approach and an adjoint variable method (AVM), which permits direct calculation of both sensitivity values from field solutions of the primary and adjoint systems. Investigation of the formulations of TS and MS reveals that they have similar forms, and implementation of the hybrid ON/OFF method that uses both sensitivities can be achieved by one optimization module. The proposed method is applied to dielectric material reconstruction problems, and the results show the feasibility and effectiveness of the method.