• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2226-2229
• /
• 2003

A new method is presented to construct a classifier. This was accomplished by combining a generalized regression neural network (GRNN) and a genetic algorithm (GA). The classifier constructed in this way is referred to as a GA-GRNN. The GA played a role of controlling training factors simultaneously. In GA optimization, neuron spreads were represented in a chromosome. The proposed optimization method was applied to a data set, consisted of 4 different promoter sequences. The training and test data were composed of 115 and 58 sequence patterns, respectively. The range of neuron spreads was experimentally varied from 0.4 to 1.4 with an increment of 0.1. The GA-GRNN was compared to a conventional GRNN. The classifier performance was investigated in terms of the classification sensitivity and prediction accuracy. The GA-GRNN significantly improved the total classification sensitivity compared to the conventional GRNN. Also, the GA-GRNN demonstrated an improvement of about 10.1% in the total prediction accuracy. As a result, the proposed GA-GRNN illustrated improved classification sensitivity and prediction accuracy over the conventional GRNN.

• Structural Engineering and Mechanics
• /
• v.61 no.2
• /
• pp.283-293
• /
• 2017

The main contribution of the present paper is to propose an intelligent fuzzy inference system approach for modeling the debonding strength of masonry elements retrofitted with Fiber Reinforced Polymer (FRP). To achieve this, the hybrid of meta-heuristic optimization methods and adaptive-network-based fuzzy inference system (ANFIS) is implemented. In this study, particle swarm optimization with passive congregation (PSOPC) and real coded genetic algorithm (RCGA) are used to determine the best parameters of ANFIS from which better bond strength models in terms of modeling accuracy can be generated. To evaluate the accuracy of the proposed PSOPC-ANFIS and RCGA-ANFIS approaches, the numerical results are compared based on a database from laboratory testing results of 109 sub-assemblages. The statistical evaluation results demonstrate that PSOPC-ANFIS in comparison with ANFIS-RCGA considerably enhances the accuracy of the ANFIS approach. Furthermore, the comparison between the proposed approaches and other soft computing methods indicate that the approaches can effectively predict the debonding strength and that their modeling results outperform those based on the other methods.

• Journal of Ocean Engineering and Technology
• /
• v.25 no.5
• /
• pp.76-81
• /
• 2011

In the shipbuilding industry, accuracy management is one of the keys for strengthening competitiveness. However, ship block errors are unavoidable in the block erection stage because of the deformation of the blocks. Currently, accuracy managers decide whether or not block corrections are needed, based on measured and designed point data. They adjust the locations of hull blocks so that the blocks are aligned with other assembly blocks based upon the experience of production engineers. This paper proposes an optimization process that can adjust the locations of ship blocks during the erection stage. A genetic algorithm is used for this optimization scheme. Finally, the feasibility of the proposed method is discussed using several case studies. We found that the proposed method can find the optimized re-alignment of erection blocks, as well as improve the productivity of the erection stage.

• Journal of computational fluids engineering
• /
• v.9 no.1
• /
• pp.34-40
• /
• 2004

Recently with growth in the capability of super computers and Parallel computers, shape design optimization is becoming easible for real problems. Also, Computational Fluid Dynamics(CFD) techniques have been improved for higher reliability and higher accuracy. In the shape design optimization, analysis solvers and optimization schemes are essential. In this work, the Roe's 2nd-order Upwind TVD scheme and DADI time march with multigrid were used for the flow solution with the Euler equation and FDM(Finite Differenciation Method), GA(Genetic Algorithm) and Kriging were used for the design optimization. Kriging were applied to 2-D airfoil design optimization and compared with FDM and GA's results. When Kriging is applied to the nonlinear problems, satisfactory results were obtained. From the result design optimization by Kriging method appeared as good as other methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.1
• /
• pp.215-236
• /
• 2017

Obtaining accurate location information is important in practical applications of wireless sensor networks (WSNs). The distance vector hop (DV-Hop) is a frequently-used range-free localization algorithm in WSNs, but it has low localization accuracy. Moreover, despite various improvements to DV-Hop-based localization algorithms, maintaining a balance between high localization accuracy and good stability and convergence is still a challenge. To overcome these shortcomings, we proposed an improved DV-Hop localization algorithm based on the bat algorithm (IBDV-Hop) for WSNs. The IBDV-Hop algorithm incorporates optimization methods that enhance the accuracy of the average hop distance and fitness function. We also introduce a nonlinear dynamic inertial weight strategy to extend the global search scope and increase the local search accuracy. Moreover, we develop an updated solutions strategy that avoids premature convergence by the IBDV-Hop algorithm. Both theoretical analysis and simulation results show that the IBDV-Hop algorithm achieves higher localization accuracy than the original DV-Hop algorithm and other improved algorithms. The IBDV-Hop algorithm also exhibits good stability, search capability and convergence, and it requires little additional time complexity and energy consumption.

• Journal of Drive and Control
• /
• v.20 no.4
• /
• pp.54-63
• /
• 2023

High and intermittent loading cycles induce fatigue damage to transmission components, resulting in premature gearbox failure. To identify gearbox defects, numerous vibration-based diagnostics techniques, using several artificial intelligence (AI) algorithms, have recently been presented. In this paper, an optimized deep belief network (DBN) model for gearbox problem diagnosis was designed based on time-frequency visual pattern identification. To optimize the hyperparameters of the model, a particle swarm optimization (PSO) approach was integrated into the DBN. The proposed model was tested on two gearbox datasets: a wind turbine gearbox and an experimental gearbox. The optimized DBN model demonstrated strong and robust performance in classification accuracy. In addition, the accuracy of the generated datasets was compared using traditional ML and DL algorithms. Furthermore, the proposed model was evaluated on different partitions of the dataset. The results showed that, even with a small amount of sample data, the optimized DBN model achieved high accuracy in diagnosis.

• International Journal of Fluid Machinery and Systems
• /
• v.8 no.3
• /
• pp.209-219
• /
• 2015

A robust multi-fidelity optimization methodology has been developed, focusing on efficiently handling industrial runner design of hydraulic Francis turbines. The computational task is split between low- and high-fidelity phases in order to properly balance the CFD cost and required accuracy in different design stages. In the low-fidelity phase, a physics-based surrogate optimization loop manages a large number of iterative optimization evaluations. Two derivative-free optimization methods use an inviscid flow solver as a physics-based surrogate to obtain the main characteristics of a good design in a relatively fast iterative process. The case study of a runner design for a low-head Francis turbine indicates advantages of integrating two derivative-free optimization algorithms with different local- and global search capabilities.

• Proceedings of the KSME Conference
• /
• 2001.06c
• /
• pp.531-536
• /
• 2001

The structural shape optimization is a useful tool for engineers to determine the shape of a structure. During the optimization process, relocations of nodes happen successively. However, excessive movement of nodes often results in the mesh distortion and eventually deteriorates the accuracy of the optimum solution. To overcome this problem, an efficient method for the shape optimization has been developed. The method starts from the design domain which is large enough to hold the possible shape of the structure. The design domain has pre-defined uniform fine meshes. At every cycle, the method judges whether all the elements are inside of the structure or not. Elements inside of the structure are assigned with real material properties, however elements outside of the structure are assigned with nearly zero values. The performance of the method is evaluated through various examples.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.30 no.8 s.251
• /
• pp.889-896
• /
• 2006

The concept of reliability has been applied to the topology optimization based on a reliability index approach or a performance measure approach. Since these approaches, called double-loop single vector approach, require the nested optimization problem to obtain the most probable point in the probabilistic design domain, the time for the entire process makes the practical use infeasible. In this work, new reliability-based topology optimization method is proposed by utilizing single-loop single-vector approach, which approximates searching the most probable point analytically, to reduce the time cost. The results of design examples show that the proposed method provides efficiency curtailing the time for the optimization process and accuracy satisfying the specified reliability.

• Proceedings of the KSME Conference
• /
• 2001.11a
• /
• pp.367-371
• /
• 2001

In the shape optimization based on the finite element method, the accuracy of finite element analysis of a given structure is important to determine the final shape. In case of a bending dominant problem, finite element solutions by the full integration scheme are not reliable because of the locking phenomenon. Furthermore, in the process of shape optimization, the mesh distortion is large due to the change of the structure outline: therefore, we cannot guarantee the accurate result unless the finite element itself is accurate. We approach to more accurate shape optimization to diminish these inaccuracies by improving the existing finite element. The shape optimization using the modified finite element is applied to a two-dimensional simple beam. Results show that the modified finite element have improved the optimization results.