• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.8
• /
• pp.551-560
• /
• 2004

In this paper, we propose a new architecture of Self-Organizing Fuzzy Polynomial Neural Networks (SOFPNN) that is based on a genetically optimized multilayer perceptron with fuzzy polynomial neurons (FPNs) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially genetic algorithms (GAs). The proposed SOFPNN gives rise to a structurally optimized structure and comes with a substantial level of flexibility in comparison to the one we encounter in conventional SOFPNNs. The design procedure applied in the construction of each layer of a SOFPNN deals with its structural optimization involving the selection of preferred nodes (or FPNs) with specific local characteristics (such as the number of input variables, the order of the polynomial of the consequent part of fuzzy rules, and a collection of the specific subset of input variables) and addresses specific aspects of parametric optimization. Through the consecutive process of such structural and parametric optimization, an optimized and flexible fuzzy neural network is generated in a dynamic fashion. To evaluate the performance of the genetically optimized SOFPNN, the model is experimented with using two time series data(gas furnace and chaotic time series), A comparative analysis reveals that the proposed SOFPNN exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literatures.

• Smart Structures and Systems
• /
• v.24 no.6
• /
• pp.733-744
• /
• 2019

Wind speed forecasting is critical for a variety of engineering tasks, such as wind energy harvesting, scheduling of a wind power system, and dynamic control of structures (e.g., wind turbine, bridge, and building). Wind speed, which has characteristics of random, nonlinear and uncertainty, is difficult to forecast. Nowadays, machine learning approaches (generalized regression neural network (GRNN), back propagation neural network (BPNN), and extreme learning machine (ELM)) are widely used for wind speed forecasting. In this study, two schemes are proposed to improve the forecasting performance of machine learning approaches. One is that optimization algorithms, i.e., cross validation (CV), genetic algorithm (GA), and particle swarm optimization (PSO), are used to automatically find the optimal model parameters. The other is that the combination of different machine learning methods is proposed by finite mixture (FM) method. Specifically, CV-GRNN, GA-BPNN, PSO-ELM belong to optimization algorithm-assisted machine learning approaches, and FM is a hybrid machine learning approach consisting of GRNN, BPNN, and ELM. The effectiveness of these machine learning methods in wind speed forecasting are fully investigated by one-year field monitoring data, and their performance is comprehensively compared.

• Structural Engineering and Mechanics
• /
• v.32 no.5
• /
• pp.667-683
• /
• 2009

FE model-based dynamic analysis has been widely used to predict the dynamic characteristics of civil structures. In a physical point of view, an FE model is unavoidably different from the actual structure as being formulated based on extremely idealized engineering drawings and design data. The conventional model updating methods such as direct method and sensitivity-based parameter estimation are not flexible for model updating of complex and large structures. Thus, it is needed to develop a model updating method applicable to complex structures without restriction. The main objective of this paper is to present the model updating method based on the hybrid genetic algorithm (HGA) by combining the genetic algorithm as global optimization method and modified Nelder-Mead's Simplex method as local optimization method. This FE model updating method using HGA does not need the derivation of derivative function related to parameters and without application of complicated inverse analysis methods. In order to allow its application on diversified and complex structures, a commercial FEA tool is adopted to exploit previously developed element library and analysis algorithms. Moreover, an output-level objective function making use of measurement and analytical results is also presented to update simultaneously the stiffness and mass of the analysis model. The numerical examples demonstrated that the proposed method based on HGA is effective for the updating of the FE model of bridge structures.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.399-402
• /
• 2005

For efficient and accurate diagnosis of ultrasound images, the time gain compensation (TGC) and dynamic range (DR) control of the ultrasound echo signal are important. TGC is for compensating the attenuation of the ultrasound echo signal along the depth, and DR is used to control the image contrast. In this paper, we propose an algorithm for finding the optimized values of TGC and DR automatically. For TGC, the degree of compensation is determined along the depth based on the effective attenuation estimation of ultrasound signal. For DR optimization, we introduce a novel cost function on the basis of the characteristics of ultrasound image, which provides the minimum value at the optimal DR. Experiments have been performed by applying the proposed algorithm to a real US imaging system. The results show that the algorithm automatically can determine the values of TGC and DR in realtime so that the subjective quality of the corresponding US image may be good enough for diagnosis.

• 유체기계공업학회:학술대회논문집
• /
• 2002.12a
• /
• pp.47-53
• /
• 2002

The hydraulic design optimization and performance analysis of mixed-flow pumps for waterjet marine vehicle propulsion has been carried out using mean streamline analysis and three-dimensional computational fluid dynamics (CFD) code. In the present study the conceptual design optimization has been formulated with a non-linear objective function to minimize the fluid dynamic losses and then the commercial CFD code was incorporated to allow for detailed flow dynamic phenomena in the pump system. New designed mixed-flow model pump has been tested in the laboratory. Predicted performance curves by the CFD code agree very well with experimental data for a newly designed mixed-flow pump over the normal operating conditions. The design and prediction methods presented herein can be used efficiently as a unified hydraulic design process of mixed-flow pumps for waterjet marine vehicle propulsion.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.6
• /
• pp.2146-2156
• /
• 2017

When a failure occurs in active distribution system, it will be isolated through the action of circuit breakers and sectionalizing switches. As a result, the network might be divided into several connected components, in which distributed generations could supply power for customers. Aimed at decreasing customer interruption cost, this paper proposes a theoretically optimal island partition model for such connected components, and a simplified but more practical model is also derived. The model aims to calculate a dynamic island partition schedule during the failure recovery time period, instead of a static islanding status. Fluctuation and stochastic characteristics of the renewable distributed generations and loads are considered, and the interruption cost functions of the loads are fitted. To solve the optimization model, a heuristic search algorithm based on the hill climbing method is proposed. The effectiveness of the proposed model and algorithm is evaluated by comparing with an existing static island partitioning model and intelligent algorithms, respectively.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.1006-1011
• /
• 2003

In this study, a novel systematic design procedure by Genetic Algorithm of a two stage relief valve is proposed. First of all, a mathematical model describing the dynamics of a balanced piston type relief valve has been derived. Governing equations such as dynamic equations for the main spool and the pilot spool and flow equations for each orifice are established. The mathematical model is verified by comparing the results of simulation with that of experiments. Furthermore, influences of the parameters on the dynamic characteristics of a relief valve have been investigated by simulation of the proposed model. Major design parameters on the valve response are determined, which affect the system response significantly. And then, using the determined parameters, the optimization of the two stage relief valve by Genetic Algorithm, which is a random search algorithm can find the global optimum without converging local optimum, is performed. The optimal design process of a two stage relief valve is presented to determine the major design parameters. Fitness function reflects the changing pressure according to parameters. It is shown that the genetic algorithms satisfactorily optimized the major design parameters of the two stage relief valve.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.501-506
• /
• 2002

In this study, a novel systematic design procedure by Genetic Algorithm of a two stage relief valve is proposed. First of all. a mathematical model describing the dynamics of a balanced piston type relief valve has been derived. Governing equations such as dynamic equations for the main spool and the pilot spool and flow equations for each orifice are established. The mathematical model is verified by comparing the results of simulation with that of experiments. Furthermore, influences of the parameters on the dynamic characteristics of a relief valve have been investigated by simulation of the proposed model. Major design parameters on the valve response are determined, which affect the system response significantly. And then, using the determined parameters, the optimization of the two stage relief valve by Genetic Algorithm, which is a random search algorithm can find the global optimum without converging local optimum, is performed. The optimal design process of a two stage relief valve is presented to determine the major design parameters. Fitness function reflects the changing pressure according to parameters. It is shown that the genetic algorithms satisfactorily optimized the major design parameters of the two stage relief valve.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.12 no.1
• /
• pp.617-635
• /
• 2020

The purpose of this study is to discuss how to improve the maneuverability of lifting and diving for underwater vehicle's vertical motion. Therefore, to solve these problems, applied the 3-D numerical simulation, Taguchi's Design of Experiment (DOE), and intelligent parameter design methods, etc. We planned four steps as follows: firstly, we applied the 2-D flow simulation with NACA series, and then through the Taguchi's dynamic method to analyze the sensitivity (β). Secondly, take the data of pitching torque and total resistance from the Taguchi orthogonal array (L9), the ignal-to-noise ratio (SNR), and analysis each factorial contribution by ANOVA. Thirdly, used Radial Basis Function Network (RBFN) method to train the non-linear meta-modeling and found out the best factorial combination by Particle Swarm Optimization (PSO) and Weighted Percentage Reduction of Quality Loss (WPRQL). Finally, the application of the above methods gives the global optimum for multi-quality characteristics and the robust design configuration, including L/D is 9.4:1, the foreplane on the hull (Bow-2), and position of the sail is 0.25 Ls from the bow. The result shows that the total quality is improved by 86.03% in comparison with the original design.

• Smart Structures and Systems
• /
• v.19 no.1
• /
• pp.39-46
• /
• 2017

Finite element model updating is very effective procedure to determine the uncertainty parameters in structural model and minimize the differences between experimentally and numerically identified dynamic characteristics. This procedure can be practiced with manual and automatic model updating procedures. The manual model updating involves manual changes of geometry and analyses parameters by trial and error, guided by engineering judgement. Besides, the automated updating is performed by constructing a series of loops based on optimization procedures. This paper addresses the ambient vibration based finite element model updating of long span reinforced concrete highway bridges using manual model updating procedure. Birecik Highway Bridge located on the $81^{st}km$ of Şanliurfa-Gaziantep state highway over Firat River in Turkey is selected as a case study. The structural carrier system of the bridge consists of two main parts: Arch and Beam Compartments. In this part of the paper, the arch compartment is investigated. Three dimensional finite element model of the arch compartment of the bridge is constructed using SAP2000 software to determine the dynamic characteristics, numerically. Operational Modal Analysis method is used to extract dynamic characteristics using Enhanced Frequency Domain Decomposition method. Numerically and experimentally identified dynamic characteristics are compared with each other and finite element model of the arch compartment of the bridge is updated manually by changing some uncertain parameters such as section properties, damages, boundary conditions and material properties to reduce the difference between the results. It is demonstrated that the ambient vibration measurements are enough to identify the most significant modes of long span highway bridges. Maximum differences between the natural frequencies are reduced averagely from %49.1 to %0.6 by model updating. Also, a good harmony is found between mode shapes after finite element model updating.