• 전기학회논문지
• /
• 제57권11호
• /
• pp.2108-2116
• /
• 2008

The paper concerns Fuzzy C-Means clustering based Radial Basis Function neural networks (FCM-RBFNN) and the optimization of the network is carried out by means of Particle Swarm Optimization(PSO). FCM-RBFNN is the extended architecture of Radial Basis Function Neural Network(RBFNN). In the proposed network, the membership functions of the premise part of fuzzy rules do not assume any explicit functional forms such as Gaussian, ellipsoidal, triangular, etc., so its resulting fitness values directly rely on the computation of the relevant distance between data points by means of FCM. Also, as the consequent part of fuzzy rules extracted by the FCM - RBFNN model, the order of four types of polynomials can be considered such as constant, linear, quadratic and modified quadratic. Weighted Least Square Estimator(WLSE) are used to estimates the coefficients of polynomial. Since the performance of FCM-RBFNN is affected by some parameters of FCM-RBFNN such as a specific subset of input variables, fuzzification coefficient of FCM, the number of rules and the order of polynomials of consequent part of fuzzy rule, we need the structural as well as parametric optimization of the network. In this study, the PSO is exploited to carry out the structural as well as parametric optimization of FCM-RBFNN. Moreover The proposed model is demonstrated with the use of numerical example and gas furnace data set.

• 한국소음진동공학회논문집
• /
• 제23권1호
• /
• pp.84-91
• /
• 2013

Ultrasonic flip-chip bonding needs a precise bonding tool which delivers ultrasonic energy into chip bumps effectively to use the selected resonance mode and frequency of the horn structure. The bonding tool is excited at the resonance frequency and the input and output ports should locate at the anti-nodal points of the resonance mode. In this study, we propose new design method with topology optimization for ultrasonic bonding tools. The SIMP(solid isotropic material with penalization) method is used to formulate topology optimization and OC(optimal criteria) algorithm is adopted for the update scheme. MAC(modal assurance criterion) tracking is used for the target frequency and mode. We fabricate two prototypes of ultrasonic tools which are based on 3D optimization models after reviewing 2D and 3D topology optimization results. The prototypes are satisfied with the ultrasonic frequency and vibration amplitude as the ultrasonic bonding tools.

• Journal of Welding and Joining
• /
• 제26권1호
• /
• pp.63-68
• /
• 2008

This paper has aimed to prevent excessive heat input by controlling arc distribution and heat input capacity with pulse GTAW in order to improve weld quality in 0.08mm pressure gauge diaphragm and flange welding parts. A design of experiment was designed using Box-Behnken method to optimize a welding process. The pulse GTAW parameters such as pulse current, base current, pulse duty, frequency and welding speed were set to input variables while hydraulic pressure that represents welding characteristics in diaphragm and flange joint were set to output variables. Based on the test result, a second regression equation was obtained between input and output variables and turned out significant. Besides, an influence of parameters has been confirmed through response surface analysis using the second-order regression equation and optimum welding condition was obtained through a grid-search method. The optimum welding condition was set to pulse current 84.4(A), base current 29.6(A), pulse duty 58.8(%), frequency 10(%), and welding speed 596(mm/min). Then, decent bead shape was acquired with no excessive heat input under the $2.3kgf/cm^2$ of hydrostatic pressure.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.346-348
• /
• 2004

In this rarer, we introduce a new Fuzzy Polynomial Neural Networks (FPNNs)-like structure whose neuron is based on the Fuzzy Set-based Fuzzy Inference System (FS-FIS) and is different from that of FPNNs based on the Fuzzy relation-based Fuzzy Inference System (FR-FIS) and discuss the ability of the new FPNNs-like structurenamed Fuzzy Set-based Polynomial Neural Networks (FSPNN). The premise parts of their fuzzy rules are not identical, while the consequent parts of the both Networks (such as FPNN and FSPNN) are identical. This difference results from the angle of a viewpoint of partition of input space of system. In other word, from a point of view of FS-FIS, the input variables are mutually independent under input space of system, while from a viewpoint of FR-FIS they are related each other. In considering the structures of FPNN-like networks such as FPNN and FSPNN, they are almost similar. Therefore they have the same shortcomings as well as the same virtues on structural side. The proposed design procedure for networks' architecture involves the selection of appropriate nodes with specific local characteristics such as the number of input variables, the order of the polynomial that is constant, linear, quadratic, or modified quadratic functions being viewed as the consequent part of fuzzy rules, and a collection of the specific subset of input variables. On the parameter optimization phase, we adopt Information Granulation (IG) based on HCM clustering algorithm and a standard least square method-based learning. 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 FSPNN (gFSPNN), the model is experimented with using gas furnace process dataset.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2004년도 추계학술대회 학술발표 논문집 제14권 제2호
• /
• pp.433-436
• /
• 2004

In this paper, we introduce a new Fuzzy Polynomial Neural Networks (FPNNS)-like structure whose neuron is based on the Fuzzy Set-based Fuzzy Inference System (FS-FIS) and is different from that of FPNNS based on the Fuzzy relation-based Fuzzy Inference System (FR-FIS) and discuss the ability of the new FPNNS-like structure named Fuzzy Set-based Polynomial Neural Networks (FSPNN). The premise parts of their fuzzy rules are not identical, while the consequent parts of the both Networks (such as FPNN and FSPNN) are identical. This difference results from the angle of a viewpoint of partition of input space of system. In other word, from a point of view of FS-FIS, the input variables are mutually independent under input space of system, while from a viewpoint of FR-FIS they are related each other. The proposed design procedure for networks architecture involves the selection of appropriate nodes with specific local characteristics such as the number of input variables, the order of the polynomial that is constant, linear, quadratic, or modified quadratic functions being viewed as the consequent part of fuzzy rules, and a collection of the specific subset of input variables. On the parameter optimization phase, we adopt Information Granulation (IC) based on HCM clustering algorithm and a standard least square method-based learning. 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 FSPNN (gFSPNN), the model is experimented with using the time series dataset of gas furnace process.

• 융합신호처리학회논문지
• /
• 제19권2호
• /
• pp.77-88
• /
• 2018

본 논문은 입력 포화를 가지는 불확실한 전기 구동 로봇 시스템에 대해 입자 군집 최적화(PSO)를 이용한 방사형 기저 함수 신경망(RBFNN) 기반 분산 적응 추종 제어 기법을 제안한다. 실제적으로 로봇 시스템에서는 구동기의 포화로 인해 입력 전압과 전류 신호 크기가 제한된다. 제안된 제어기는 이러한 입력 포화를 극복하며, 어떠한 로봇 링크 및 구동기의 모델 파라미터들을 요구하지 않는다. 제시된 PSO 기법에서 쓰인 적합도 함수는 추종 오차만이 아니라 전압과 전류의 크기를 포함하는 다중 목적 함수로 표현된다. PSO 기법을 이용하여 제어 이득과 방사형 기저 함수의 개수가 자동으로 조정되어 제어 시스템의 성능이 개선된다. 리아푸노프 안정도 해석에 의해 전체 제어 시스템의 안정도가 보장된다. 제안된 제어 기법의 타당성과 강인성이 시뮬레이션 결과를 통해 검증된다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제50권7호
• /
• pp.318-324
• /
• 2001

Efficiency optimization of an indirect vector controlled induction motor drive is proposed. The loss models are used in the validation of the fuzzy logic based on-line efficiency optimization control. At steady state, the fuzzy controller adaptively changes the excitation current on the basis of measured input power, until the maximum efficiency point is reached. The pulsating torque, due to flux reduction, has been compensated by an ingenious feedforward scheme. During transient state, rated flux is established to get the best transient response. Through a comprehensive simulation study, the results confirmed the validity of the proposed method.

• Journal of Mechanical Science and Technology
• /
• 제15권8호
• /
• pp.1132-1142
• /
• 2001

The paper describes the construction of global function approximation models for use in design optimization via global search techniques such as genetic algorithms. Two different approximation methods referred to as evolutionary fuzzy modeling (EFM) and neuro-fuzzy modeling (NFM) are implemented in the context of global approximate optimization. EFM and NFM are based on soft computing paradigms utilizing fuzzy systems, neural networks and evolutionary computing techniques. Such approximation methods may have their promising characteristics in a case where the training data is not sufficiently provided or uncertain information may be included in design process. Fuzzy inference system is the central system for of identifying the input/output relationship in both methods. The paper introduces the general procedures including fuzzy rule generation, membership function selection and inference process for EFM and NFM, and presents their generalization capabilities in terms of a number of fuzzy rules and training data with application to a three-bar truss optimization.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 추계학술대회논문집B
• /
• pp.365-370
• /
• 2001

In order to minimize unstable flow occurred at a multiblade fan/scroll system, optimal angle and shape of cut-off was determined by using two-dimensional turbulent fluid field analyses and neural network. The results of CFD analyses were used for learning as data of input and output of neural network. After learning neural network optimization process was accomplished for design variables, the angle and the shape of cut-off, in the design domain. As a result of optimization, the optimal angle and shape were obtained as 71 and 0.092 times the outer diameter of impeller, respectively, which are very similar values to previous studies. Finally, it was verified that the fluid field is very stable for optimal angle and shape of cut-off by two-dimensional CFD analysis.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2008년도 추계학술대회A
• /
• pp.695-700
• /
• 2008

Artificial neural network (ANN) has been extensively used in areas of nonlinear system modeling, analysis and design applications. Basically, ANN has its distinct capabilities of implementing system identification and/or function approximation using a number of input/output patterns that can be obtained via numerical and/or experimental manners. The paper describes a role of ANN, especially a back-propagation neural network (BPN) in the context of engineering analysis, design and optimization. Fundamental mechanism of BPN is briefly summarized in terms of training procedure and function approximation. The BPN based causality analysis (CA) is further discussed to realize the problem decomposition in the context of multidisciplinary design optimization. Such CA is also applied to quantitatively evaluate the uncoupled or decoupled design matrix in the context of axiomatic design with the independence axiom.