• Title/Summary/Keyword: Neuro-fuzzy model

Search Result 217, Processing Time 0.033 seconds

CMAC Neuro-Fuzzy Design for Color Calibration (컬러재현을 위한 CMAC의 뉴로퍼지 설계)

  • 이철희;변오성;문성룡;임기영
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.11 no.4
    • /
    • pp.331-335
    • /
    • 2001
  • Cl\iAC model was proposed by Albus [6J to formulate the processing characteristics of the human cerebellum. Instead of the global weight updating scheme used in the back propagation, CMAC use the local weight updating scheme. Therefore, CMAC have the advantage of fast learning and high convergence rate. In this paper, simulate Color Calibration by CMAC in color images and design hardware by VHDL-base high-level synthesis.

  • PDF

A study on Generation rate Constraints of Power System using Neuro-Fuzzy Controller (뉴로-퍼지 제어기를 이용한 전력시스템의 발전량 증가율 제한에 관한 연구)

  • Kim, Sang-Hyo;Lee, Chang-Woo;Joo, Seok-Min;Chong, Dong-Il;Chung, Hyung-Hwan
    • Proceedings of the KIEE Conference
    • /
    • 2002.07a
    • /
    • pp.301-303
    • /
    • 2002
  • The load frequency control of power system is one of important subjects in view of system operation and control. To converge within allowance load variation value the frequency and tie-line power flow deviation of each areas, we should regulate the active power output of power plant for regulation in system Applying the NFC(Neuro-Fuzzy Controller) to the model of load frequency control of 2-area power system, we prove that the control is superior to the conventional control technique through computer simulation. For verification of robustness, when we consider generator-rate constraint similar to nonlinearities of power system.

  • PDF

Residential Load Modeling Method Based on Neuro-Fuzzy Inference System (뉴로-퍼지 추론 시스템 기반 주거용 부하의 모델링 기법)

  • Ji, Pyeong-Shik;Lee, Jong-Pil;Lee, Dae-Jong;Lim, Jae-Yoon
    • The Transactions of the Korean Institute of Electrical Engineers P
    • /
    • v.60 no.1
    • /
    • pp.6-12
    • /
    • 2011
  • In this study, we proposed a residential load modeling method based on neuro-fuzzy inference system by considering of various harmonics. The developed method was implemented by using harmonic information, fundamental frequency and voltage which are essential input factors in conventional method. Thus, the proposed method makes it possible to effectively estimate load characteristics in power lines with harmonics. To show the effectiveness, the proposed method has been intensively tested with various dataset acquired under the different frequency and voltage and compared it with a conventional method based on neural networks.

Adaptive Neuro-Fuzzy Ingerence based Torque Model of SRM (적응 뉴로퍼지 추론기법에 의한 SRM의 토오크모델)

  • 홍정표;박성준;홍순일;김철우
    • Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
    • /
    • 1999.11a
    • /
    • pp.279-284
    • /
    • 1999
  • Although the switched reluctance motor (SRM) has a several advantages such as simple magnetic structure, robustness, wide range of speed characteristics and simple driving, it has a considerable inherent torque ripple and speed variation duet to the driving characteristics of pulse current waveform and the nonlinear inductance profile. The high torque ripple and speed variation inhibits wide application. The minimization of the torque ripple is very important in high performance servo drive applications, which require smooth operation with minimum torque pulsations. This paper presents the new SRM torque modeling technique for the control of instantaneous torque. The SRM is modeled by the database of torque profiles for every small variation in currents and rotor angles, which is inferred from the several measured data by the adaptive neuro-fuzzy inference technique. Simulation results demonstrating the effectiveness of proposed torque modeling technique are presented.

  • PDF

Neuro-Fuzzy Identification for Non-linear System and Its Application to Fault Diagnosis (비선형 계통의 뉴로-퍼지 동정과 이의 고장 진단 시스템에의 적용)

  • 김정수;송명현;이기상;김성호
    • Proceedings of the Korean Institute of Intelligent Systems Conference
    • /
    • 1998.10a
    • /
    • pp.447-452
    • /
    • 1998
  • A fault is considered as a variation of physical parameters; therefore the design of fault detection and identification(FDI) can be reduced to the parameter identification of a non linear system and to the association of the set of the estimated parameters with the mode of faults. ANFIS(Adaptive Neuro-Fuzzy Inference System) which contains multiple linear models as consequent part is used to model non linear systems. In this paper, we proposes an FDI system for non linear systems using ANFIS. The proposed diagnositc system consists of two ANFISs which operate in two different modes (parallel-and series-parallel mode). It generates the parameter residuals associated with each modes of faults which can be further processed by additional RBF (Radial Basis function) network to identify the faults. The proposed FDI scheme has been tested by simultation on a two-tank system

  • PDF

Design of Fuzzy PID Controller Using GAs and Estimation Algorithm (유전자 알고리즘과 Estimation기법을 이용한 퍼지 제어기 설계)

  • Roh, Seok-Beom;Oh, Sung-Kwun
    • Proceedings of the KIEE Conference
    • /
    • 2001.11c
    • /
    • pp.416-419
    • /
    • 2001
  • In this paper a new approach to estimate scaling factors of fuzzy controllers such as the fuzzy PID controller and the fuzzy PD controller is presented. The performance of the fuzzy controller is sensitive to the variety of scaling factors[1]. The desist procedure dwells on the use of evolutionary computing(a genetic algorithm) and estimation algorithm for dynamic systems (the inverted pendulum). The tuning of the scaling factors of the fuzzy controller is essential to the entire optimization process. And then we estimate scaling factors of the fuzzy controller by means of two types of estimation algorithms such as Neuro-Fuzzy model, and regression polynomial [7]. This method can be applied to the nonlinear system as the inverted pendulum. Numerical studies are presented and a detailed comparative analysis is also included.

  • PDF

Prediction of Building Construction Project Costs Using Adaptive Neuro-Fuzzy Inference System(ANFIS) (적응형 뉴로-퍼지(ANFIS)를 이용한 건축공사비 예측)

  • Yun, Seok-Heon;Park, U-Yeol
    • Journal of the Korea Institute of Building Construction
    • /
    • v.23 no.1
    • /
    • pp.103-111
    • /
    • 2023
  • Accurate cost estimation in the early stages of a construction project is critical to the successful execution of the project. In this study, an ANFIS model was presented to predict construction costs in the early stages of a construction project. To increase the usability of the model, open construction cost data was used, and a model using limited information in the early stage of the project was presented. We analyzed existing studies related to ANFIS to identify recent trends, and after reviewing the basic structure of ANFIS, presented an ANFIS model for predicting conceptual construction costs. The variation in prediction performance depending on the type and number of membership functions of the ANFIS model was analyzed, the model with the best performance was presented, and the prediction accuracy of representative machine learning models was compared and analyzed. Through comparing the ANFIS model with other machine learning models, it was found to show equal or better performance, and it is concluded that it can be applied to predicting construction costs in the early stage of a project.

Effects of infill walls on RC buildings under time history loading using genetic programming and neuro-fuzzy

  • Kose, M. Metin;Kayadelen, Cafer
    • Structural Engineering and Mechanics
    • /
    • v.47 no.3
    • /
    • pp.401-419
    • /
    • 2013
  • In this study, the efficiency of adaptive neuro-fuzzy inference system (ANFIS) and genetic expression programming (GEP) in predicting the effects of infill walls on base reactions and roof drift of reinforced concrete frames were investigated. Current standards generally consider weight and fundamental period of structures in predicting base reactions and roof drift of structures by neglecting numbers of floors, bays, shear walls and infilled bays. Number of stories, number of bays in x and y directions, ratio of shear wall areas to the floor area, ratio of bays with infilled walls to total number bays and existence of open story were selected as parameters in GEP and ANFIS modeling. GEP and ANFIS have been widely used as alternative approaches to model complex systems. The effects of these parameters on base reactions and roof drift of RC frames were studied using 3D finite element method on 216 building models. Results obtained from 3D FEM models were used to in training and testing ANFIS and GEP models. In ANFIS and GEP models, number of floors, number of bays, ratio of shear walls and ratio of infilled bays were selected as input parameters, and base reactions and roof drifts were selected as output parameters. Results showed that the ANFIS and GEP models are capable of accurately predicting the base reactions and roof drifts of RC frames used in the training and testing phase of the study. The GEP model results better prediction compared to ANFIS model.

Reservoir Water Level Forecasting Using Machine Learning Models (기계학습모델을 이용한 저수지 수위 예측)

  • Seo, Youngmin;Choi, Eunhyuk;Yeo, Woonki
    • Journal of The Korean Society of Agricultural Engineers
    • /
    • v.59 no.3
    • /
    • pp.97-110
    • /
    • 2017
  • This study investigates the efficiencies of machine learning models, including artificial neural network (ANN), generalized regression neural network (GRNN), adaptive neuro-fuzzy inference system (ANFIS) and random forest (RF), for reservoir water level forecasting in the Chungju Dam, South Korea. The models' efficiencies are assessed based on model efficiency indices and graphical comparison. The forecasting results of the models are dependent on lead times and the combination of input variables. For lead time t = 1 day, ANFIS1 and ANN6 models yield superior forecasting results to RF6 and GRNN6 models. For lead time t = 5 days, ANN1 and RF6 models produce better forecasting results than ANFIS1 and GRNN3 models. For lead time t = 10 days, ANN3 and RF1 models perform better than ANFIS3 and GRNN3 models. It is found that ANN model yields the best performance for all lead times, in terms of model efficiency and graphical comparison. These results indicate that the optimal combination of input variables and forecasting models depending on lead times should be applied in reservoir water level forecasting, instead of the single combination of input variables and forecasting models for all lead times.

Application of Soft Computing Based Response Surface Techniques in Sizing of A-Pillar Trim with Rib Structures (승용차 A-Pillar Trim의 치수설계를 위한 소프트컴퓨팅기반 반응표면기법의 응용)

  • Kim, Seung-Jin;Kim, Hyeong-Gon;Lee, Jong-Su;Gang, Sin-Il
    • Transactions of the Korean Society of Mechanical Engineers A
    • /
    • v.25 no.3
    • /
    • pp.537-547
    • /
    • 2001
  • The paper proposes the fuzzy logic global approximate optimization strategies in optimal sizing of automotive A-pillar trim with rib structures for occupant head protection. Two different strategies 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 inherent nonlinearity in analysis model should be accommodated over the entire design space and the training data is not sufficiently provided. The objective of structural design is to determine the dimensions of rib in A-pillar, minimizing the equivalent head injury criterion HIC(d). The paper describes the head-form modeling and head impact simulation using LS-DYNA3D, and the approximation procedures including fuzzy rule generation, membership function selection and inference process for EFM and NFM, and subsequently presents their generalization capabilities in terms of number of fuzzy rules and training data.