A Neuro-Fuzzy Inference System for Sensor Failure Detection Using Wavelet Denoising, PCA and SPRT

Na, Man-Gyun Korean Nuclear Society 2001 Nuclear Engineering and Technology Vol.33 No.5

In this work, a neuro-fuzzy inference system combined with the wavelet denoising, PCA (principal component analysis) and SPRT (sequential probability ratio test) methods is developed to detect the relevant sensor failure using other sensor signals. The wavelet denoising technique is applied to remove noise components in input signals into the neuro-fuzzy system The PCA is used to reduce the dimension of an input space without losing a significant amount of information. The PCA makes easy the selection of the input signals into the neuro-fuzzy system. Also, a lower dimensional input space usually reduces the time necessary to train a neuro-fuzzy system. The parameters of the neuro-fuzzy inference system which estimates the relevant sensor signal are optimized by a genetic algorithm and a least-squares algorithm. The residuals between the estimated signals and the measured signals are used to detect whether the sensors are failed or not. The SPRT is used in this failure detection algorithm. The proposed sensor-monitoring algorithm was verified through applications to the pressurizer water level and the hot-leg flowrate sensors in pressurized water reactors.

선박 근접 충돌사고 데이터를 이용한 충돌 위험도 추론 시스템

남궁호,정중식,김주성 한국지능시스템학회 2019 한국지능시스템학회논문지 Vol.29 No.5

Collision risk at sea has been studied as a required quantitative index for making a decision of collision avoidance between ships. Recently, inference methods of the collision risk were proposed on the basis of the fuzzy theory because of being possible to collect data in real time. Fuzzy inference system was composed of results of interview with navigating officers. In this study, we obtained fuzzy inference system by utilizing the adaptive neuro fuzzy inference system through extracting ship near-collisions data. Proposed fuzzy inference systeme expressed appropriate collision risk index corresponding to level. It was possible to express various collision risk index compared to existing the fuzzy inference system. 해상에서 선박의 충돌 위험도는 충돌 회피 동작을 위해 의사결정시 요구되는 정량적인 지수로써 연구되어 왔다. 최근실시간으로 정보 수집이 가능해지면서 퍼지 이론 기반의 충돌 위험도 추론 방법이 제안되었다. 퍼지 추론 시스템은 항해사와인터뷰에 의한 결과에 기반을 두고 퍼지 이론을 적용하여 충돌 위험성을 표현하였다. 본 연구에서는 선박 안전영역을적용하여 선박 근접 충돌사고 데이터 추출을 통해 퍼지 집합을 이끌어 내고, 적응형 뉴로-퍼지 시스템(Adaptive Neuro-Fuzzy Inference System, ANFIS)을 활용함으로써 퍼지 추론 시스템을 얻어내고자 하였다. 조우하는 선박에 적용 결과, ANFIS 기반설계된 퍼지 추론 시스템은 단계별 대응되는 적절한 충돌위험도 값을 추론하였으며, 기존 퍼지 추론 시스템에 비해 다양한충돌위험도 추론 값의 표현이 가능하였다.

A Model-free Output Feedback Adaptive Optimal Fuzzy Controller for LC-filtered Three-phase Voltage Source Inverters

Nam Hai Trinh,Loc Ong Xuan,Nga Thi-Thuy Vu,Anh Tuan Nguyen 제어·로봇·시스템학회 2023 International Journal of Control, Automation, and Vol.21 No.6

This paper proposes a model-free output feedback control-based adaptive fuzzy controller using a current-sensorless configuration for LC-filtered three-phase voltage source inverters (VSIs). The proposed adaptive fuzzy scheme is constructed of three parts: an adapter, an adaptive optimal fuzzy controller, and an adaptive optimal fuzzy identifier. The adapter is designed based on an adaptive neuro-fuzzy inference system (ANFIS) network which uses the error between the system output and identifier output as an input to generate the online updated parameters. Next, both the adaptive fuzzy controller and the fuzzy identifier are designed based on the Takagi-Sugeno (T-S) fuzzy model. In particular, the proposed algorithm is robust against external disturbance and parameter uncertainties due to not requiring the system parameters. Moreover, the proposed scheme uses a current-sensorless configuration, which reduces the system complexity and cost. Both the stability of the proposed method and the convergence of adapted parameters are completely assured by using the Lyapunov stability theory. Finally, the effectiveness of the proposed adaptive fuzzy controller is verified through simulation in comparison with a conventional T-S fuzzy controller. The results show that the proposed model-free output feedback control-based adaptive fuzzy controller yields better control performance, such as faster transient response, smaller steady-state error, and lower total harmonic distortion (THD) under the change of load (step changes of linear load, unbalanced load, and nonlinear load), parameter variations, and input disturbances.

심박변이도를 이용한 적응적 뉴로 퍼지 감정예측 모형에 관한 연구

박성수,이건창 한국디지털정책학회 2019 디지털융복합연구 Vol.17 No.1

An accurate prediction of emotion is a very important issue for the sake of patient-centered medical device development and emotion-related psychology fields. Although there have been many studies on emotion prediction, no studies have applied the heart rate variability and neuro-fuzzy approach to emotion prediction. We propose ANFEP(Adaptive Neuro Fuzzy System for Emotion Prediction) HRV. The ANFEP bases its core functions on an ANFIS(Adaptive Neuro-Fuzzy Inference System) which integrates neural networks with fuzzy systems as a vehicle for training predictive models. To prove the proposed model, 50 participants were invited to join the experiment and Heart rate variability was obtained and used to input the ANFEP model. The ANFEP model with STDRR and RMSSD as inputs and two membership functions per input variable showed the best results. The result out of applying the ANFEP to the HRV metrics proved to be significantly robust when compared with benchmarking methods like linear regression, support vector regression, neural network, and random forest. The results show that reliable prediction of emotion is possible with less input and it is necessary to develop a more accurate and reliable emotion recognition system. 감정을 정확히 예측하는 것은 환자중심의 의료디바이스 개발 및 감성관련 산업에서 매우 중요한 이슈이다. 감정 예측에 관한 많은 연구 중 감정 예측에 심박 변동성과 뉴로-퍼지 접근법을 적용한 연구는 없다. 본 연구는 HRV를 이용한 ANFEP(Adaptive Neuro Fuzzy system for Emotion Prediction)을 제안한다. ANFEP의 핵심 기능은 인공 신경망과 퍼지 시스템을 통합해 예측 모델을 학습하는 ANFIS(Adaptive Neuro-Fuzzy Inference System)에 기반한다. 제안 모형의 검증을 위해 50명의 실험자를 대상으로 청각자극으로 감정을 유발하고, 심박변이도를 구하여 ANFEP 모형에 입력하였다. STDRR과 RMSSD를 입력으로 하고 입력변수 당 2개의 소속함수로 하는 ANFEP모형이 가장 좋은 결과를 나타났다. 제안한 감정예측 모형을 선형회귀 분석, 서포트 벡터 회귀, 인공신경망, 랜덤 포레스트와 비교한 결과 본 제안모형이 가장 우수한 성능을 보였다. 연구 결과는 보다 적은 입력으로 신뢰성 높은 감정인식이 가능함을 입증했고, 이를 활용해 보다 정확하고 신뢰성 높은 감정인식 시스템 개발에 대한 연구가 필요하다.

Fuzzy추론 시스템과 신경회로망을 결합한 하천유출량 예측

허창환 ( Heo Chang-hwan ),임기석 ( Lim Kee-seok ) 한국농공학회 2007 한국농공학회논문집 Vol.49 No.3

This study is aimed at the development of a runoff forecasting model by using the Fuzzy inference system and Neural Network model to solve the uncertainties occurring in the process of rainfall-runoff modeling and improve the modeling accuracy of the stream runoff forecasting. The Neuro-Fuzzy (NF) model were used in this study. The NF model, recently received a great deal of attention, improve the existing Neural Networks by the aid of the Fuzzy theory applied to each node. The study area is the downstreams of Naeseong-chun. Therefore, time-dependent data was obtained from the Wolpo water level gauging station. 11 and 2 out of total 13 flood events were selected for the training and testing set of model respectively. The schematic diagram method and the statistical analysis are conducted to evaluate the feasibility of rainfall-runoff modeling. The model accuracy was rapidly decreased as the forecasting time became longer. The NF model can give accurate runoff forecasts up to 4 hours ahead in standard above the Determination coefficient (R²) 0.7. In the comparison of the runoff forecasting using the NF and TANK models, characteristics of peak runoff in the TANK model was higher than ones in the NF models, but peak values of hydrograph in the NF models were similar.

An Adaptive Input Data Space Parting Solution to the Synthesis of Neuro-Fuzzy Models

Sy Dzung Nguyen,Kieu Nhi Ngo 대한전기학회 2008 International Journal of Control, Automation, and Vol.6 No.6

This study presents an approach for approximation an unknown function from a numerical data set based on the synthesis of a neuro-fuzzy model. An adaptive input data space parting method, which is used for building hyperbox-shaped clusters in the input data space, is proposed. Each data cluster is implemented here as a fuzzy set using a membership function MF with a hyperbox core that is constructed from a min vertex and a max vertex. The focus of interest in proposed approach is to increase degree of fit between characteristics of the given numerical data set and the established fuzzy sets used to approximate it. A new cutting procedure, named NCP, is proposed. The NCP is an adaptive cutting procedure using a pure function Ψ and a penalty function τ for direction the input data space parting process. New algorithms named CSHL, HLM1 and HLM2 are presented. The first new algorithm, CSHL, built based on the cutting procedure NCP, is used to create hyperbox-shaped data clusters. The second and the third algorithm are used to establish adaptive neuro-fuzzy inference systems. A series of numerical experiments are performed to assess the efficiency of the proposed approach.

A Study on the Neuro-Fuzzy Control and Its Application

So, Myung-Ok,Yoo, Heui-Han,Jin, Sun-Ho The Korean Society of Marine Engineering 2004 한국마린엔지니어링학회지 Vol.28 No.2

In this paper. we present a neuro-fuzzy controller which unifies both fuzzy logic and multi-layered feed forward neural networks. Fuzzy logic provides a means for converting linguistic control knowledge into control actions. On the other hand. feed forward neural networks provide salient features. such as learning and parallelism. In the proposed neuro-fuzzy controller. the parameters of membership functions in the antecedent part of fuzzy inference rules are identified by using the error back propagation algorithm as a learning rule. while the coefficients of the linear combination of input variables in the consequent part are determined by using the least square estimation method. Finally. the effectiveness of the proposed controller is verified through computer simulation for an inverted pole system.

PCA-based neuro-fuzzy model for system identification of smart structures

Soroush Mohammadzadeh,Yeesock Kim,안재훈 국제구조공학회 2015 Smart Structures and Systems, An International Jou Vol.15 No.4

This paper proposes an efficient system identification method for modeling nonlinear behaviorof civil structures. This method is developed by integrating three different methodologies: principalcomponent analysis (PCA), artificial neural networks, and fuzzy logic theory, hence named PANFIS(PCA-based adaptive neuro-fuzzy inference system). To evaluate this model, a 3-story building equippedwith a magnetorheological (MR) damper subjected to a variety of earthquakes is investigated. To train theinput-output function of the PANFIS model, an artificial earthquake is generated that contains a variety ofcharacteristics of recorded earthquakes. The trained model is also validated using the1940 El-Centro, Kobe,Northridge, and Hachinohe earthquakes. The adaptive neuro-fuzzy inference system (ANFIS) is used as abaseline. It is demonstrated from the training and validation processes that the proposed PANFIS model iseffective in modeling complex behavior of the smart building. It is also shown that the proposed PANFISproduces similar performance with the benchmark ANFIS model with significant reduction ofcomputational loads.

Determination of bearing capacity of stone column with application of Neuro-fuzzy system

Manita Das,Ashim Kanti Dey 대한토목학회 2018 KSCE JOURNAL OF CIVIL ENGINEERING Vol.22 No.5

The neuro-fuzzy controller applies the neural network learning techniques to tune the membership functions and keeps thesemantics of the fuzzy logic controller intact. Hence benefits of both the neural network and fuzzy logic controller are taken intoconsideration. In this study, to predict the bearing capacity of a stone column, application of Adaptive Neuro-fuzzy Inference System(ANFIS) is presented. To train and test the data sets, 105 data pairs are collected from the previous technical literature. These data setsinclude the data of stone and sand columns. The spacing of the columns varies from 1.5 to 10 times the diameter. The undrainedcohesion varies from 7 to 400 kPa. Both experimental and analytical data are included in the collection. To test the trained ANFISmodels, data are collected from physical experiments on plate load test and numerical analysis with PLAXIS-2D. For thecomparative study, ANFIS models combined with plate load test results and analytical results, three ANFIS models are developed. Acomparative study on the accuracy of prediction by these three models is discussed.

Adaptive Neuro-Fuzzy Inference System for Prediction of Pile Setup

전종구,이송 한국지반공학회 2009 international journal of geo-engineering Vol.1 No.1

The evaluation of time dependent increase in pile capacity (setup) may lead to more economical design of pile foundations. This paper presents an Adaptive Neuro Fuzzy Inference System (ANFIS) to predict pile setup. A database of field dynamic tests is developed from the review of literature and selected input variables include soil type, roughness volume of pile shaft, pile diameter, pile length, time after pile installation, and initial effective stress at pile tip. Ultimate pile capacity at the beginning of restrike is evaluated by adding pile capacity at end of drive to the pile capacity increase predicted by ANFIS. The results of this study indicate that ANFIS provide predictions that are better than those from empirical methods, and can serve as a reliable and simple predictive tool for the prediction of pile setup. The evaluation of time dependent increase in pile capacity (setup) may lead to more economical design of pile foundations. This paper presents an Adaptive Neuro Fuzzy Inference System (ANFIS) to predict pile setup. A database of field dynamic tests is developed from the review of literature and selected input variables include soil type, roughness volume of pile shaft, pile diameter, pile length, time after pile installation, and initial effective stress at pile tip. Ultimate pile capacity at the beginning of restrike is evaluated by adding pile capacity at end of drive to the pile capacity increase predicted by ANFIS. The results of this study indicate that ANFIS provide predictions that are better than those from empirical methods, and can serve as a reliable and simple predictive tool for the prediction of pile setup.