Wyniki wyszukiwania - Biblioteka Nauki

1

Refining the diagnostic quality of the abdominal fetal electrocardiogram using the techniques of artificial intelligence

100%

Martinek R. , Zidek J.

Przegląd Elektrotechniczny

|

2012

|

tom R. 88, nr 12b

155-160

EN

This article deals with utilization of the combination of the fuzzy system and artificial intelligence techniques, called the Adaptive Neuro Fuzzy Inference System ANFIS, with the aim to refine the diagnostic quality of the abdominal fetal electrocardiogram FECG. Within the scope of the experiments carried out and based on the ANFIS structure the authors created a complex system for removing the undesirable mother’s MECG degrading the abdominal FECG. Current research shows that the application of the conventional systems for enhancing the diagnostic quality of the abdominal FECG faces a series of problems (e.g. non-linear character of the task to solve, computational complexity of RLS algorithms, etc.). The need for a higher diagnostic quality of the abdominal FECG is reflected in the authors’ intention to utilize the designed system for the latest intrapartum monitoring method, called ST analysis. In terms of this advanced method, the aspect subjected to a diagnostic analysis is the ST segment of the FECG curve. The results indicate that the system utilizing ANFIS shows better experimental results than the conventional systems based on the LMS or RLS adaptive algorithms. The proposed adaptive system aims to clear any doubts in evaluation of the results of ST analysis while using a non-invasive method of external monitoring.

PL

W artykule przedstawiono wykorzystanie fuzji metod: zbiorów rozmytych i sztucznej inteligencji ANFIS do poprawy jakości diagnostyki elektrokardiografii płodu. Głównym problemem jest usunięcie sygnału pochodzącego od matki który znacznie przewyższa sygnał płodu. (Poprawa jakości sygnału elektrokardiogramu płodu przy wykorzystaniu narzędzi sztucznej inteligencji)

2

ANFIS UPFC Damping Controller for Multi machines Power Systems Oscillations

100%

Bekri M. A. , Hazzab A.

Przegląd Elektrotechniczny

|

2013

|

tom R. 89, nr 12

105-109

EN

The main purpose of this paper is to investigate an Adaptive Neuron- Fuzzy Inference System (ANFIS) based supplementary Unified Power Flow Controller (UPFC) in superimposing a damping function on the control signal of UPFC who’s incorporated in multi-machines power system. This control scheme designed to produce supplementary signal for damping oscillations in the interconnected power systems. The improved damping performance was studied and it is validated on a benchmark power system example taken from literature.The control actions are formulated as a set of local controllers, which are coordinated to maintain transient angle stability, transient voltage stability and damping of interarea and local oscillations following a disturbance.

PL

W artykule przedstawiono wyniki badania sterownika przepływu mocy UPFC wykorzystującego system ANFIS zastosowanego w systemie wielogeneratorowym. Celem było tłumienie oscylacji na połączeniach.

3

Forecasting the electricity generation of photovoltaic plants

94%

Kuievda I. , Baliuta S. , Zinkevich P. , Stoliarov O.

Journal of New Technologies in Environmental Science

|

2021

|

tom Vol. 5, nr 1

40--45

EN

Due to the need in accordance with Ukrainian legislation to submit a day-ahead hourly forecast of electricity generation of solar power plants, the problem of forecasting model quality becomes very important. In the study it is proposed a method of choosing the optimal structure and sensitivity assessment of ANFIS-based forecasting model. In the model the input is solar irradiance, the output is solar panel generation power. The method is based on computational procedures using MATLAB software. For the data set, used in the study, the results, optimal for normalized mean absolute error (NMAE), were achieved on 5 triangular input member functions (trimf), while the error varied within 0.23% depending on number and shape of input member functions. According to the calculations of input error sensitivity of the forecasting model with 5 input trimf membership functions, the increasing of input error up to 8.19% NMAE leads to the raising of the output error in the testing sample up to 5.78%, NMAE. The rather low sensitivity of the model to the input data error allows us to conclude that forecasted meteorological data with a pre-known fixed forecast error can be used as input data.

4

Zastosowanie adaptacyjnego systemu neuro rozmytego do identyfikacji modelu diagnostycznego rurociągów

94%

Kwaśniewski J. , Śmieja M. , Wojciechowski J.

Mechanika / Akademia Górniczo-Hutnicza im. St. Staszica

|

1999

|

tom T. 18, z. 4

509-518

PL

W pracy opisano koncepcje zastosowania adaptacyjnego systemu neuro rozmytego (ANFIS) w diagnostyce sieci rurociągowych. Przedstawiono charakter zachodzących w uszkodzonym rurociągu zjawisk fizycznych oraz opisano przeprowadzony dla ich potwierdzenia eksperyment. Dla uzyskanych na stanowisku laboratoryjnym pomiarów przeprowadzono próbę identyfikacji założonego modelu rozmytego, przez uczenie nadzorowane z wykorzystaniem ANFIS Toolbox FUZZY pakietu Matlab. l opisano efekt wykorzystania metody do lokalizacji uszkodzenia. Wskazano również kierunek dalszych prac nad przyjętą koncepcją.

EN

In this paper the conception of applying adaptive neuro-fuzzy inference system in diagnostic of pipelines was presented. At first, the features of physical phenomenous occuring in faulted pipelines arę charakterized and experiment, madę in to confirm them, is described. Then, for results obtained on laboratory stand, there is madę a test of identification for presumed fuzzy-model, by supervised learning, with using of ANFIS Toolbox FUZZY from Matlab, and there is described an effect of using the method for localization of damage. At the end, directs of future research on the conception was presented.

5

Wpływ temperatury na krótkoterminową prognozę obciążenia elektroenergetycznego

84%

Łosiowski W.

Elektrotechnika i Elektronika

|

2000

|

tom T. 19, z. 2

132--139

PL

W artykule omówiono wpływ temperatury na prognozę dobowego profilu obciążeń elektroenergetycznych z wyprzedzeniem od jednego dnia do tygodnia, dla każdej pory roku, dla spółki dystrybucyjnej o maksymalnej wartości godzinowego szczytu rocznego rzędu 1000 MW. Do określenia prognozy użyto modeli opartych na sieci neurorozmytej ANFIS i sieci neuronowej typu kaskadowego. Zwrócono uwagę na praktyczny brak zależności od temperatury w okresie letnim oraz problemy związane z dokładnością prognozy i porównywania wyników uzyskanych dla różnych wielkości systemów energetycznych.

EN

Temperature influence of short-term daily profile load forecasting one day to week ahead, for each season.for distri- bution company with max daily pik about 1000 MW, was shown. For realise models of load forecasting, neuro-fuzzy ANFIS and cascaded neural network were used. Practical temperature indepedence in summer season was observed. Accuracy and uncomparison results problems for different magnitude systems were discused.

6

Methodology for monitoring and diagnosing faults of hybrid dynamic systems: a case study on a desalination plant

84%

Achbi M. S. , Kechida S.

Diagnostyka

|

2020

|

tom Vol. 21, No. 1

27--33

EN

The imperative of quality and productivity has increased the complexity of technological processes, posing the problem of reliability. Today, fault diagnosis remains a very important task because of its essential role in improving reliability, but also in minimizing the harmful consequences that can be catastrophic for the safety of equipment and people. Indeed, an effective diagnosis not only improves reliability, but also reduces maintenance costs. Systems in which dynamic behaviour evolves as a function of the interaction between continuous dynamics and discrete dynamics, present in the system, are called hybrid systems. The goal is to develop monitoring and diagnostic procedures to the highest level of control to ensure safety, reliability and availability objectives. This article presents an approach to the diagnosis of hybrid systems using hybrid automata and neural-fuzzy system. The use of the neural-fuzzy system allows modeling the continuous behaviour of the system. On the other hand, the hybrid automata gives a perfect estimate of the discrete events and make it possible to execute a fault detection algorithm mainly consists of classifying the appeared defects. On the implementation plan, the results were applied in a water desalination plant.

7

ANFIS Approach for Noise Reduction of Lightning Current Online Monitoring System

84%

Yan N. , Fu Z. , Li J.

Przegląd Elektrotechniczny

|

2012

|

tom R. 88, nr 7a

108-112

EN

A novel de-noising algorithm, based on adaptive neural-fuzzy inference system (ANFIS) is proposed for noise reduction of the lightning current online monitoring system. The paper presents the theory and the implement procedure of the fuzzy neural system. Comparisons among the traditional strategies, such as curve fitting (CF), wavelet transform (WT) methods and the proposed ANFIS strategy are carried out. The simulation results demonstrate the superiority of the proposed method. Moreover, the employed approach has been tested on the practical measured current of lightning current online monitoring system. The testing results validate the proposed approach.

PL

Zaproponowano nowy algorytm odszumiania bazujący na adaptacyjnym neuro-fuzzy systemie interferencji ANFIS. System zastosowano przy monitorowaniu prądu wyładowań. System porównano z innymi dotychczas stosowanymi – dopasowanie krzywej czy transformata falkowa.

8

Application of fuzzy analytic hierarchy process to building research teams

84%

Dąbrowski K. , Skrzypek K.

Management Systems in Production Engineering

|

2016

|

tom nr 1 (21)

7--11

EN

Building teams has a fundamental impact for execution of research and development projects. The teams appointed for the needs of given projects are based on individuals from both inside and outside of the organization. Knowledge is not only a product available on the market but also an intangible resource affecting their internal and external processes. Thus it is vitally important for businesses and scientific research facilities to effectively manage knowledge within project teams. The article presents a proposal to use Fuzzy AHP (Analytic Hierarchy Process ) and ANFIS (Adaptive Neuro Fuzzy Inference System) methods in working groups building for R&D projects on the basis of employees skills.

PL

Budowanie zespołów ma podstawowe znaczenie dla realizacji projektów badawczych i rozwojowych. Zespoły powołane na potrzeby określonych projektów oparte są o osoby z wewnątrz i z zewnątrz organizacji. Wiedzy nie można traktować tylko jako jeden z produktów dostępnych na rynku, ale także jako zasób niematerialny, który wpływa na procesy wewnętrzne i zewnętrzne. Tak więc jest to niezwykle istotny potencjał dla firm i naukowych ośrodków badawczych, który ma wpływ na skuteczne zarządzanie wiedzą w zespołach projektowych. W artykule przedstawiono propozycję wykorzystania metod Fuzzy AHP (Analytic Hierarchy Process) i ANFIS (Adaptive Neuro Fuzzy Inference System) w budowaniu, kompletowaniu zespołów do realizacji projektów B + R na podstawie kwalifikacji pracowników.

9

Faults detection in gas turbine using hybrid adaptive network based fuzzy inference systems

84%

Hadroug N. , Hafaifa A. , Kouzou A. , Chaibet A.

Diagnostyka

|

2016

|

tom Vol. 17, No. 4

3--17

EN

The main aim of the present paper is the implementation of a fault detection strategy to ensure the fault detection in a gas turbine which is presenting a complex system. This strategy is based on an adaptive hybrid neuro fuzzy inference technique which combines the advantages of both techniques of neuron networks and fuzzy logic, where, the objective is to maintain the desired performance of the studied gas turbine system in the presence of faults. On the other side, the representation of fuzzy knowledge in the learning neural networks has to be accurate to provide significant improvements for modeling of the studied system dynamic behavior. The results presented in this paper proves clearly that the proposed detection technique allows the perfect detection of the studied gas turbine malfunctions, furthermore it shows that the use of the proposed technique based on the Adaptive Neuro-Fuzzy Interference System (ANFIS) approach which uses the adaptive learning mechanism of neuron networks and fuzzy inference techniques, can be a promising technique to be applied in several industrial application for faults detection.

10

Artificial intelligence approaches for spatial modeling of streambed hydraulic conductivity

84%

Deka P. C. , Naganna S. R.

Acta Geophysica

|

2019

|

tom Vol. 67, no. 3

891--903

EN

Saturated hydraulic conductivity (Ks) describes the water movement through saturated porous media. The hydraulic conductivity of streambed varies spatially owing to the variations in sediment distribution profiles all along the course of the stream. The artificial intelligence (AI) based spatial modeling schemes were instituted and tested to predict the spatial patterns of streambed hydraulic conductivity. The geographical coordinates (i.e., latitude and longitude) of the sampled locations from where the in situ hydraulic conductivity measurements were determined were used as model inputs to predict streambed Ks over spatial scale using artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS) and support vector machine (SVM) paradigms. The statistical measures computed by using the actual versus predicted streambed Ks values of individual models were comparatively evaluated. The AI-based spatial models provided superior spatial Ks prediction efficiencies with respect to both the strategies/schemes considered. The model efficiencies of spatial modeling scheme 1 (i.e., Strategy 1) were better compared to Strategy 2 due to the incorporation of more number of sampling points for model training. For instance, the SVM model with NSE = 0.941 (Strategy 1) and NSE = 0.895 (Strategy 2) were the best among all the models for 2016 data. Based on the scatter plots and Taylor diagrams plotted, the SVM model predictions were found to be much efficient even though, the ANFIS predictions were less biased. Although ANN and ANFIS models provided a satisfactory level of predictions, the SVM model provided virtuous streambed Ks patterns owing to its inherent capability to adapt to input data that are non-monotone and nonlinearly separable. The tuning of SVM parameters via 3D grid search was responsible for higher efficiencies of SVM models.

11

Predicting ground vibration caused by blasting operations in Sarcheshmeh copper mine considering the charge type by adaptive neuro-fuzzy inference system (ANFIS)

84%

Soltani-Mohammadi S. , Amnieh H. B. , Bahadori M.

Archives of Mining Sciences

|

2011

|

tom Vol. 56, no 4

701-710

EN

Ground vibration is an inevitable effect of blasting operations. The propagated wave generated, can cause serious damage to the surrounding environment and nearby structures. The type of charge used in each blast is one of the important parameters affecting this vibration. In order to study the effect of charge type, ground vibrations from 11 blasts with two different charges (ANFO and Emolan) were recorded in Sarcheshmeh copper mine by PDAS-100 digital seismographs. Seismometers were installed in three vertical, tangential and radial directions and 46 data were obtained. Data processing was carried out with the DADISP software. In this paper, using Active Neuro-Fuzzy Inference System (ANFIS) and dividing data into ANFO and Emolan sets (charge types), the sensitivity of Peak Particle Velocity (PPV) with respect to the amount of charge weight per delay and the distance from the center of the blast site was analyzed. The correlation coefficient of the estimated and the measured data in both cases is about 0.97 and the Mean Square Error (MSE) in the network testing process for ANFO and Emolan data sets are equal to 0.52 and 0.7 respectively. The amount of PPV caused by ANFO and Emolan blasting for the critical cases was predicted by ANFIS. The critical cases have the maximum charge weights for ANFO and Emolan equal to 5200 kg and 7111 kg respectively and the nearest distance to blast site equals 740 m. The PPVs estimated by ANFIS are equal to 7.42 and 7.47 mm/s for blasting by Emolan and ANFO, respectively. This study shows that the amount of ground vibration caused by high-pressure explosives has more dependence on weight of charge used.

PL

Wibracje gruntu to nieuchronny skutek robót strzałowych. Wytworzona fala uderzeniowa może spowodować poważne zniszczenia sąsiadującego terenu oraz budynków. Jednym z ważnych parametrów wpływających na wibrację jest rodzaj ładunku używanego przy każdym wybuchu. Aby zbadać wpływ rodzaju ładunku, za pomocą sejsmografów cyfrowych PDAS-100 zarejestrowano wibracje gruntu które nastąpiły po 11 wybuchach dwóch typów ładunków (ANFO i Emolan) w kopalni miedzi Sarcheshmeh. Sejsmometry zostały zainstalowane w trzech pionowych, stycznych i promieniowych kierunkach i uzyskano 46 zapisów. Dane zostały przetworzone przy użyciu oprogramowania DADISP. W niniejszej pracy, przy użyciu adaptacyjnego systemu neuro-rozmytego (ANFIS), oraz dzieląc dane na zestawy ANFO i Emolan (rodzaje ładunku), zbadano wrażliwość maksymalnej prędkości cząstki (PPV) z uwzględnieniem wagi ładunku na opóźnienia i odległości od centrum wybuchu. Współczynnik korelacji danych szacunkowych i pomiarowych wyniósł w obu przypadkach 0,97, a błąd średniokwadratowy w procesie testowania sieciowego dla zestawów danych ANFO i Emolan, wyniósł odpowiednio 0,52 i 0,7. PPV wywołane wybuchami ANFO i Emolan dla przypadków krytycznych zostały prawidłowo oszacowane przez ANFIS. W przypadkach krytycznych maksymalne wagi ładunków ANFO i Emolan wynoszą odpowiednio 5200 kg i 7111 kg, a najbliższa odległość od miejsca wybuchu wynosi 740 m. PPV oszacowane przez ANFIS wynoszą 7,42 i 7,47 mm/s, odpowiednio dla Emolan i ANFO. Badania wykazały, że wibracje gruntu spowodowane wysokociśnieniowymi ładunkami wybuchowymi zależą w dużej mierze od wagi zastosowanego ładunku.

12

ANFIS based prediction of the aluminum extraction from boehmite bauxite in the Bayer process

83%

Mihajlović I. , Đurić I. , Živković Ž.

Polish Journal of Chemical Technology

|

2014

|

tom Vol. 16, nr 1

103-109

EN

This paper presents the results of nonlinear statistical modeling of the bauxite leaching process, as part of Bayer technology for alumina production. Based on the data, collected during the year 2011 from the industrial production in the alumina factory Birač, Zvornik (Bosnia and Herzegovina), nonlinear statistical modeling of the industrial process was performed. The model was developed as an attempt to define the dependence of the Al2O3 degree of recovery as a function of input parameters of the leaching process: content of Al2O3, SiO2 and Fe2O3 in the bauxite, as well as content of Na2Ocaustic and Al2O3 in the starting sodium aluminate solution. As the statistical modeling tool, Adaptive Network Based Fuzzy Inference System (ANFIS) was used. The model, defined by the ANFIS methodology, expressed a high fitting level and accordingly can be used for the efficient prediction of the Al2O3 degree of recovery, as a function of the process inputs under the industrial conditions.

13

ANFIS based prediction of the aluminum extraction from boehmite bauxite in the Bayer process

83%

Mihajlović I. , Đurić I. , Živković Ž.

Polish Journal of Chemical Technology

|

2014

|

tom 16

|

nr 1

103-109

EN

This paper presents the results of nonlinear statistical modeling of the bauxite leaching process, as part of Bayer technology for alumina production. Based on the data, collected during the year 2011 from the industrial production in the alumina factory Birač, Zvornik (Bosnia and Herzegovina), nonlinear statistical modeling of the industrial process was performed. The model was developed as an attempt to define the dependence of the Al2O3 degree of recovery as a function of input parameters of the leaching process: content of Al2O3, SiO2 and Fe2O3 in the bauxite, as well as content of Na2Ocaustic and Al2O3 in the starting sodium aluminate solution. As the statistical modeling tool, Adaptive Network Based Fuzzy Inference System (ANFIS) was used. The model, defined by the ANFIS methodology, expressed a high fitting level and accordingly can be used for the efficient prediction of the Al2O3 degree of recovery, as a function of the process inputs under the industrial conditions.

14

ANFIS-based PID continuous sliding mode controller for robot manipulators in joint space

83%

Elawady W. M. , Asar M. F. , Sarhan A. M.

Control and Cybernetics

|

2019

|

tom Vol. 48, No. 4

525--555

EN

This paper presents a feasible design for a con- trol algorithm to synthesize an adaptive neuro-fuzzy inference system-based PID continuous sliding mode control system (ANFIS- PIDCSMC) for adaptive trajectory tracking control of the rigid robot manipulators (RRMs) in the joint space. First, a PID sliding mode control algorithm with sliding surface dynamics-based continuous proportional-integral (PI) control action (PIDSMC-SSDCPI) is presented. The global stability conditions are formulated in terms of Lyapunov full quadratic form such that the robot system output can track the desired reference output. Second, to increase the control system robustness, the PI control action in the PIDSMC- SSDCPI controller is supplanted by an ANFIS control signal to provide a control approach that can be termed adaptive neuro-fuzzy inference system-based PID continuous sliding mode control system (ANFIS-PIDCSMC). For the proposed control algorithm, numerical simulations using the dynamic model of RRM with uncertainties and external disturbances show high quality and effectiveness of the adopted control approach in high-speed trajectory tracking control problems. The simulation results that are compared with the results, obtained for the traditional controllers (standalone PID and traditional sliding mode controller (TSMC)), illustrate the fact that the tracking control behavior of the robot system achieves acceptable tracking performance.

15

Neuro-fuzzy control design of processes in chemical technologies

83%

Blahová L. , Dvoran J. , Kmeťová J.

Archives of Control Sciences

|

2012

|

tom Vol. 22, no. 2

233-250

EN

The paper presents design of neuro-fuzzy control and its application in chemical technologies. Our approach to neuro-fuzzy control is a combination of the neural predictive controller and the neuro-fuzzy controller (Adaptive Network-based Fuzzy Inference System - ANFIS). These controllers work in parallel. The output of ANFIS adjusts the output of the neural predictive controller to enhance the control performance. Such design of an intelligent control system is applied to control of the continuous stirred tank reactor and laboratory mixing process.

16

Hybrid Intelligence Modeling using Genetic Algorithm for optimizing welding process parameters of Mod. 9Cr-1Mo Stee

83%

Vasudevan M. , Gowtham K. N. , Jayakumar T.

Computer Methods in Materials Science

|

2011

|

tom Vol. 11, No. 1

16-22

EN

This abstract is for Mini symposium on Genetic Algorithm in Materials Design and Processing Modified 9Cr-1Mo ferritic steel is used as structural material for stream generator components of power plants. Generally, Tungsten Inert Gas (TIG) welding is preferred for welding these steels in which the depth of penetration achievable during autogenous welding is very limited and hence productivity is less. Therefore, Activated flux Tungsten Inert Gas (A-TIG) welding, a novel welding technique has been developed in house to increase the depth of penetration. In modified 9Cr-1Mo steel joints produced by A-TIG welding process, weld bead width, depth of penetration and Heat Affected Zone (HAZ) width play an important role in determining the mechanical properties and also the performance of the weld joints during service. To obtain the desired weld bead geometry, HAZ width and make a good weld, it becomes important to set the welding process parameters. Since the experimental optimization of these parameters is time consuming, soft-computing techniques are commonly used for optimization of the welding process parameters (welding voltage, current and torch speed). In this work, Adaptative Neuro Fuzzy Inference System (ANFIS), one of the soft-computing tools, is used to develop independent models correlating the welding process parameters like current, voltage and speed with weld bead shape parameters like depth of penetration, bead width and HAZ width. Then Genetic Algorithm is employed to determine the optimum A-TIG welding process parameters in order to obtain the desired weld bead shape parameters and HAZ width. Validation of the GA model is completed by carrying out experiments to compare the target values with that of the actual values of the weld bead shape parameters obtained. There is good agreement between the target values and the actual values.

PL

Modyfikowana stal ferrytyczna 9Cr-1MoDo wykorzystywana jest do budowy generatorów stosowanych w elektrowniach. Tego typu stale spawane są najczęściej metodą TIG (Tungsten Inert Gas), charakteryzującą się bardzo małą głębokością przetopu podczas spawania, a tym samym niską sprawnością. Dla zwiększenia głębokości przetopu opracowana została nowa technika spawania, tzw. A-TIG (Activated flux Tungsten Inert Gas). Własności mechaniczne oraz jakość wykonania spawów metodą A-TIG zależy w dużej mierze od szerokości spoiny, głębokości przetopu oraz wielkości strefy wpływu ciepła (Heat Affected Zone). Kontrola jakości spawu, czyli dobranie odpo-wiedniej szerokości spoiny oraz utrzymanie strefy ciepła HAZ, zależy od parametrów procesu. Ze względu na czasochłonności optymalizacji doświadczalnej, do określenia optymalnych para-metrów spawania zastosowano model obliczeniowy procesu połączony z algorytmem genetycznym (GA). Do wyznaczenia niezależnych modeli korelacji pomiędzy parametrami procesu: natężeniem i napięciem prądu oraz prędkością spawania, a szerokością spawu, głębokością przetopu oraz wielkością HAZ wykorzystano jedno z narzędzi ANFIS (Adaptive Neuro Fuzzy Interface System). Następnie za pomocą algorytmu genetycznego oszacowano optymalne parametry procesu spawania metodą A-TIG. W celu weryfikacji modelu wykonano doświadczenia i porównano wartości otrzymane z rzeczywistymi potwierdzając poprawność otrzymanych wyników obliczeń.

17

Improvement of microgrid dynamic performance under fault circumstances using ANFIS for fast varying solar radiation and fuzzy logic controller for wind system

83%

Izadbakhsh M. , Rezvani A. , Gandomkar M.

Archives of Electrical Engineering

|

2014

|

tom Vol. 63, nr 4

551--578

EN

The microgrid (MG) technology integrates distributed generations, energy storage elements and loads. In this paper, dynamic performance enhancement of an MG consisting of wind turbine was investigated using permanent magnet synchronous generation (PMSG), photovoltaic (PV), microturbine generation (MTG) systems and flywheel under different circumstances. In order to maximize the output of solar arrays, maximum power point tracking (MPPT) technique was used by an adaptive neuro-fuzzy inference system (ANFIS); also, control of turbine output power in high speed winds was achieved using pitch angle control technic by fuzzy logic. For tracking the maximum point, the proposed ANFIS was trained by the optimum values. The simulation results showed that the ANFIS controller of grid-connected mode could easily meet the load demand with less fluctuation around the maximum power point. Moreover, pitch angle controller, which was based on fuzzy logic with wind speed and active power as the inputs, could have faster responses, thereby leading to flatter power curves, enhancement of the dynamic performance of wind turbine and prevention of both frazzle and mechanical damages to PMSG. The thorough wind power generation system, PV system, MTG, flywheel and power electronic converter interface were proposed by Rusing Mat-lab/Simulink.

18

Predicition of compressive strength in light-weight Self-Compacting Concrete by ANFIS analytical model

72%

Vakhshouri B. , Nejadi S. , Vakhshouri B. , Nejadi S.

|

nr 2

19

Novel Adaptive Inverse Control for Permanent Magnet Synchronous Motor Servo System

71%

Yulin G. , Yongyin Q.

Przegląd Elektrotechniczny

|

2012

|

tom R. 88, nr 3b

9-14

EN

The adaptive inverse control is a novel method in control system. It makes set signal, parameter disturbance and external disturbance separately controlled and makes them reach the optimal control without compromiseThe traditional adaptive inverse control system often used FIR filters. It madde the system costing long training time and slow convergence. So, it is unable to adapt the requirement of real-time control system. In this paper, a novel adaptive inverse control with adaptive neuro-fuzzy inference system (ANFIS) was designed for permanent magnet synchronous motor (PMSM) servo system. Meanwhile the microhabitat particle swarm optimization (MPSO) algorithm and RLS algorithm were used for updating parameters for ANFIS. This hybrid learning algorithm can reduce the computing costs and improve the convergence speed. Also, the ANFIS was used to for identification and inverse modeling of PMSM servo system. The simulation results show that the PMSM servo system based on novel adaptive inverse control strategy achieve higher tracking ability, steady precision and good robustness.

PL

Przedstawiono nowy adaptacyjny system sterowania odwrotnego wykorzystujący neuronowy-rozmyty system interferencji ANFIS. System zastosowano do układu serwomechanizmu z silnikiem synchronicznym o magnesach trwałych. Dodatkowo rojowy algorytm optymalizacji oraz algorytm RLS były wykorzystywane do zmiany parametrów. Badania symulacyjne potwierdziły, że nowy system ma dobra precyzję i odporność na zakłócenia.

20

Intelligent cutting tool condition monitoring in milling

71%

Zuperl U. , Cus F. , Balic J.

Journal of Achievements in Materials and Manufacturing Engineering

|

2011

|

tom Vol. 49, nr 2

477--486

EN

Purpose: of this paper is to present a tool condition monitoring (TCM) system that can detect tool breakage in real time by using a combination of neural decision system, ANFIS tool wear estimator and machining error compensation module. Design/methodology/approach: The principal presumption was that the force signals contain the most useful information for determining the tool condition. Therefore, ANFIS method is used to extract the features of tool states from cutting force signals. The trained ANFIS model of tool wear is then merged with a neural network for identifying tool wear condition (fresh, worn). Findings: The overall machining error is predicted with very high accuracy by using the deflection module and a large percentage of it is eliminated through the proposed error compensation process. Research limitations/implications: This study also briefly presents a compensation method in milling in order to take into account tool deflection during cutting condition optimization or tool-path generation. The results indicate that surface errors due to tool deflections can be reduced by 65-78%. Practical implications: The fundamental limitation of research was to develop a single-sensor monitoring system, reliable as commercially available system, but much cheaper than multi-sensor approach. Originality/value: A neural network is used in TCM as a decision making system to discriminate different malfunction states from measured signals.