Wyniki wyszukiwania - BazTech

1

Forecasting the Flow Coefficient of the River Basin Using Adaptive Fuzzy Inference System and Fuzzy SMRGT Method

Gunal Ayse Yeter, Mehdi Ruya

Journal of Ecological Engineering

|

2023

|

Vol. 24, nr 7

96--107

EN

In hydrology and water resources engineering, predicting the flow coefficient is a crucial task that helps estimate the precipitation resulting in a surface flow. Accurate flow coefficient prediction is essential for efficient water management, flood control strategy development, and water resource planning. This investigation calculated the flow coefficient using models based on Simple Membership functions and fuzzy Rules Generation Technique (SMRGT) and an Adaptive Neuro-Fuzzy Inference System (ANFIS) model. The fuzzy logic methods are used to model the intricate connections between the inputs and the output. Statistical parameters such as the coefficient of determination (R2), the root mean square error (RMSE), the mean absolute error (MAE), and the mean absolute percentage error (MAPE) were used to evaluate the performance of models. The statistical tests outcome for the SMRGT model was (RMSE:0.056, MAE:1.92, MAPE:6.88, R2:0.996), and for the ANFIS was (RMSE:0.96, MAE:2.703, MAPE:19.97, R2:0.8038). According to the findings, the SMRGT, a physics-based model, exhibited superior accuracy and reliability in predicting the flow coefficient compared to ANFIS. This is attributed to the SMRGT’s ability to integrate expert knowledge and domain-specific information, rendering it a viable solution for diverse issues.

2

Prediction of lightning density value tower based on Adaptive Neuro-fuzzy Inference System

Said Sri Mawar, Nappu Muhammad Bachtiar, Asri Andarini, Utomo Bayu Tri

Archives of Electrical Engineering

|

2021

|

Vol. 70, nr 3

499--511

EN

Lightning is one of the causes of transmission disorders and natural phenomena that cannot be avoided. The South Sulawesi region is located close to the equator and has a high lightning density. This condition results in lightning susceptibility of distur- bances to electrical system lines, especially in high-voltage airlines and substations. An Adaptive Neuro-Fuzzy Inference System (ANFIS) will show the Root Mean Square Error (RMSE) based on the membership function type. This journal is to predict the value of the transmission tower lightning density using the ANFIS method. The value of the lightning strike density index can later be determined based on ANFIS predictions. Analysis of the value calculation system of structural lightning strikes in the South Sulawesi region of the Sungguminasa-Tallasa route can be categorized as three characteristics lightning density (Nd). The calculation system results for the value of structural lightning struck in the South Sulawesi region and validated between manual calculations and ANFIS with an average percentage of 0.0554%.

3

A class of neuro-computational methods for assamese fricative classification

Patgiri C., Sarma M., Sarma K. K.

Journal of Artificial Intelligence and Soft Computing Research

|

2015

|

Vol. 5, No. 1

59--70

EN

In this work, a class of neuro-computational classifiers are used for classification of fricative phonemes of Assamese language. Initially, a Recurrent Neural Network (RNN) based classifier is used for classification. Later, another neuro fuzzy classifier is used for classification. We have used two different feature sets for the work, one using the specific acoustic-phonetic characteristics and another temporal attributes using linear prediction cepstral coefficients (LPCC) and a Self Organizing Map (SOM). Here, we present the experimental details and performance difference obtained by replacing the RNN based classifier with an adaptive neuro fuzzy inference system (ANFIS) based block for both the feature sets to recognize Assamese fricative sounds.

4

Zastosowanie ANFIS w analizie wyników badań gruntów

Daniszewska E

Budownictwo i Architektura

|

2014

|

Vol. 13, nr 2

7--15

PL

Adaptacyjny system wnioskowania neuronowo-rozmytego ANFIS (Adaptive Neuro-Fuzzy Inference System) w programie Matlab posłużył modelowaniu i określaniu relacji między prędkością ścinania a parametrami wytrzymałościowymi gruntu. Sprawdzono możliwości i umiejętności narzędzia ANFIS w interpretacji wyników badań trójosiowego ściskania iłów pobranych z okolic Olsztyna. Model neuronowo-rozmyty został zbudowany na podstawie zbioru wartości, którymi dysponowano po szeregu badań eksperymentalnych, łącznie z wartościami parametrów wytrzymałościowych gruntu na ścinanie. Baza danych wykorzystana do modelowania neuronowo-rozmytego składa się z 6 różnych parametrów gruntowych dla każdej z 12 prędkości ścinania stosowanych podczas badań trójosiowych. Umiejętność uczenia zweryfikowano na bazie danych testowych - model neuronowo-rozmyty zbudowany został z zestawów szkoleniowych, a dokładność została zweryfikowana przez zestawy testów, z którymi model miał do czynienia po raz pierwszy. Wyniki z modelu ANFIS nie odbiegały znacznie od tych, które zostały uzyskane bezpośrednio z badań fizycznych. System ANFIS okazał się narzędziem niezwykle uniwersalnym i nieskomplikowanym w obsłudze. Pozwolił uwzględnić wieloaspektowość wzajemnych relacji parametrów gruntowych.

EN

The article was analyzed in order to test applicability and capability of the ANFIS tool used for interpretation of results of triaxial shear tests on loamy soils sampled near Olsztyn. The ANFIS system in the Matlab software programme was used to model and determine relationships between the shear stress and soil resistance parameters in a triaxial shear test apparatus. It has been demonstrated that the achieved shear strength parameters are significantly affected by the variables tested during the triaxial experiments and physical parameters of a given soil sample, but also by the loading increment rate during the tests. It is extremely important to adjust the rate of loading during a test according to the preliminary characterization of a tested ground sample so as to have some control over the obtained ground strength parameters. The neuro-fuzzy model has been constructed based on a set of values obtained after a series of experimental tests, including values of ground shear strength parameters. The database used for the neuro-fuzzy modelling consisted of 6 different ground parameters for each of the 12 shear stress rates applied during the triaxial tests. The learnability was verified on a database composed of the test results – a neuro-fuzzy model was built from learning sets and its accuracy was verified by sets of tests to which the model was applied for the first time. The results obtained from the ANFIS model did not diverge substantially from the ones obtained directly by performing the physical tests. The ANFIS proved to be highly universal and easy to operate. It accounted for the multi-faceted nature of interrelationships between ground parameters.

5

Prediction of backbreak in open pit blasting by Adaptive Neuro-Fuzzy Inference System

Bazzazi A. A., Esmaeili M.

Archives of Mining Sciences

|

2012

|

Vol. 57, no. 4

933--943

EN

Adaptive neuro-fuzzy inference system (ANFIS) is powerful model in solving complex problems. Since ANFIS has the potential of solving nonlinear problem and can easily achieve the input-output mapping, it is perfect to be used for solving the predicting problem. Backbreak is one of the undesirable effects of blasting operations causing instability in mine walls, falling down the machinery, improper fragmentation and reduction in efficiency of drilling. In this paper, ANFIS was applied to predict backbreak in Sangan iron mine of Iran. The performance of the model was assessed through the root mean squared error (RMSE), the variance account for (VAF) and the correlation coefficient (R2) computed from the measured of backbreak and model-predicted values of the dependent variables. The RMSE, VAF, R2 indices were calculated 0.6, 0.94 and 0.95 for ANFIS model. As results, these indices revealed that the ANFIS model has very good prediction performance.

PL

Adaptywny system wnioskowania wykorzystujący elementy sieci neuronowych i logiki rozmytej (ANFIS) stanowi potężny narzędzie do rozwiązywania złożonych problemów. Ponieważ model ANFIS może być wykorzystywany do rozwiązywania problemów nieliniowych i umożliwia wygodne przedstawienie problemu w formie: wejście - wyjście, jest idealnym narzędziem do rozwiązywania problemów związanych z prognozowaniem. Pękanie skał w odkrywce jest jednym z niekorzystnych skutków prowadzenia prac strzałowych, powoduje niestabilność ścian, uszkodzenia maszyn i urządzeń, nieodpowiednią fragmentację skał oraz prowadzi do obniżenia efektywności wierceń. W pracy przedstawiono zastosowanie systemu ANFIS do prognozowania pękań skał w kopalni rud żelaza w Sangan (Iran). Działanie modelu zbadano na podstawie wartości błędu średniokwadratowego (RMSE), wariancji (VAF) i współczynnika korelacji (R2) obliczonego na podstawie pomiarów pęknięć skał i wartości uzyskanych z modelowania. Wartości wskaźników RMSE, VAF i R2 obliczonych przy użyciu modelu ANFIS wynoszą odpowiednio 0.6, 0.94 i 0.95. Wielkości te wyraźnie potwierdzają wysoką skuteczność modelu.

6

ANFIS and neural network techniques for non-parametric modelling of a twin rotor system

Toha S. F., Tokhi M. O.

Systems Science

|

2010

|

Vol. 36, no 4

13-31

EN

Interest in system identification especially for nonlinear systems has significantly increased in the past few decades. Soft-computing methods which concern computation in an imprecise environment have gained significant attention amid widening studies of explicit mathematical modelling. In this research, three different soft computing techniques that are multi-layered perceptron neural network using Levenberg-Marquardt (LM), Elman recurrent neural network and adaptive neuro-fuzzy inference system (ANFIS) network are deployed and used for modelling a twin rotor multi-input multi-output system (TRMS). The system is perceived as a challenging engineering problem due to its high nonlinearity, cross coupling between horizontal and vertical axes and inaccessibility of some of its states and outputs for measurements. Accurate modelling of the system is thus required so as to achieve satisfactory control objectives. It is demonstrated experimentally that soft computing methods can be effectively used for modelling the system with highly accurate results. The accuracy of the modelling results is demonstrated through validation tests including training and test validation and correlation tests.

7

Characterization of syndiotactic polystyrene / carbon nanofiber composites through X-ray diffraction using adaptive neuro-fuzzy interference system and artificial neural network

Bose S., Shome D., Das C.K.

Archives of Computational Materials Science and Surface Engineering

|

2009

|

Vol. 1, nr 4

197-204

EN

Purpose: The purpose of the paper is to characterize of syndiotactic polystyrene/carbon nanofiber composites through X-ray diffraction using adaptive neuro-fuzzy interference system and artificial neural network. Owing to their interesting mechanical, electrical and thermal properties, syndiotactic polystyrene (s-PS)/carbon nanofiber (CNF) composites have gained adequate importance in the scientific and industrial communities and as a result, characterization of s-PS/CNF is an issue of major interest to the researchers. Design/methodology/approach: In the present paper, two quantitative models, based on adaptive neuro-fuzzy interference system (ANFIS) and artificial neural network (ANN), are developed and compared with a goal of accurately predicting the intensity values from the scattering angle values in X-ray Diffraction (XRD) of syndiotactic polystyrene (s-PS)/carbon nanofiber (CNF) composites. Findings: Results demonstrate that both the proposed models are highly effective in estimating intensity from scattering angle. However, more accurate results are obtained with the ANFIS model as compared to the ANN model. Research limitations/implications: The results of the investigations carried out in this study is suggestive of the fact that both ANFIS and ANN can be used quite effectively for prediction of intensity from scattering angle values in XRD of s-PS/CNF composites. Originality/value: The proposed ANFIS and ANN model-predicted intensity values are in very good agreement with the experimental intensity values. However, it is seen that, irrespective of the type of composite sample, the proposed ANFIS models outperform the proposed ANN models in terms of prediction accuracy.