Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 3

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: ANFIS system

Sortuj według:

Ogranicz wyniki do:

Applications of neuro-fuzzy system ANFIS for predictions of time series

Kashpruk N.

Zeszyty Naukowe. Elektryka / Politechnika Opolska

2017

z. 75

31--32

This paper presents the calculations, which have been carried out on the base of the chosen technological process. The data set is a realization of a very high variation stochastic process, with constant mean value and white noise disturbances. The results of the ANFIS predictions depend on the number of data in the dataset as well as on the number of fuzzy sets in the neuro-fuzzy structure. When the dataset number and the number of fuzzy sets are increasing, then the absolute error and relative error are clearly decreasing.

Adaptive Neuro-Fuzzy Inference System-Based Pulverizing Capability Model for Running Time Assessment of Ball Mill Pulverizing System

Cao H., Wang Y., Jia L.

Przegląd Elektrotechniczny

2013

R. 89, nr 5

122-127

Ball mill pulverizing system (BMPS) of thermal power plant has high energy consumption and the running time assessment of BMPS is of important theoretical significance and practical motivation for the energy saving. In the paper, an adaptive neuro-fuzzy inference system-based pulverizing capability model (ANFIS-PCM) for running time assessment of BMPS is proposed. The proposed model integrates of the artificial neural network and the Takagi-Sugeno type fuzzy rule to construct an input-output mapping based on both human knowledge and stipulated input-output data pair. For the proposed method, the subtractive clustering algorithm is used to obtain the initial rules, and the membership functions and the rules could be determined by the learning ability. The proposed model is performed on the field data under different work conditions. The experiments results verify that the proposed model has higher prediction precision. Moreover, the proposed model has been put into practice and the field operation curve verifies that the pulverizing capability could be predicted correctlly and the running time assessment of BMPS would be realized.

W artykule przedstawiono model szacowania czasu pracy urządzenia do proszkowania w młynie kulowym, opracowany w oparciu o system wnioskowania neuro-rozmytego. W systemie zintegrowano sztuczną sieć neuronową oraz model rozmyty Takagi-Sugeno. Proponowany model zbudowano na podstawie pomierzonych wartości w różnych warunkach pracy. Przeprowadzono zostały próby weryfikujące skuteczność działania, które potwierdziły wysoką sprawność algorytmu.

A Probabilistic-Fuzzy System Applied To Modeling Of Time Series

Błaszczyk K.

Zeszyty Naukowe. Elektryka / Politechnika Opolska

2009

z. 62

15-16

The paper describes an approach to time series modeling using probabilistic-fuzzy system. Results of prediction for experimental data are compared with the results obtained from fuzzy inference system FIS and neuro-fuzzy system ANFIS.