PL
 |
EN
Preferencje help
Polish version English version Język
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 8

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  dynamic neural networks
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
1
Modelowanie rekrystalizacji dynamicznej za pomocą dynamicznych sieci neuronowych
Stanisławczyk A., Kusiak J.
Hutnik, Wiadomości Hutnicze
|
2009
|
Vol. 76, nr 8
659-661
PL
W pracy zaprezentowano neuronowy model naprężenia uplastyczniającego dla mikrostopowej stali z dodatkiem niobu. W modelowaniu wykorzystano dynamiczną sieć neuronową typu LRN (Layer-Recurrent Network). Model uwzględnia dwa kluczowe w procesie rekrystalizacji dynamicznej parametry: temperaturę i prędkość odkształcenia. Opracowany model cechuje się wysoką dokładnością przewidywania wartości naprężenia uplastyczniającego (błąd RMSE równy 3,1 MPa), oraz bardzo dużą szybkością działania. Przedstawione wyniki potwierdzają przydatność dynamicznych sieci neuronowych w modelowaniu zjawisk i procesów dynamicznych.
EN
The paper presents the neural network model of the flow stress for nobium microalloyed steel. The dynamic neural network of the type LRN (Layer-Recurrent Network) was used in modelling. The model takes into account two key parameters in the dynamic recrystallization: temperature and strain rate. The model characterizes high accuracy of flow stress prediction (RMSE equals 3.1 MPa), and the very high speed. Introduced model confirms the usefulness of dynamic neural networks in the dynamic processes modelling.
2
Content available remote Neural network modelling of the gas phase of a copper flash smelting process
Stanisławczyk A., Kusiak J.
Computer Methods in Materials Science
|
2009
|
Vol. 9, No. 3
374-378
EN
The paper presents the results of modelling of gaseous phase parameters of the copper flash smelting process. Models based on static and dynamic artificial neural networks are presented. The worked out models can be used for process optimisation, in turn resulting in reduction of the amount of harmful waste in the environment.
PL
Celem pracy jest prezentacja wyników modelowania para-metrów fazy gazowej dla procesu wytopu miedzi w piecu za-wiesinowym. W pracy zaprezentowano modele oparte o statyczne i dynamiczne sztuczne sieci neuronowe. Opracowane modele mogą być zastosowane do optymalizacji procesu, prowadzącej m.in. do zmniejszenia ilość odpadów szkodliwych dla środowiska.
3
Content available remote Towards robustness in neural network based fault diagnosis
Patan K., Witczak M., Korbicz J.
International Journal of Applied Mathematics and Computer Science
|
2008
|
Vol. 18, no 4
443-454
EN
Challenging design problems arise regularly in modern fault diagnosis systems. Unfortunately, classical analytical techniques often cannot provide acceptable solutions to such difficult tasks. This explains why soft computing techniques such as neural networks become more and more popular in industrial applications of fault diagnosis. Taking into account the two crucial aspects, i.e., the nonlinear behaviour of the system being diagnosed as well as the robustness of a fault diagnosis scheme with respect to modelling uncertainty, two different neural network based schemes are described and carefully discussed. The final part of the paper presents an illustrative example regarding the modelling and fault diagnosis of a DC motor, which shows the performance of the proposed strategy.
4
Content available remote Zastosowanie dynamicznych sieci neuronowych do modelowania procesu wytopu miedzi w piecu zawiesinowym
Stanisławczyk A., Talar J., Jarosz P., Kusiak J.
Computer Methods in Materials Science
|
2006
|
Vol. 6, No. 2
116-122
PL
W pracy przedstawiono przykłady wykorzystania dynamicznych SSN do modelowania złożonych procesów przemysłowych, w których obserwuje się opóźnienie sygnałów wyjściowych w stosunku do zmiany sygnałów wejściowych. Uzyskane wyniki przewidywania wielkości wyjściowych opóźnionych w stosunku do sygnałów wejściowych dla prostej funkcji zainspirowały Autorów do podjęcia próby wykorzystania sieci dynamicznych do modelowania rzeczywistego, złożonego procesu przemysłowego. Przedmiotem analizy był zawiesinowy procesu wytopu miedzi. Analizie poddano wpływ opóźnienia pomiaru nadawy koncentratu na temperaturę gazów za kotłem odzysknicowym. Uzyskane wyniki modelowania tego procesu z wykorzystaniem sieci dynamicznych potwierdzają ich przydatność do tego rodzaju zastosowań. Sieci dynamiczne lepiej odwzorowują rzeczywisty przebieg zmian temperatury niż sieci statyczne. Analizowany problem potwierdza fakt, że sieci dynamiczne są bardziej uniwersalne od sieci statycznych w przypadku modelowania procesów z opóźnieniami.
EN
The main objective of the work is evaluation of effectiveness of the dynamic neural networks in modelling of the copper flash smelting process. The fundamentals of the dynamic neural networks were presented in the paper. This type of neural networks was tested in solving the theoretical problem with time-lag. Next, the dynamic neural networks were applied to prediction of the chosen output parameters of the copper flash smelting process. The work presents the comparison of the results obtained by dynamic and static neural networks.
5
Content available remote Neural Network Fault Detection System for Dynamic Processes
Korbicz J., Patan K., Obuchowicz A.
Bulletin of the Polish Academy of Sciences. Technical Sciences
|
2001
|
vol. 49, nr 2
301-321
EN
The neural model-based Fault Detection and Isolation (FDI) system for dynamic non-linear processes is considered. The emphasis is placed upon the use of Artificial Neural Networks (ANN's) for residual generation. The proposed network is constructed with the Dynamic Neuron Model (DNM) which contains local memory. Similar to server based schemes, a network is applied to build the nominal and fault models of the investigated system. The output residuals between the process and the models bank are use to detect and identify faults in the system. The modelling efficiency based on the multilayer feedforward Network of Dynamic Neurons (NDN) is compared with the Elman and recurrent network with outside feedbacks. Finally, the NDN and the cascade NDN architectures are applied to build Neural-Residual Generators (NRG) of the two tank system.
6
Content available remote Dynamic Neural Networks for Process Modelling in Fault Detection and Isolation Systems
Korbicz J., Patan K., Obuchowicz A.
International Journal of Applied Mathematics and Computer Science
|
1999
|
Vol. 9, no 3
519-546
EN
A fault diagnosis scheme for unknown nonlinear dynamic systems with modules of residual generation and residual evaluation is considered. Main emphasis is placed upon designing a bank of neural networks with dynamic neurons that model a system diagnosed at normal and faulty operating points.To improve the quality of neural modelling, two optimization problems are included in the construction of such dynamic networks: searching for an optimal network architecture and the network training algorithm. To find a good solution, the effective well-known cascade-correlation algorithm is adapted here. The residuals generated by a bank of neural models are then evaluated by means of pattern classification. To illustrate the effectiveness of our approach, two applications are presented: a neural model of Narendra's system and a fault detection and identification system for the two-tank process.
7
Content available remote Development of Dynamic Neural Networks With Application to Observer-Based Fault Detection and Izolation
Marcu T., Mirea L., Frank P. M.
International Journal of Applied Mathematics and Computer Science
|
1999
|
Vol. 9, no 3
547-570
EN
The paper suggests a neural-network approach to the design of robust fault diagnosis systems. The main emphasis is placed upon the development of neural observer schemes. They are built based on dynamic neural networks, i.e. dynamic multi-layer perceptrons with mixed structure. The goal is to achieve an adequate approximation of process outputs for known classes of the process behaviour. The obtained symptoms are then classified by means of static artificial nets. Appropriate decision mechanisms are designed for each type of observer schemes. An application to a laboratory process is included. It refers to component and instrument fault detection and isolation in a three-tank system.
8
Content available remote Robust identification by dynamic neural networks using sliding mode learning
Poznyak A. S., Yu W., Sanchez E. N., Sira-Ramirez H.
Applied Mathematics and Computer Science
|
1998
|
Vol. 8, no 1
135-144
EN
The problem of identification of continuous, uncertain nonlinear systems in the presence of bounded disturbances is implemented using dynamic neural networks. The proposed neural identifier guarantees a bound for the state estimation error. This bound turns out to be a linear combination of internal and external uncertainty levels. The neural net weights are updated on-line by a learning algorithm based on the sliding mode technique. To the best of the authors' knowledge, such a learning scheme is proposed for dynamic neural networks for the first time. Numerical simulations illustrate its effectiveness, even for highly nonlinear systems in the presence of important disturbances.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.