Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: trójosiowe badanie gruntu

Sortuj według:

Ogranicz wyniki do:

Zastosowanie ANFIS w analizie wyników badań gruntów

Daniszewska E

Budownictwo i Architektura

2014

Vol. 13, nr 2

7--15

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.

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.

Determination of the shear speed of soil triaxial testing based on fuzzy logic

Tran C.

Computer Assisted Mechanics and Engineering Sciences

2008

Vol. 15, No. 2

113-121

To design foundations, embankments and other soil structures, geotechnical engineers require methods of assessing engineering properties of soils. Some of the more complex phenomena that occur in soils have often been difficult to recreate in a laboratory: seismic activity, vibration, unsaturated condition, control of principal stresses etc. are areas which have proven difficult to replicate, despite their importance of being understood. This was partly due to the lack of test systems capable of reproducing these effects and the complexity of test systems that were developed to carry out such work. A number of advanced computer/software controlled systems allow the geotechnical engineer to perform the most complex test regimes via a user-friendly software interface. However, it is difficult to determine firstly parameters needed, e.g. shear speed in soil triaxial testing. In this paper we represent a new approach to determine this shear speed by solving the inverse problem using testing results obtained by the forward procedure. Direct search method, i.e. Adaptive Neuro-Fuzzy Inference System (ANFIS), is developed and applied to soil triaxial shear tests. It allows us to use the advanced sensor and actuator technologies in order to change the traditional triaxial shear apparatus from a mechanical system to a mechatronics system in next work.