Search Results

You are looking at 1 - 7 of 7 items for :

  • "Marquardt algorithm" x
  • Refine by Access: All Content x
Clear All

In the paper a combined inversion algorithm solving the nonlinear geophysical well-logging inverse problem is presented. We apply a successive combination of a float-encoded Genetic Algorithm as a global optimization method and the well-known linearized Marquardt algorithm forming a fast inversion procedure. The technique is able to decrease the CPU run time at least one order of magnitude compared to the Genetic Algorithm and gives the parameter estimation errors having a few linearized optimization steps at the end of the iteration process. We use depth-dependent tool response equations to invert all the data of a greater depth-interval jointly in order to determine petrophysical parameters of homogeneous or inhomogeneous layers in one inversion procedure. The so-called interval inversion method gives more accurate and reliable estimation for the petrophysical model parameters than the conventional point by point inversion methods. It also enables us to determine the layer-thicknesses that can not be extracted from the data set by means of conventional inversion techniques. We test the combined interval inversion method on synthetic data, and employ it to the interpretation of well logs measured in a Hungarian hydrocarbon exploratory borehole.

Restricted access

set to train, test, and validate the experimental data. Finally, the Levenberg-Marquardt algorithm is used for iterative trial and error procedures to achieve the best output parameter. The performance of the ANN modelling was compared to the results

Open access

Abstract  

The tendency of selenium to interact with heavy metals in presence of naturally occurring species has been exploited for the development of green bioremediation of toxic metals from soil using Artificial Neural Network (ANN) modeling. The cross validation of the data for the reduction in uptake of Hg(II) ions in the plant R. sativus grown in soil and sand culture in presence of selenium has been used for ANN modeling. ANN model based on the combination of back propagation and principal component analysis was able to predict the reduction in Hg uptake with a sigmoid axon transfer function. The data of fifty laboratory experimental sets were used for structuring single layer ANN model. Series of experiments resulted into the performance evaluation based on considering 20% data for testing and 20% data for cross validation at 1,500 Epoch with 0.70 momentums The Levenberg–Marquardt algorithm (LMA) was found as the best of BP algorithms with a minimum mean squared error at the eighth place of the decimal for training (MSE) and cross validation.

Restricted access
Reaction Kinetics, Mechanisms and Catalysis
Authors:
Cristina Benincá
,
Patrício Peralta-Zamora
,
Ronaldo Cardoso Camargo
,
Célia Regina Granhen Tavares
,
Everton Fernando Zanoelo
, and
Luciana Igarashi-Mafra

independent variables must be defined on a coded scale from –1 to +1. The parameters estimated in this regression model are related to the effects of the factors [ 29 – 31 ]. A Levenberg–Marquardt algorithm for nonlinear least-squares was applied to obtain the

Restricted access

-linear models. There are vast numbers of optimization methods that can be applied to parameter estimation, such as the Levenberg–Marquardt algorithm [ 33 ], and orthogonal collocation on finite elements [ 2 , 17 ]. These methods make use of algebraic objective

Restricted access

networks with the Marquardt algorithm ,” IEEE Trans. Neural Networks , vol.  5 , no. 6 , pp. 989 – 993 , 1994 . [39] Z. Cömert and A. Kocamaz , “ A study of artificial neural network training algorithms for classification of cardiotocography

Restricted access

: Simultaneous exponential regression of the data in the initial and final periods is currently carried out using a freeware program (Visual Basic routine for non-linear regression, based on the Levenberg–Marquardt algorithm, available from the website http

Restricted access