Application of a Bayesian Artificial Neural Network and the Reversible Jump Markov Chain Monte Carlo Method to predict the grain size of hot strip low carbon steels

Botlani-Esfahani, Mohsen; Toroghinejad, Mohammad Reza
July 2012
Journal of the Serbian Chemical Society;2012, Vol. 77 Issue 7, p937
Academic Journal
An Artificial Neural Network (ANN) with Reversible Jump Markov Chain Monte Carlo (RJMCMC) simulation was used to predict the grain size of hot strip low carbon steels, as a function of steel composition. The results show good agreement with experimental data taken from the Mobarakeh Steel Company (MSC). The developed model is capable of recognizing the role and importance of elements in grain refinement. Furthermore, the effects of these elements, including manganese, silicon and vanadium, were investigated in the present study, which were in good agreement with the literature.


Related Articles

  • Integration of Support Vector Machine and Bayesian Neural Network for Data Mining and Classification.  // World Academy of Science, Engineering & Technology;Apr2010, Issue 40, p202 

    No abstract available.

  • Artificial neural network assisted Bayesian calibration of climate models. Hauser, Tristan; Keats, Andrew; Tarasov, Lev // Climate Dynamics;Jul2012, Vol. 39 Issue 1/2, p137 

    We demonstrate and validate a Bayesian approach to model calibration applicable to computationally expensive General Circulation Models (GCMs) that includes a posterior estimate of the intrinsic structural error of the model. Bayesian artificial neural networks (BANNs) are trained with output...

  • Non-Gaussian spatiotemporal modelling through scale mixing. Fonseca, Thaís C. O.; Steel, Mark F. J. // Biometrika;Dec2011, Vol. 98 Issue 4, p761 

    We construct non-Gaussian processes that vary continuously in space and time with nonseparable covariance functions. Starting from a general and flexible way of constructing valid nonseparable covariance functions through mixing over separable covariance functions, the resulting models are...

  • Markov chain estimation for test theory without an answer key. Karabatsos, George; Batchelder, William // Psychometrika;Sep2003, Vol. 68 Issue 3, p373 

    This study develops Markov Chain Monte Carlo (MCMC) estimation theory for the General Condorcet Model (GCM), an item response model for dichotomous response data which does not presume the analyst knows the correct answers to the test a priori (answer key). In addition to the answer key,...

  • Bayesian calibration of process-based forest models: bridging the gap between models and data. Marcel MV Van Oijen; Jonathan JR Rougier; Ron RS Smith // Tree Physiology;Jul2005, Vol. 25 Issue 7, p915 

    Process-based forest models generally have many parameters, multiple outputs of interest and a small underlying empirical database. These characteristics hamper parameterization. Bayesian calibration offers a solution to the calibration problem because it applies to models of any type or size....

  • Bayesian estimation of a multilevel IRT model using gibbs sampling. Fox, Jean-Paul; Glas, Cees // Psychometrika;Jun2001, Vol. 66 Issue 2, p271 

    In this article, a two-level regression model is imposed on the ability parameters in an item response theory (IRT) model. The advantage of using latent rather than observed scores as dependent variables of a multilevel model is that it offers the possibility of separating the influence of item...

  • Stochastic Volatility: Likelihood Inference and Comparison with ARCH Models. Kim, Sangjoon; Shephard, Neil; Chib, Siddhartha // Review of Economic Studies;Jul98, Vol. 65 Issue 3, p361 

    In this paper, Markov chain Monte Carlo sampling methods are exploited to provide a unified, practical likelihood-based framework for the analysis of stochastic volatility models. A highly effective method is developed that samples all the unobserved volatilities at once using an approximating...

  • Bayesian sampling of genomic rearrangement scenarios via double cut and join. Miklós, István; Tannier, Eric // Bioinformatics;Dec2010, Vol. 26 Issue 24, p3012 

    Motivation: When comparing the organization of two genomes, it is important not to draw conclusions on their modes of evolution from a single most parsimonious scenario explaining their differences. Better estimations can be obtained by sampling many different genomic rearrangement scenarios....

  • Estimation of recruitment in catch-at-age models. Maunder, Mark N.; Deriso, Richard B. // Canadian Journal of Fisheries & Aquatic Sciences;Oct2003, Vol. 60 Issue 10, p1204 

    Management strategies must be designed to take into account the uncertainty inherent in fish populations and their assessments. Annual recruitment variation is an important component of uncertainty. Several methods that allow the estimation of annual recruitment in statistical catch-at-age...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics