Phase equilibrium modeling of semi-clathrate hydrates of seven commonly gases in the presence of TBAB ionic liquid promoter based on a low parameter connectionist technique

Connectionist intelligent model estimates output power and torque of stirling engine

“…An ANN paradigm is made up of a huge number of extremely interconnected processing elements, similar to neurons (are referred to artificial neurons (ANs)) that are joined together with weighted connections that are similar to synapses. ANNs are known as massively parallel-distributed information processors which have propensity for identifying highly complex and non-linear patterns within available data [60,61]. Although several types of ANN strategies (i.e.…”

A least-squares support vector machine approach to predict temperature drop accompanying a given pressure drop for the natural gas production and processing systems

“…SVM is a very effective approach and has been used widely for classification, regression and pattern recognition (Cortes and Vapnik, 1995). The principle idea of SVM is transforming the nonlinear input space to a high-dimensional characteristic space and finds a hyper plane via a nonlinear mapping (Baylar et al, 2009;Ahmadi et al, 2014e;2015a;2015b;2015c;Baghban et al, 2015;Ahmadi and Bahadori, 2015;Ahmadi, 2015). This novel approach is based upon the structural risk minimization (SRM) and the statistical learning theorem (SLT) concepts (Mehdizadeh and Movagharnejad, 2011).…”

“…Suykens and Vandewalle (1999) proposed least squares-support vector machine (LSSVM) models as an alternate formulation of SVM regression. LSSVM enjoys A c c e p t e d M a n u s c r i p t 5 similar advantages as SVM, in addition it requires solving a set of only linear equations (linear programming) instead of a quadratic programming (QP) problem, which is computationally simpler and makes the problem easier to deal with (Ahmadi et al, 2014e;2015a;2015b;2015c;Baghban et al, 2015;Ahmadi and Bahadori, 2015;Ahmadi, 2015).…”

“…and refers to the number of the training samples. Using nonlinear function , which maps the training set in input space to the high (and possibly infinite) dimensional space, the following regression model is constructed (Ahmadi et al, 2014e;2015a;2015b;2015c;Baghban et al, 2015;Ahmadi and Bahadori, 2015;Ahmadi, 2015):…”

Experimental and modeling study on the phase equilibria for hydrates of gas mixtures in TBAB solution

“…Good prediction results are obtained over wide ranges of salt concentrations and pressures. Baghban et al (2015) have developed a Support Vector Machine (SVM) model and coupling of Support Vector Machine with Genetic Algorithm (GA-SVM) model to predict semi-clathrate hydrate pressure of CO 2 , CH 4 , N 2 , H 2 , Ar, Xe and H 2 S in TBAB aqueous solution. A low parameter connectionist technique was applied to predict phase equilibrium modeling of semi-clathrate hydrates with the fast rate and cheap method of calculation.…”