Experimental data modeling neural networks

Using these experimental data, artificial neural network models for predicting fractal dimension have been developed using multi-layer feed-forward back propagation algorithm. 

The technique involves the deformation of a flat sheet of test fabric with compressed air into an extended blister and is more sensitive in the lower biaxial strain region (3-5%) that occurs in airbag inflation. The prediction of the proposed neural network model was found to be in excellent agreement with the experimental data. The neural network model performed extremely well for first predictions after training and has the potential to be used for on-line simulation of airbag deployment studies. 

VR, the inputs correspond to the value of the various parameters and the network is 1 to reproduce the experimentally determined activities. Once trained, the activity of mown compound can be predicted by presenting the network with the relevant eter values. Some encouraging results have been reported using neural networks, have also been applied to a wide range of problems such as predicting the secondary ire of proteins and interpreting NMR spectra. One of their main advantages is an to incorporate non-linearity into the model. However, they do present some problems Hack et al. 1994] for example, if there are too few data values then the network may memorise the data and have no predictive capability. Moreover, it is difficult to the importance of the individual terms, and the networks can require a considerable 1 train. 

An artificial neural network based approach for modeling physical properties of nine different siloxanes as a function of temperature and molecular configuration will be presented. Specifically, the specific volumes and the viscosities of nine siloxanes were investigated. The predictions of the proposed model agreed well with the experimental data [41]. 

A list of the systems investigated in this work is presented in Tables 8-10. These systems represent 4 nonpolar binaries, 8 nonpolar/polar binaries, and 9 polar binaries. These binary systems were recognized by Heil and Prausnitz [55] as those which had been well studied for a wide range of concentrations. With well-documented behavior they represent a severe test for any proposed model. The experimental data used in this work have been obtained from the work of Alessandro [53]. The experimental data were arbitrarily divided into two data sets one for use in training the proposed neural network model and the remainder for validating the trained network. 

In this approach, connectivity indices were used as the principle descriptor of the topology of the repeat unit of a polymer. The connectivity indices of various polymers were first correlated directly with the experimental data for six different physical properties. The six properties were Van der Waals volume (Vw), molar volume (V), heat capacity (Cp), solubility parameter (5), glass transition temperature Tfj, and cohesive energies ( coh) for the 45 different polymers. Available data were used to establish the dependence of these properties on the topological indices. All the experimental data for these properties were trained simultaneously in the proposed neural network model in order to develop an overall cause-effect relationship for all six properties. 

Chapter 17 - Vapor-liquid equilibrium (VLE) data are important for designing and modeling of process equipments. Since it is not always possible to carry out experiments at all possible temperatures and pressures, generally thermodynamic models based on equations on state are used for estimation of VLE. In this paper, an alternate tool, i.e. the artificial neural network technique has been applied for estimation of VLE for the binary systems viz. tert-butanol+2-ethyl-l-hexanol and n-butanol+2-ethyl-l-hexanol. The temperature range in which these models are valid is 353.2-458.2K at atmospheric pressure. The average absolute deviation for the temperature output was in range 2-3.3% and for the activity coefficient was less than 0.009%. The results were then compared with experimental data. 

The neural network model for the two binary systems viz. tert-butanol+2-ethyl-l-hexanol and n-butanol+2-ethyl-l-hexanol is based on the experimental data reported by Ghanadzadeh et al. [23], The summary of the data is shown in tables 1 and 2. All neural networks take numeric input and produce numeric output. The transformation function of a neuron is typically chosen so that it can accept input in any range, and produce output in a strictly limited range. Although the input can be in any range, there is a saturation effect so that the unit is only sensitive to inputs within a fairly limited range. Numeric values have to be scaled into a range that is appropriate for the network. 

Such applications of NN as a predictive method make the artificial neural networks another technique of data treatment, comparable to parametric empirical modeling by, for example, numerical regression methods [e.g., 10,11] briefly mentioned in section 16.1. The main advantage of NN is that the network needs not be programmed because it learns from sets of experimental data, which results in the possibility of representing even the most complex implicit functions, and also in better modeling without prescribing a functional form of the actual relationship. Another field of... 

Afantitis et al. investigated the use of radial basis function (RBF) neural networks for the prediction of Tg [140]. Radial basis functions are real-valued functions, whose value only depends on their distance from an origin. Using the dataset and descriptors described in Cao s work [130] (see above), RBF networks were trained. The best performing network models showed high correlations between predicted and experimental values. Unfortunately the authors do not formally report an RMS error, but a cursory inspection of the reported data in the paper would suggest approximate errors of around 10 K. 

Once a good fit between experimental and calculated data has been obtained, the model function given by the neural network may be tested and, if adequate, used for simulation and prediction purposes. 

Example of Application Large-Scale Actinometry. Neural network modelling was applied to large-scale actinometry in a continuous elliptical photochemical reactor with a concentric annular reaction chamber [2, 3,108, 148], Uranyl oxalate was used as an actinometer, which is based on the photosensitized decomposition of oxalate ions (Eq. 89) [2, 3] the experimental data were taken from the literature [108],... 

Court (2), Eberhard (3), and Tyagi et al. (4) have reported some applications of computers and software sensors for fermentation control in experimental research in data acquisition of bioreactors. Neural network models were used to interprete sensor signals in the control of an alcohol fed-batch fermentation (5) and in the detection of the individual components of a gas mixture and to measure the concentration of both gases (6). 

Molecular mechanics is a simple technique for scanning the potential energy surface of a molecule, molecular ion, crystal lattice or solvate. The model is based on a set of functions which may or may not be based on chemical and physical principles. These functions are parameterized based on experimental data. That is, the potential energy surface is not computed by fundamental theoretical expressions but by using functions whose parameters are derived empirically by reproducing experimentally observed data. Molecular mechanics then is, similar to a neural network, completely dependent on the facts that it has been taught. The quality of results to be obtained depends on the choice of the experimental data used for the parameterization. Clearly, the choice of potential energy functions is also of some importance. The most common model used is loosely derived from... 

---