Use of a Neural Network to Predict Strength and Optimum Compositions of Natural Alumina-Silica-Based Geopolymers

In order to predict compressive strength of geopolymers prepared from alumina-silica natural products, based on the effect of Al 2 O 3 /SiO 2, Na 2 O/Al 2 O 3, Na 2 O/H 2 O, and Na/[Na+K], more than 50 pieces of data were gathered from the literature. The data was utilized to train and test a multilayer artificial neural network (ANN). Therefore a multilayer feedforward network was designed with chemical compositions of alumina silicate and alkali activators as inputs and compressive strength as output. In this study, a feedforward network with various numbers of hidden layers and neurons were tested to select the optimum network architecture. The developed three-layer neural network simulator model used the feedforward back propagation architecture, demonstrated its ability in training the given input/output patterns. The cross-validation data was used to show the validity and high prediction accuracy of the network. This leads to the optimum chemical composition and the best paste can be made from activated alumina-silica natural products using alkaline hydroxide, and alkaline silicate. The research results are in agreement with mechanism of geopolymerization.


Read More: http://ascelibrary.org/doi/abs/10.1061/(ASCE)MT.1943-5533.0000829

Characterisation of polyethylene powders for rotational moulding and effect of powder size and shape on densification behaviour

The particle size, shape and distribution of a range of rotational moulding polyethylenes (PEs) ground to powder was investigated using a novel visual data acquisition and analysis system (TP Picture®), developed by Total Petrochemicals. Differences in the individual particle shape factors of the powder samples were observed and correlations with the grinding conditions were determined. When heated, the bubble dissolution behaviour of the same powders was investigated and the shape factor correlated with densification rate, bubble size and bubble distribution.

The effect of pigment on rotomoulded polyethylene powder and micropellets

This paper presents the results from investigations into the differences in the rotational moulding and mechanical properties between pigmented polyethylene powder and micropellets. Both high shear and low shear pigment blending methods were examined, as were a range of pigment addition levels. This was followed by a series of mechanical and analytical tests on the rotomoulded articles to determine properties. Whilst micropellets tended to produce a different surface porosity than powder, few bubbles were evident within the wall thickness for both high shear and low shear blending. For high shear blending, with pigment addition levels up to 0.05%, similar impact properties were noticed for both powder and micropellets. Low shear blending resulted in more inconsistent impact values. There were also more visual inconsistencies in articles produced from powder.