Artificial neural network for prediction of air flow in a single rock joint
- Authors: Ranjith, Pathegama , Khandelwal, Manoj
- Date: 2012
- Type: Text , Journal article
- Relation: Neural Computing and Applications Vol. 21, no. 6 (2012), p. 1413-1422
- Full Text: false
- Reviewed:
- Description: In this paper, an attempt has been made to evaluate and predict the air flow rate in triaxial conditions at various confining pressures incorporating cell pressure, air inlet pressure, and air outlet pressure using artificial neural network (ANN) technique. A three-layer feed forward back propagation neural network having 3-7-1 architecture network was trained using 37 data sets measured from laboratory investigation. Ten new data sets were used for the, validation and comparison of the air flow rate by ANN and multi-variate regression analysis (MVRA) to develop more confidence on the proposed method. Results were compared based on coefficient of determination (CoD) and mean absolute error (MAE) between measured and predicted values of air flow rate. It was found that CoD between measured and predicted air flow rate was 0. 995 and 0. 758 by ANN and MVRA, respectively, whereas MAE was 0. 0413 and 0. 1876. © 2011 Springer-Verlag London Limited.
Behaviour of brittle material in multiple loading rates under uniaxial compression
- Authors: Khandelwal, Manoj , Ranjith, Pathegama
- Date: 2013
- Type: Text , Journal article
- Relation: Geotechnical and Geological Engineering Vol. 31, no. 4 (2013), p. 1305-1315
- Full Text: false
- Reviewed:
- Description: It is of great importance to investigate the effect of loading rate on the behaviour of brittle material such as concrete and rock because engineering structures are subjected to multiple loading conditions. Although material behaviour under single loading mode has been extensively studied, very limited research has been conducted to investigate the performance of brittle materials subjected to varying loading conditions. This paper presents an experimental study of the effects of single and multiple strain rates (ε) on cement mortar samples. The first set of samples was loaded at constant strain rates until failure. For the remaining samples, the first strain rate (0.005 mm/s) was applied to the sample up to a predetermined load, and then the second strain was initiated immediately by using the specially-designed gear system in place in the compression rig. As expected, the increase in strain rate showed an increase in peak strength of the sample with reduced ultimate strain. For multiple strain modes, it was observed that the highest peak strength occurred when the second strain was applied at 50 % of the peak strength of the first strain. © 2013 Springer Science+Business Media Dordrecht.
Effect of strain rate on strength properties of low-calcium fly-ash-based geopolymer mortar under dry condition
- Authors: Khandelwal, Manoj , Ranjith, Pathegama , Pan, Zhu , Sanjayan, Jay
- Date: 2013
- Type: Text , Journal article
- Relation: Arabian Journal of Geosciences Vol. 6, no. 7 (2013), p. 2383-2389
- Full Text: false
- Reviewed:
- Description: This paper presents the mechanical and elastic properties of inorganic polymer mortar under varying strain rates. The study includes a determination of the compressive strength, modulus of elasticity and Poisson's ratio at 0.001, 0.005, 0.01 and 0.05 mm/s strain rate. A total of 21 cylindrical specimens having 100 mm length and 50 mm diameter were investigated, and all tests were carried out pursuant to the relevant Australian Standards. Although some variability between the mixes was observed, the results show that, in most cases, the engineering properties of geopolymer mortar compare favourably to those predicted by the relevant Australian Standards for concrete mixtures. It was found that the change in the strain rate causes different behaviour related to the percentage of the ultimate load. The ultimate strength, Young's modulus and Poisson's ratio of the geopolymer mortar depend on the strain rate. It was also found that as the strain rate increases, mechanical and elastic properties of geopolymer mortar substantially increase in logarithmic manner. © 2012 Saudi Society for Geosciences.
A new model based on gene expression programming to estimate air flow in a single rock joint
- Authors: Khandelwal, Manoj , Armaghani, Danial , Faradonbeh, Roohollah , Ranjith, Pathegama , Ghoraba, Saber
- Date: 2016
- Type: Text , Journal article
- Relation: Environmental Earth Sciences Vol. 75, no. 9 (2016), p.
- Full Text: false
- Reviewed:
- Description: This paper is aimed to introduce and validate a gene expression programming (GEP) model to estimate the rate of air flow in triaxial conditions at various confining pressures incorporating cell pressure, air inlet pressure and air outlet pressure. To achieve the aim of this study, a series of laboratory experiments were designed and carried out and then a database comprising 47 datasets was prepared to develop new predictive models. A gene expression programming (GEP) model for prediction of air flow was proposed using the prepared datasets. In this regard, a series of sensitivity analyses were performed to choose the best GEP model. For comparison purposes, multiple regression (MR) analysis was also employed for air flow estimation. Several performance indices, i.e., coefficient of determination (CoD), mean absolute error (MAE), root mean square error (RMSE) and variance account for (VAF) were considered and calculated to evaluate the performance prediction of the developed models. Considering both training and testing datasets, the developed GEP model can provide higher performance prediction of rate of air flow in comparison to the MR model. © 2016, Springer-Verlag Berlin Heidelberg.