Search

The dynamic modulus (|E*|) is one of the primary hot-mix asphalt (HMA) material property inputs at all three hierarchical levels in the new Mechanistic-empirical pavement design guide (MEPDG). The existing |E*| prediction models were developed mainly from regression analysis of an |E*| database obtained from laboratory testing over many years and, in general, lack the necessary accuracy for making reliable predictions. This paper describes the development of a simplified HMA |E*| prediction model employing artificial neural network (ANN) methodology. The intelligent |E*| prediction models were developed using the latest comprehensive |E*| database that is available to researchers (from National Cooperative Highway Research Program Report 547) containing 7400 data points from 346 HMA mixtures. The ANN model predictions were compared with the Hirsch |E*| prediction model, which has a logical structure and a relatively simple prediction model in terms of the number of input parameters needed with respect to the existing |E*| models. The ANN-based |E*| predictions showed significantly higher accuracy compared with the Hirsch model predictions. The sensitivity of input variables to the ANN model predictions were also examined and discussed. Le module dynamique (|E*|) est l’une des principales propriétés du mélange d’asphalte à chaud utilisée en entrée aux trois niveaux hiérarchiques dans le nouveau guide de conception mécanisto-empirique des chaussées (« Mechanistic-empirical pavement design guide »). Les modèles actuels de prédiction de |E*| sont principalement développés à l’aide d’analyses de régression de bases de données de |E*| obtenues à partir de tests en laboratoire sur de nombreuses années. Ils manquent en général de la précision nécessaire pour faire des prédictions fiables. Cet article décrit la mise au point d’un modèle de prédiction simplifié du |E*| du mélange d’asphalte à chaud qui emploie la méthodologie des réseaux de neurones artificiels (RNA). Les modèles de prédiction intelligents de |E*| ont été développés en utilisant la base de données complète de |E*| la plus récente (rapport no 547 du National Cooperative Highway Research Program) à la disposition des chercheurs et contenant 7400 exemples provenant de 346 mélanges d’asphalte à chaud. Les prédictions de |E*| à partir du modèle des RNA ont été comparées à celles du modèle de Hirsch, lequel a une structure logique et un modèle de prédiction relativement simple en termes du nombre de paramètres nécessaires en entrée comparativement aux autres modèles de prédiction de |E*| existants. Les prédictions de |E*| fondées sur le modèle des RNA ont montré une précision significativement plus élevée comparativement à celles du modèle de Hirsch. La sensibilité des variables d’entrée aux prédictions du modèle des RNA a aussi été examinée et discutée. [ABSTRACT FROM AUTHOR]

The support vector machine (SVM) is an emerging machine learning technique where prediction error and model complexity are simultaneously minimized. This paper examines the potential of SVM to predict the friction capacity of driven piles in clay. This SVM is firmly based on the statistical learning theory and uses the regression technique by introducing accuracy (ε) insensitive εloss function. The results are compared with those from a widely used artificial neural network (ANN) model. Overall, the SVM showed good performance and is proven to be better than ANN model. A sensitivity analysis has been also performed to investigate the importance of the input parameters. The study shows that SVM has the potential to be a useful and practical tool for prediction of friction capacity of driven piles in clay. [ABSTRACT FROM AUTHOR]

This paper describes the authors' recent research on the theories about internal workings of feed-forward artificial neural networks (ANNs). Knowledge of the inner workings of ANNs progresses with the evolution of ANN modelling techniques. In the early stages, neural networks consisted of perceptrons and were easy to interpret. Since the emergence of backpropagation learning in the 1980s, ANN models have become much more complex. Even today, many users still consider ANN models as black-box type models. In this paper, a systematic approach is demonstrated to study the behaviours of ANN models in an attempt to open up the ANN "black box". The authors emphasise that feed-forward ANN models are functions, and use a graphical interpretation technique to open the ANN models and show the detailed activities of each inner component through several case studies. These studies include how the training process changes the internal components of an ANN model, how noise impacts the training process, and how the sensitivity of ANN models is affected by the training data. [ABSTRACT FROM AUTHOR]

Although the artificial neural network (ANN) approach has been used in various disciplines of engineering since the 1980s, its use in the oil sands extraction industry is quite new and has great potential. This paper demonstrates two important ANN modelling techniques that will be very useful to the oil sand industry through a case study. First, the ANN pattern recognition approach is illustrated to categorize a large oil sand processing database consisting of experimental data from the last 20 years. Second, within each category, the authors demonstrate how to follow a general protocol to build ANN models that are capable of predicting the primary recovery and the primary froth quality for the oil sand treatment process with fairly good accuracy. To verify the reliability of the ANN models, besides the regular statistical and graphical analysis, the authors also conducted a sensitivity analysis to test the response logic, parameter interaction, and extrapolation capability of the ANN models. As shown in the paper, these tests are both satisfactory and interesting. With sufficient accuracy and robustness in performance, these ANN models can be used to evaluate both the qualitative and the quantitative response of the oil sand treatment process to the known key parameters, which, in turn, can then be used to optimize the oil sand treatment process. Furthermore, these ANN models can be linked with the geological survey results to estimate the production potential of an oil sand ore field and to manage the cost of stockpiling the chemicals for the treatment process. [ABSTRACT FROM AUTHOR]

Artificial neural network (ANN) technology has evolved from the experimental stage into actual industrial applications. To achieve this significant transition, careful planning and adjustment are required. This paper illustrates such an example in the water treatment industry. The project objective is to upgrade the ANN models from a previous research project and install the system on-line in the Rossdale Water Treatment Plant in Edmonton, Alberta, Canada, to forecast raw water colour one day ahead. The article discusses the important issues and techniques to upgrade the neural network model to the actual application. Furthermore, sufficient communication is also required between the designers and the users to address the applicability and user friendly issues in model implementation. Failure in communication can render the whole process ineffective. Possible improvements are also recommended for the future on-line applications. [ABSTRACT FROM AUTHOR]