Neural Network for Rapid Depth Evaluation of Shallow Cracks in Asphalt Pavements

Abstract

Rapid and nondestructive evaluation of pavement crack depths is a major challenge in pavement maintenance and rehabilitation. This article presents a computer-based methodology with which one can estimate the actual depths of shallow, surface-initiated fatigue cracks in asphalt pavements based on rapid measurement of their surface characteristics. It is shown that the complex overall relationship among crack depths, surface geometrical properties of cracks, pavement properties, and traffic characteristics can be learnt effectively by a neural network (NN). The learning task is facilitated by a database that includes relevant traffic and pavement characteristics of Florida's state highway network. In addition, the specific data used for the NN model development also contained laser-scanned microscopic surface geometrical properties of cracks in 95 pavement sections and pavement core samples scattered within five counties of Florida. Relatively advanced training algorithms were investigated in addition to the Standard Backpropagation algorithm to determine the optimal NN architecture. In terms of optimizing the NN training process, the "early stopping method" was found to be effective. The crack depth evaluation model was validated based on an unused portion of the database and fresh core samples. The results indicate the promise of NN usage in

Prediction of IRI in short and long terms for flexible pavements: ANN and GMDH methods

“…Fwa and Chen 1993, Attoh-Okine 1994, 2001, Eldin and Senouci 1995, Huang and Moore 1997, Alsugair and Al-Qudrah 1998, Owusu-Ababio 1998, Shekharan 2000, Sundin and Braban-Ledoux 2001, Bayrak et al 2004, Choi et al 2004, Mei et al 2004, Loizos and Karlaftis 2006, Terzi 2007 have been used to predict pavement condition. The ANN helps to illustrate effect of each individual variable on pavement condition and effect of interactions between the variables.…”

Prediction of Marshall test results for polypropylene modified dense bituminous mixtures using neural networks

“…Lee and Lee (2004) presents an integrated neural network-based crack imaging system to classify crack types of digital pavement images which includes three types of neural networks: image-based neural network, histogram-based neural network and proximity-based neural network. In an article by Mei, Gunaratne, Lu, and Dietrich (2004), it is presented a computer-based methodology with which one can estimate the actual depths of shallow, surface-initiated fatigue cracks in asphalt pavements based on rapid measurement of their surface characteristics. Ceylan, Guclu, Tutumluer, and Thompson (2005) has investigated the use of artificial neural networks as pavement structural analysis tools for the rapid and accurate prediction of critical responses and deflection profiles of full-depth flexible pavements subjected to typical highway loadings.…”

Polypropylene fiber-reinforced bitumen

“…Marshall Quotient values, which are in fact of 'pseudo-stiffness', are also related to stability and flow values, therefore their prediction is also very important. Detailed knowledge about the applications of artificial neural networks in transportation and pavement engineering can be found in the relevant literature (Tapkın 2004;ritchie et al 1991;kaseko and ritchie 1993;Gagarin et al 1994;Eldin and Senouci 1995;cal 1995;razaqpur et al 1996;roberts and attoh-Okine 1998;Owusu-ababia 1998;alsugair and al-Qudrah 1998;kim and kim 1998;Shekharan 1998;attoh-Okine 2001attoh-Okine , 2005Lee and Lee 2004;Mei et al 2004;Bosurgi and Trifiro 2005;zeghal 2008;Xue et al 2009;Alavi et al 2011;Mirzahosseini et al 2011). Throughout this part of the study, artificial neural networks were utilised in order to predict the stability, flow and Marshall Quotient values of asphalt concrete specimens obtained from a series of Marshall designs, based on experimental results described above.…”