Detection and Monitoring of Bottom-Up Cracks in Road Pavement Using a Machine-Learning Approach

The current methods that aim at monitoring the structural health status (SHS) of road pavements allow detecting surface defects and failures. This notwithstanding, there is a lack of methods and systems that are able to identify concealed cracks (particularly, bottom-up cracks) and monitor their growth over time. For this reason, the objective of this study is to set up a supervised machine learning (ML)-based method for the identification and classification of the SHS of a differently cracked road pavement based on its vibro-acoustic signature. The method aims at collecting these signatures (using acoustic-sensors, located at the roadside) and classifying the pavement’s SHS through ML models. Different ML classifiers (i.e., multilayer perceptron, MLP, convolutional neural network, CNN, random forest classifier, RFC, and support vector classifier, SVC) were used and compared. Results show the possibility of associating with great accuracy (i.e., MLP = 91.8%, CNN = 95.6%, RFC = 91.0%, and SVC = 99.1%) a specific vibro-acoustic signature to a differently cracked road pavement. These results are encouraging and represent the bases for the application of the proposed method in real contexts, such as monitoring roads and bridges using wireless sensor networks, which is the target of future studies.

[1]  Filippo Giammaria Praticò,et al.  Potential of fire extinguisher powder as a filler in bituminous mixes. , 2010, Journal of hazardous materials.

[2]  Filippo Giammaria Praticò,et al.  The Prediction of Road Cracks through Acoustic Signature: Extended Finite Element Modeling and Experiments , 2019 .

[3]  Eduardo Zalama Casanova,et al.  Road Crack Detection Using Visual Features Extracted by Gabor Filters , 2014, Comput. Aided Civ. Infrastructure Eng..

[4]  Filippo Giammaria Praticò,et al.  On the dependence of acoustic performance on pavement characteristics , 2014 .

[5]  Mădălin-Dorin Pop,et al.  A Comparison Between Smart City Approaches in Road Traffic Management , 2018 .

[6]  Fabrizio D'Amico,et al.  An overview of ground-penetrating radar signal processing techniques for road inspections , 2017, Signal Process..

[7]  Anil K. Jain,et al.  Artificial Neural Networks: A Tutorial , 1996, Computer.

[8]  Mohamed Rehan Karim,et al.  A review on fatigue and rutting performance of asphalt mixes , 2011 .

[9]  Clara Celauro,et al.  Asphalt mixtures modified with basalt fibres for surface courses , 2018 .

[10]  Yashon O. Ouma,et al.  Pothole detection on asphalt pavements from 2D-colour pothole images using fuzzy c-means clustering and morphological reconstruction , 2017 .

[11]  Daniel Sun,et al.  Analyzing Spatiotemporal Congestion Pattern on Urban Roads Based on Taxi GPS Data , 2017, Logic-Driven Traffic Big Data Analytics.

[12]  Dong-Soo Kim,et al.  Propagation and Attenuation Characteristics of Various Ground Vibrations , 2000 .

[13]  P. A. Morgan,et al.  A novel approach to the acoustic characterisation of porous road surfaces , 2003 .

[14]  Leslie London,et al.  Undereporting of acute pesticide poisoning in Tanzania: modelling results from two cross-sectional studies , 2016, Environmental Health.

[15]  Ming L. Wang,et al.  Estimation of Pavement Macrotexture by Principal Component Analysis of Acoustic Measurements , 2014 .

[16]  Filippo Giammaria Praticò,et al.  A study on the relationship between mean texture depth and mean profile depth of asphalt pavements , 2015 .

[17]  Geert Lombaert,et al.  The effect of road unevenness on the dynamic vehicle response and ground-borne vibrations due to road traffic , 2011 .

[18]  Hugo Jair Escalante,et al.  Evaluation of Detection Approaches for Road Anomalies Based on Accelerometer Readings—Addressing Who’s Who , 2018, IEEE Transactions on Intelligent Transportation Systems.

[19]  Filippo Giammaria Praticò,et al.  Factors Affecting Variance and Bias of Non-nuclear Density Gauges for Porous European Mixes and Dense -Graded Friction Courses , 2009 .

[20]  Hae-Bum Yun,et al.  Comparison of Supervised Classification Techniques for Vision-Based Pavement Crack Detection , 2016 .

[21]  D. Sun,et al.  Analyzing spatiotemporal traffic line source emissions based on massive didi online car-hailing service data , 2018, Transportation Research Part D: Transport and Environment.

[22]  Yashon O. Ouma,et al.  Wavelet-morphology based detection of incipient linear cracks in asphalt pavements from RGB camera imagery and classification using circular Radon transform , 2016, Adv. Eng. Informatics.

[23]  Jie Gao,et al.  Recognition, location, measurement, and 3D reconstruction of concealed cracks using convolutional neural networks , 2017 .

[24]  Filippo Giammaria Praticò,et al.  Energy savings in transportation: Setting up an innovative SHM method , 2018 .

[25]  Roberto Spinola Barbosa,et al.  Vehicle dynamic response due to pavement roughness , 2011 .

[26]  Fereidoon Moghadas Nejad,et al.  An expert system based on wavelet transform and radon neural network for pavement distress classification , 2011, Expert Syst. Appl..

[27]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[28]  Gaetano Licitra,et al.  A modified Close Proximity method to evaluate the time trends of road pavements acoustical performances , 2014 .

[29]  Massimo Merenda,et al.  Energy harvesting for IoT road monitoring systems , 2018 .

[30]  James Bryce,et al.  Wavelet Denoising of TSD Deflection Slope Measurements for Improved Pavement Structural Evaluation , 2014, Comput. Aided Civ. Infrastructure Eng..

[31]  E. D. de León Izeppi,et al.  Pavement macro-texture analysis using wavelets , 2013 .

[32]  Minh-Ngoc Vu,et al.  Extended analytical solutions for effective elastic moduli of cracked porous media , 2017 .

[33]  Nigel Waters,et al.  Review of remote sensing methodologies for pavement management and assessment , 2015 .

[34]  T. Sadowski,et al.  Sensitivity analysis of crack propagation in pavement bituminous layered structures using a hybrid system integrating Artificial Neural Networks and Finite Element Method , 2014 .

[35]  Amir Hossein Alavi,et al.  New machine learning-based prediction models for fracture energy of asphalt mixtures , 2019, Measurement.

[36]  Riccardo Carotenuto,et al.  A Real-Time Decision Platform for the Management of Structures and Infrastructures , 2019, Electronics.