Application of signal processing and support vector machine to transverse cracking detection in asphalt pavement

Abstract

Vibration-based pavement condition (roughness and obvious anomalies) monitoring has been expanding in road engineering. However, the indistinctive transverse cracking has hardly been considered. Therefore, a vehicle-based novel method is proposed for detecting the transverse cracking through signal processing techniques and support vector machine (SVM). The vibration signals of the car traveling on the transverse-cracked and the crack-free sections were subjected to signal processing in time domain, frequency domain and wavelet domain, aiming to find indices that can discriminate vibration signal between the cracked and uncracked section. These indices were used to form 8 SVM models. The model with the highest accuracy and F1-measure was preferred, consisting of features including vehicle speed, range, relative standard deviation, maximum Fourier coefficient, and wavelet coefficient. Therefore, a crack and crack-free classifier was developed. Then its feasibility was investigated by 2292 pavement sections. The detection accuracy and F1-measure are 97.25% and 85.25%, respectively. The cracking detection approach proposed in this paper and the smartphone-based detection method for IRI and other distress may form a comprehensive pavement condition survey system.

Keywords

asphalt pavement / transverse crack detection / vehicle vibration / support vector machine / classification model

References

[1] YangQ, DengY-J. Evaluation of cracking in asphalt pavement with stabilized base course based on statistical pattern recognition [J]. International Journal of Pavement Engineering, 2019, 20(4): 417-424 LinkOut]

[2] Nhat-DucH, NguyenQ L, TranV D. Automatic recognition of asphalt pavement cracks using metaheuristic optimized edge detection algorithms and convolution neural network [J]. Automation in Construction, 2018, 94: 203-213 LinkOut]

[3] MeiQ-P, GülM. A cost effective solution for pavement crack inspection using cameras and deep neural networks [J]. Construction and Building Materials, 2020, 256: 119397

[4] InkoomS, SobanjoJ, BarbuA, NiuX-F. Pavement crack rating using machine learning frameworks: Partitioning, bootstrap forest, boosted trees, naïve Bayes, and K-nearest neighbors [J]. Journal of Transportation Engineering, Part B: Pavements, 2019, 145(3): 04019031

[5] DuY-C, LiuC-L, WuD-F, LiS-Y. Application of vehicle mounted accelerometers to measure pavement roughness [J]. International Journal of Distributed Sensor Networks, 2016, 1268413146

[6] SinghG, BansalD, SofatS, AggarwalN. Smart patrolling: An efficient road surface monitoring using smartphone sensors and crowdsourcing [J]. Pervasive and Mobile Computing, 2017, 4071-88

[7] YuB X, YuX B. Vibration-based system for pavement condition evaluation [C]. Ninth International Conference on Applications of Advanced Technology in Transportation (AATT), 2006, Reston, VA, USA, American Society of Civil Engineers, 183-189

[8] ErikssonJ, GirodL, HullB, NewtonR, MaddenS, BalakrishnanH. The pothole patrol: Using a mobile sensor network for road surface monitoring [C]. Proceeding of the 6th International Conference on Mobile systems, Applications, and Services-MobiSys’ 08, 2008, Breckenridge, CO, USA. New York, ACM Press

[9] PerttunenM, MazhelisO, CongF-Y, KauppilaM, LeppanenT, KantolaJ, CollinJ, PirttikangasS, HaverinenJ, RistaniemiT, RiekkiJ. Distributed road surface condition monitoring using mobile phones [C]. 8th International Conference on Ubiquitous Intelligence and Computing, 2011, UIC Banff, AB, Canada, Springer Verlag

[10] SattarS, LiS, ChapmanM. Road surface monitoring using smartphone sensors: A review [J]. Sensors (Basel, Switzerland), 2018, 18(11): E3845

[11] ButtlatW G, AlaviA, BrownH, SillsH, MesaA, OkenfussE. Pavement roughness measurement using android smartphones: Case study of Missouri roads and airports [R]. Rep. CMR18-010, 2018, Jefferson City, MO, Missouri DOT

[12] HarikrishnanP M, GopiV P. Vehicle vibration signal processing for road surface monitoring [J]. IEEE Sensors Journal, 2017, 17165192-5197

[13] WANG Hsiu-wen, CHEN Chi-hua, CHENG Ding-yuan, LIN Chun-hao, LO Chi-chun. A real-time pothole detection approach for intelligent transportation system [J]. Mathematical Problems in Engineering, 2015: 869627. DOI: https://doi.org/10.1155/2015/869627.

[14] MelhemH, KimH. Damage detection in concrete by Fourier and wavelet analyses [J]. Journal of Engineering Mechanics, 2003, 129(5): 571-577

[15] PawarP M, Venkatesulu ReddyK, GanguliR. Damage detection in beams using spatial Fourier analysis and neural networks [J]. Journal of Intelligent Material Systems and Structures, 2007, 18(4): 347-359

[16] GUO Hua-ping, DIAO Xiao-yu, LIU Hong-bing. Embedding undersampling rotation forest for imbalanced problem [J]. Computational Intelligence and Neuroscience, 2018: 1–15. DOI: https://doi.org/10.1155/2018/6798042.

[17] ChenB-Q, CuiJ-G, XuQ, ShuT, LiuH-L. Coupling denoising algorithm based on discrete wavelet transform and modified median filter for medical image [J]. Journal of Central South University, 2019, 26(1): 120-131

[18] GhanizadehA R, FakhriM. Quasi-static analysis of flexible pavements based on predicted frequencies using fast fourier transform and artificial neural network [J]. International Journal of Pavement Research and Technology, 2018, 11(1): 47-57

[19] AddisonP SThe illustrated wavelet transform handbook: introductory theory and applications in science, engineering, medicine and finance [M], 2002, Edinburgh, UK, Institute of Physics Publishing

[20] YingY-J, GarrettJ HJr, OppenheimI J, SoibelmanL, HarleyJ B, ShiJ, JinY-W. Toward data-driven structural health monitoring: Application of machine learning and signal processing to damage detection [J]. Journal of Computing in Civil Engineering, 2013, 27(6): 667-680

[21] LiZ-M, GuiW-H, ZhuJ-Y. Fault detection in flotation processes based on deep learning and support vector machine [J]. Journal of Central South University, 2019, 26(9): 2504-2515

[22] KarthikeyanR, AlliP. Feature selection and parameters optimization of support vector machines based on hybrid glowworm swarm optimization for classification of diabetic retinopathy [J]. Journal of Medical Systems, 2018, 42(10): 1-11

[23] ZhangY-Y, LiR. Selection of the parameter in Gaussian kernels in support vector machine [C]. 2017 IEEE 2nd International Conference on Cloud Computing and Big Data Analysis (ICCCBDA), 2017, Chengdu, China, IEEE, 430433

[24] ElbisyM S. Support vector machine and regression analysis to predict the field hydraulic conductivity of sandy soil [J]. KSCE Journal of Civil Engineering, 2015, 19(7): 2307-2316