Influence of surface distresses on smartphone-based pavement roughness evaluation

Janani, L.; Sunitha, V.; Mathew, Samson

doi:10.1080/10298436.2020.1714045

Cited by 37 publications

(10 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Great leaps in the advancement of transportation systems have made it possible for greater distances to be covered in a unit of time, resulting from efficient and safe riding pavement surfaces [ 29 ]. Pavement design and construction are generally carried out to keep the underlying layers unsaturated.…”

Section: Methodsmentioning

confidence: 99%

Pavement Quality Index Rating Strategy Using Fracture Energy Analysis for Implementing Smart Road Infrastructure

Abejide

Hassan

Das

et al. 2021

Sensors

View full text Add to dashboard Cite

Developing a responsive pavement-management infrastructure system is of paramount importance, accentuated by the quest for sustainability through adoption of the Road Traffic Management System. Technological advances have been witnessed in developed countries concerning the development of smart, sustainable transportation infrastructure. However, the same cannot be said of developing countries. In this study, the development of a pavement management system at network level was examined to contribute towards a framework for evaluating a Pavement Quality Index and service life capacity. Environmental surface response models in the form of temperature and moisture variations within the pavement were applied, using sensor devices connected to a data cloud system to carry out mathematical analysis using a distinctive mesh analysis deformation model. The results indicated variation in the Resilient Modulus of the pavement, with increasing moisture content. Increase in moisture propagation increased saturation of the unbound granular base which reduced the elastic modulus of the sub-base and base layer and reduced the strength of the pavement, resulting in bottom-up cracks and cracking failure. The horizontal deformation reduced, indicating that the material was experiencing work hardening and further stress would not result in significant damage. Increasing temperature gradient resulted in reduced stiffness of the asphalt layer. In tropical regions, this can result in rutting failure which, over time, results in top-down cracks and potholes, coupled with increasing moisture content.

show abstract

Section: Methodsmentioning

confidence: 99%

Pavement Quality Index Rating Strategy Using Fracture Energy Analysis for Implementing Smart Road Infrastructure

Abejide

Hassan

Das

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…To summarize this literature review, road surface distress detection using accelerometers is a technique that needs to be further studied and improved [ 34 ]. It is indeed necessary to offer to RAs a reliable and low-cost process able to screen the entire road network in a short time and to detect and classify the different distresses on the road surface in terms of severity and type.…”

Section: Related Workmentioning

confidence: 99%

Road Surface Anomaly Assessment Using Low-Cost Accelerometers: A Machine Learning Approach

Martinelli¹,

Meocci

Dolfi

et al. 2022

Sensors

View full text Add to dashboard Cite

Roads are a strategic asset of a country and are of great importance for the movement of passengers and goods. Increasing traffic volume and load, together with the aging of roads, creates various types of anomalies on the road surface. This work proposes a low-cost system for real-time screening of road pavement conditions. Acceleration signals provided by on-car sensors are processed in the time–frequency domain in order to extract information about the condition of the road surface. More specifically, a short-time Fourier transform is used, and significant features, such as the coefficient of variation and the entropy computed over the energy of segments of the signal, are exploited to distinguish between well-localized pavement distresses caused by potholes and manhole covers and spread distress due to fatigue cracking and rutting. The extracted features are fed to supervised machine learning classifiers in order to distinguish the pavement distresses. System performance is assessed using real data, collected by sensors located on the car’s dashboard and floorboard and manually labeled. The experimental results show that the proposed system is effective at detecting the presence and the type of distress with high classification rates.

show abstract

“…In the MLP model, tested were multiple architectures with different sizes of layers and units. The best performance was obtained using the network with 3 hidden layers (2,4,6), adaptive learning rate which starts at 0.01 and L2 penalty set at 1.…”

Section: Regressionmentioning

confidence: 99%

“…In order to support decision-makers in optimizing repair and maintenance efforts several road condition indicators have been developed [3]. In this regard, the road roughness is considered most important, as it does not only affect the pavement's ride quality, but also energy consumption, vehicle delays and maintenance costs [4]. The International Roughness Index (IRI) is the most common index applied worldwide for characterizing longitudinal road roughness and managing road systems.…”

Section: Introductionmentioning

confidence: 99%

Road Roughness Estimation Using Machine Learning

Bajic,

Pour,

Skar

et al. 2021

Preprint

View full text Add to dashboard Cite

Road roughness is a very important road condition for the infrastructure, as the roughness affects both the safety and ride comfort of passengers. The roads deteriorate over time which means the road roughness must be continuously monitored in order to have an accurate understand of the condition of the road infrastructure. In this paper, we propose a machine learning pipeline for road roughness prediction using the vertical acceleration of the car and the car speed. We compared well-known supervised machine learning models such as linear regression, naive Bayes, k-nearest neighbor, random forest, support vector machine, and the multi-layer perceptron neural network. The models are trained on an optimally selected set of features computed in the temporal and statistical domain. The results demonstrate that machine learning methods can accurately predict road roughness, using the recordings of the cost approachable in-vehicle sensors installed in conventional passenger cars. Our findings demonstrate that the technology is well suited to meet future pavement condition monitoring, by enabling continuous monitoring of a wide road network.

show abstract

Influence of surface distresses on smartphone-based pavement roughness evaluation

Cited by 37 publications

References 30 publications

Pavement Quality Index Rating Strategy Using Fracture Energy Analysis for Implementing Smart Road Infrastructure

Pavement Quality Index Rating Strategy Using Fracture Energy Analysis for Implementing Smart Road Infrastructure

Road Surface Anomaly Assessment Using Low-Cost Accelerometers: A Machine Learning Approach

Road Roughness Estimation Using Machine Learning

Contact Info

Product

Resources

About