Deep machine learning approach to develop a new asphalt pavement condition index

Majidifard, Hamed; Adu-Gyamfi, Yaw; Buttlar, William G.

doi:10.1016/j.conbuildmat.2020.118513

Cited by 177 publications

(65 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Asphalt pavement is one of the most widely applied transportation methods for passengers due to its high evenness, comfort, and low noise [ 1 ]. With the high solar heat absorptivity of asphalt, this black pavement usually suffers an extraordinary increase in structural temperature on hot days [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Stone Mastic Asphalt Containing Ceramic Waste Aggregate for Cooling Asphalt Pavement

Huang

Qian

et al. 2020

Materials

View full text Add to dashboard Cite

Construction and demolition waste material is of great potential for use in pavement engineering. This paper aims to investigate the feasibility of ceramic waste aggregate (CA) used in cooling asphalt pavement through a series of test methods and simulation techniques. Stone mastic asphalt (SMA) containing 10%, 20%, 30%, 40%, and 50% coarse ceramic waste aggregate (CASMAs) was first designed using the Marshall method. Afterward, the road performance and thermal insulation performance of the five different CASMAs were assessed by a comprehensive lab test, including a wheel rutting test, moisture susceptibility test, bending beam test, fatigue beam test, and indoor thermal insulation test. Finally, a 2D finite-element (FE) model was developed to investigate the transient thermal field and rutting deformation response of the cooling asphalt pavement with CASMAs. Results show that CASMAs experienced degradation of rutting resistance, moisture susceptibility, and anti-cracking performance while still meeting technical requirements with CA content of up to 40%. On the other hand, CASMAs can cool the pavement’s temperature by 11.5 °C at the bottom of asphalt layers. The permanent rutting deformation of cooling asphalt pavement was 45.36% smaller than that of conventional asphalt pavement without CASMAs. Based on the test results and numerical simulation results, the optimum content of ceramic waste aggregate in stone mastic asphalt was recommended as 40%.

show abstract

Section: Introductionmentioning

confidence: 99%

Evaluation of Stone Mastic Asphalt Containing Ceramic Waste Aggregate for Cooling Asphalt Pavement

Huang

Qian

et al. 2020

Materials

View full text Add to dashboard Cite

show abstract

“…Tang et al (2019) presented a dynamic real-time detection method for surface deformation and full field strain in recycled aggregate concrete-filled steel tubular columns (RACSTCs). Majidifard et al (2020) developed a U-net based model to quantify the severity of the pavement distresses and a hybrid model by integrating the YOLO and U-net models to classify the pavement distresses and quantify their severity simultaneously. Liu et al (2019) adopted U-Net to detect the concrete cracks, and U-Net is found to be more elegant than DCNN with more robustness, more effectiveness, and more accurate detection.…”

Section: Introductionmentioning

confidence: 99%

Study on Quantitative Characterization of Morphological Characteristics and High Temperature Performance Evaluation of Coarse Aggregate Based on Computer Vision

2021

View full text Add to dashboard Cite

The morphological characteristics of aggregate include outline shape, angularity, and surface texture, which determine the mutual extrusion and friction between aggregates, and significantly affect the performance of asphalt pavement. At present, the research on the morphological characteristics of coarse aggregate is mainly focused on indoor visual identification technology (AIMS, XCT, etc.), in which the applicability of the proposed aggregate shape characterization index is weak, and these instruments could not serve the practical engineering well. In this article, the Coarse Aggregate Morphological Identification System (CAMIS) is developed based on computer vision technology, and the system can recognize the shape features of aggregates above 2.36 mm particle size and carry out uninterrupted feeding and removal based on the mechanical arm system, which can realize large sample detection. Based on CAMIS aggregate identification system and laboratory tests (rutting test, dynamic modulus test, and penetration shear test), the shape identification and performance test of aggregate samples from construction site are carried out, and an aggregate performance evaluation index, CEI, suitable for high-temperature areas is proposed in combination with the improved response surface method. The processing parameters of vertical shaft impact aggregate crusher are optimized based on the CEI index, and the recommended processing parameters are verified by laboratory tests. The results show that the morphological characteristics of coarse aggregate affect the high temperature performance in order angularity, needle flake, axial coefficient, and convexity. The combination of processing parameters of vertical axis impact crusher is recommended to be of 45 m/s rotational speed, 3 t/h feed quantity, and 30% air intake. Verified by laboratory tests, the aggregate identification system CAMIS developed in this article and the proposed aggregate performance evaluation index, CEI, are highly reliable.

show abstract

“…Initially, each pavement is assigned with a score of 100. Then, the score subtracted based on the type, severity, and extent of distresses [11,12]. In fact, IRI represents the pavement roughness, and PCI is the representative of pavement distresses.…”

Section: Introductionmentioning

confidence: 99%

Smart Structural Health Monitoring of Flexible Pavements Using Machine Learning Methods

et al. 2020

View full text Add to dashboard Cite

The pavement is a complex structure that is influenced by various environmental and loading conditions. The regular assessment of pavement performance is essential for road network maintenance. International roughness index (IRI) and pavement condition index (PCI) are well-known indices used for smoothness and surface condition assessment, respectively. Machine learning techniques have recently made significant advancements in pavement engineering. This paper presents a novel roughness-distress study using random forest (RF). After determining the PCI and IRI values for the sample units, the PCI prediction process is advanced using RF and random forest trained with a genetic algorithm (RF-GA). The models are validated using correlation coefficient (CC), scatter index (SI), and Willmott’s index of agreement (WI) criteria. For the RF method, the values of the three parameters mentioned were −0.177, 0.296, and 0.281, respectively, whereas in the RF-GA method, −0.031, 0.238, and 0.297 values were obtained for these parameters. This paper aims to fulfill the literature’s identified gaps and help pavement engineers overcome the challenges with the conventional pavement maintenance systems.

show abstract

Deep machine learning approach to develop a new asphalt pavement condition index

Cited by 177 publications

References 50 publications

Evaluation of Stone Mastic Asphalt Containing Ceramic Waste Aggregate for Cooling Asphalt Pavement

Evaluation of Stone Mastic Asphalt Containing Ceramic Waste Aggregate for Cooling Asphalt Pavement

Study on Quantitative Characterization of Morphological Characteristics and High Temperature Performance Evaluation of Coarse Aggregate Based on Computer Vision

Smart Structural Health Monitoring of Flexible Pavements Using Machine Learning Methods

Contact Info

Product

Resources

About