Particle size and morphological/shape properties ensure the reliable and sustainable use of all aggregate skeleton materials placed as constructed layers in transportation applications. The composition and packing of these aggregate assemblies rely heavily on particle size and morphological properties, which affect layer strength, modulus, and deformation response under vehicular loading and therefore facilitate the quality assurance/quality control (QA/QC) process. Aggregate imaging systems developed to date for size and shape characterization, however, have primarily focused on measurement of separated or slightly contacting aggregate particles. Development of efficient computer vision algorithms is urgently needed for image-based evaluations of densely stacked (or stockpile) aggregates, which requires image segmentation of a stockpile for the size and morphological properties of individual particles. This paper presents an innovative approach for automated segmentation and morphological analyses of stockpile aggregate images based on deep learning techniques. A task-specific stockpile aggregate image dataset is established from images collected from various quarries in Illinois. Individual particles from the stockpile images are manually labeled on each image associated with particle locations and regions. A state-of-the-art object detection and segmentation framework called Mask R-CNN is then used to train the image segmentation kernel, which enables user-independent segmentation of stockpile aggregate images. The segmentation results show good agreement with ground-truth labeling and improve the efficiency of size and morphological analyses conducted on densely stacked and overlapping particle images. Based on the presented approach, stockpile aggregate image analysis promises to become an efficient and innovative application for field-scale and in-place evaluations of aggregate materials.

To achieve increased rail network safety and reliability, it is important to better understand ballast layer performance under complex and demanding dynamic loading field scenarios, especially for high speed lines on ballasted track. Repeated high-speed loading tests were recently conducted at three train speeds on a full-scale ballasted track-subgrade system, known as the Zhejiang University innovative high-speed rail tester (ZJU-iHSRT). BLOKS3D, a polyhedral discrete element method (DEM) particle simulation code with newly featured parallel computing capability, was used to capture the full-scale ballasted track dynamic responses at those speeds. A proportional–integral–derivative controller was also implemented in the DEM code to ensure identical dynamic loadings were applied in the DEM model as in the physical model. This paper presents the dynamic response findings obtained using the DEM model: 1) Crosstie vibration velocities captured in the DEM model match closely with the measurement obtained from the same crosstie in the physical model; 2) ballast particle vibration velocities recorded in the DEM model provide an overall good match with the data measured from the same location in the physical model; and finally, 3) visualized macroscopic ballast layer dynamic responses reveal the mechanical behavior of the ballast layer under dynamic loading scenarios applied in the ZJU-iHSRT full-scale ballasted track-subgrade system.

Railway ballast degrades progressively as a result of accumulated traffic primarily through abrasion and particle breakage. Degraded ballast may cause reduced lateral and longitudinal stability, ineffective drainage, and excessive settlement of track structures, all of which would adversely affect the performance of ballasted track. Traditional methods of ballast degradation assessment involve time-consuming field sampling and laboratory sieve analysis; moreover, determining the level of track performance deterioration at which ballast maintenance is best considered still remains challenging. This paper investigates the permeability of railway ballast through laboratory testing and provides insight into its field drainage capacity under degraded condition using an innovative approach of field imaging. Constant head permeability tests were conducted on clean and degraded ballast samples which indicated nonlinear power-curve trends, especially for clean ballast, of unit flow amount with its hydraulic gradient. Imaging-based degradation analysis using machine vision technology was also performed on clean and degraded in-service ballast to correlate Fouling Index (FI) from laboratory sieving with Percent Degraded Segments (PDS) obtained from the recently developed image segmentation algorithm. Accordingly, a new Permeability Index (PI) is introduced in this paper to define ballast permeability in the form of a bilinear model developed from the machine vision–based ballast degradation analysis. Based on the findings of this study, a two-stage ballast cleaning process for determining the timeframe of ballasted track maintenance considering its drainage capacity is proposed.

No abstract

Riprap rock and large-sized aggregates have been used extensively in geotechnical and hydraulic engineering. They essentially provide erosion control, sediment control, and scour protection. The sustainable and reliable use of riprap materials demands efficient and accurate evaluation of their large particle sizes, shapes, and gradation information at both quarry production lines and construction sites. Traditional methods for assessing riprap geometric properties involve subjective visual inspection and time-consuming hand measurements. As such, achieving the comprehensive in-situ characterization of riprap materials still remains challenging for practitioners and engineers. This paper presents an innovative approach for characterizing the volumetric properties of riprap by establishing a field imaging system associated with newly developed color image segmentation and three-dimensional (3-D) reconstruction algorithms. The field imaging system described in this paper with its algorithms and field application examples is designed to be portable, deployable, and affordable for efficient image acquisition. The robustness and accuracy of the image segmentation and 3-D reconstruction algorithms are validated against ground truth measurements collected in stone quarry sites and compared with state-of-the-practice inspection methods. The imaging-based results show good agreement with the ground truth and provide improved volumetric estimation when compared with currently adopted inspection methods. Based on the findings of this study, the innovative imaging-based system is envisioned for full development to provide convenient, reliable, and sustainable solutions for the onsite Quality Assurance/Quality Control tasks relating to riprap rock and large-sized aggregates.