Search

This research manuscript presents a comprehensive investigation into the prediction and detection of reflective cracking in pavement infrastructure through a combination of machine learning approaches and advanced image detection techniques. Leveraging machine learning algorithms, reflective cracking prediction models were developed and optimized for accuracy and efficiency. Additionally, the efficacy of image detection methods, particularly utilizing Mask R-CNN, was explored for robust and precise identification of reflective cracking on pavement surfaces. The study not only aims to enhance the predictive capabilities of pavement management systems (PMSs) through machine learning-based models but also seeks to integrate advanced image detection technologies to support real-time monitoring and assessment of pavement conditions. By providing accurate and timely detection of reflective cracking, these methodologies contribute to the optimization of pavement maintenance strategies and the overall improvement of pavement infrastructure management practices. Results indicate that the developed machine learning models achieve an average predictive accuracy of over 85%, with some models achieving accuracies exceeding 90%. Moreover, the utilization of a mask region-based convolutional neural network (Mask R-CNN) for image detection demonstrates exceptional precision, with a detection accuracy of over 95% on average across different pavement types and weather conditions. The results demonstrate the promising performance of the developed machine learning models in predicting reflective cracking, while the utilization of Mask R-CNN showcases exceptional accuracy in the detection of reflective cracking from images. This research underscores the importance of leveraging cutting-edge technologies to address challenges in pavement infrastructure management, ultimately supporting the sustainability and longevity of transportation networks.

Amid the growing demand for sustainable pavement solutions and the need to incorporate recycled materials into construction practices, this study explored the viability of using crushed thermal power plant bottom ash as a filler in polymer-modified asphalt concrete mixtures. Conventional lime filler was replaced with bottom ash at varying levels (0%, 25%, 50%, and 75%), and the resulting mixtures were evaluated using several performance tests. The optimal replacement level was determined to be 25%, based on the results of the indirect tensile strength (ITS) test. Comparisons between the control mixture and the 25% bottom ash-modified mixture were conducted using the dynamic modulus test, Cantabro test, Hamburg wheel tracking (HWT) test, and tensile strength ratio (TSR) test. The findings indicate that the 25% bottom ash-modified mixture demonstrated improved performance across multiple parameters. The HWT test showed enhanced rut durability, with a recorded depth of 7.56 mm compared to 8.9 mm for the control mixture. The Cantabro test results revealed lower weight loss percentages for the modified mixture, indicating better abrasion resistance. The dynamic modulus test indicated higher resilience and stiffness in both high- and low-frequency stages. The TSR test highlighted improved moisture resistance, with higher TSR values after 10 wet-drying cycles. These improvements are attributed to the fine particle size and beneficial chemical composition of bottom ash, which enhance the asphalt mixture’s density, binder-aggregate adhesion, and overall durability. The results suggest that incorporating 25% crushed bottom ash as a filler in polymer-modified asphalt concrete mixtures is a viable and sustainable approach to improving pavement performance and longevity.

This manuscript presents a comprehensive study on the sustainable optimization of asphalt mixtures tailored for regions prone to flooding. The research addresses the challenges associated with water damage to asphalt pavements by incorporating innovative additives. The study centers on incorporating recycled Low-Density Polyethylene (LDPE) and a tailored Carnauba–Soybean Oil Additive, advancing asphalt mixtures with a Control mix, LDPE (5%) + Control, and LDPE (5%) + 3% Oil + Control. A critical aspect of the research involves subjecting these mixtures to 30 wetting and drying cycles, simulating the conditions prevalent in tropical flood-prone areas. The incorporation of innovative additives in asphalt mixtures has demonstrated significant improvements across various performance parameters. Tensile Strength Ratio (TSR) tests revealed enhanced tensile strength, with the LDPE (5%) + 3% Oil-modified mixture exhibiting an impressive TSR of 85.7%. Dynamic Modulus tests highlighted improved rutting resistance, showcasing a remarkable increase to 214 MPa in the LDPE (5%) with a 3% Oil-modified mixture. The Semi-Circular Bending (SCB) test demonstrated increased fracture resistance and energy absorption, particularly in the LDPE (5%) with 3% Oil-modified mixture. Hamburg Wheel-Tracking (HWT) tests indicated enhanced moisture resistance and superior rutting resistance at 20,000 cycles for the same mixture. Cantabro tests underscored improved aggregate shatter resistance, with the LDPE (5%) + 3% Oil-modified mixture exhibiting the lowest weight loss rate at 9.820%. Field tests provided real-world insights, with the LDPE (5%) + 3% Oil mixture displaying superior stability, a 61% reduction in deflection, and a 256% improvement in surface modulus over the control mixture. This research lays the groundwork for advancing the development of sustainable, high-performance road pavement materials, marking a significant stride towards resilient infrastructure in flood-prone areas.

This study addresses the imperative for enhancing asphalt mixtures tailored for rural pavements, focusing on optimizing RAP mixtures with styrene–butadiene–styrene (SBS)-modified asphalt binders incorporating petroleum resin and oil. Through systematic investigation, the study examines the impact of varying RAP content (25% and 50%) and two SBS-modified asphalt binder types (Type 1 and Type 2) on mechanical properties and sustainability. Laboratory tests reveal that the mix of 25% RAP + 75% Type 1 exhibits exceptional flexibility, evidenced by a high ductility value of 880 mm at 25 °C, enhancing pavement resilience. Conversely, the 50% RAP + 50% Type 2 mixture displays vulnerability to fatigue cracking, while 25% RAP + 75% Type 1 demonstrates superior resistance, with a fatigue vulnerability value of 1524 kPa. The Hamburg Wheel Tracking test highlights the influence of RAP content on rut depth, with the mix of 50% RAP + 50% Type 1 achieving the lowest rutting at 3.9 mm. Overlay test results show the mix of 25% RAP + 75% Type 2’s resilience, with the lowest load reduction at 64.5%, while the mix of 50% RAP + 50% Type 1 exhibits substantial load reduction at 82.1%. Field tests unveil differences in pavement bearing capacities, with the mix of 25% RAP + 75% Type 2 demonstrating a remarkable elastic modulus of 58.5 MPa, indicating heightened bearing capacity. The investigation underscores the significant role of SBS-modified asphalt binders with incorporated petroleum resin and oil in enhancing fatigue resistance for sustainable rural pavements.

This research takes on a scientific problem originating from the pervasive deterioration observed in the pavements of Bus Rapid Transit (BRT) systems, which presents formidable challenges to their durability and imposes significant financial burdens on BRT organizations. While wear and tear on BRT pavements is a widely recognized concern, there exists a pronounced deficiency in sustainable solutions to address this issue comprehensively. This study endeavored to bridge this scientific gap by exploring the option of incorporating waste plastic aggregate (WPA) and recycled asphalt pavement (RAP) into the pavement material. The series of comprehensive investigations commenced with an assessment of modified binders. We identified a 25% extracted RAP binder as the most suitable candidate. Our research next determined that a 4% WPA content offers optimal results when used as an aggregate replacement in a stone-modified asphalt concrete mix, which is further refined with a 13 mm nominal maximum aggregate size (NMAS) gradation, resulting in superior performance. Under double-load conditions of the Hamburg Wheel Tracking test, rutting in the 10 mm NMAS mixture rapidly increased to 9 mm after 12,400 HWT cycles, while the 13 mm NMAS mixture showed a more gradual ascent to the same critical rutting level after 20,000 HWT cycles (a 61% increase). Real-world application at a designated BRT station area in Seoul reinforced the findings, revealing that the use of 13 mm NMAS with 4% WPA and RAP significantly improved performance, reducing rutting to 75 µm and enhancing pavement resilience. This configuration increased Road Bearing Capacity (RBC) to 5400 MPa at the center zone, showcasing superior load-bearing capability. Conversely, the 10 mm NMAS mixture without RAP and WPA experienced severe rutting (220 µm) and a 76% reduction in RBC to 1300 MPa, indicating diminished pavement durability. In general, this research highlights the need for innovative solutions to address BRT pavement maintenance challenges and offers a novel, environmentally friendly, and high-performance alternative to traditional methods.

In this study, the suitability of various Cement Asphalt Mortar (CAM) mixtures for bridge expansion joint applications in tropical climates was quantitatively assessed. A comprehensive analysis encompassed key properties, including mixing stability, flowability, unconfined compressive strength, expansion characteristics, and resistance to acidic and alkali environments. The influence of high-temperature exposure on unconfined compressive strength and the microstructural features were also examined. The results revealed a discernible trend: lower cement content, in conjunction with anionic Asphalt Emulsion (AE) or epoxy resin, significantly enhanced mixing stability and flowability while contributing to improved unconfined compressive strength and chemical degradation resistance. Notably, epoxy resin emerged as a valuable component in mitigating high-temperature-induced strength reduction, indicating potential promise for CAM mixture design. SEM analysis visually supported these findings by highlighting the microstructural distinctions among CAM mixtures. Quantitatively, the findings indicated that CAM mixtures with a 25% cement content and 75% anionic AE exhibited an 11% improvement in mixing stability, along with a 13% enhancement in flowability, relative to the control mixture with 100% cement. Additionally, CAM mixtures incorporating epoxy resin (at various percentages) with anionic AE exhibited a significant 15% resistance to high-temperature-induced UCS reduction, surpassing other mixtures. The SEM micrographs visually confirmed the superior microstructural connectivity achieved with epoxy resin, further validating the observed enhancements. These quantitative results offer a robust foundation for tailoring CAM mixture compositions to optimize their suitability for rigorous infrastructure projects in tropical climates.

The utilization of Recycled Asphalt Pavement (RAP) mixtures in pavement construction is an environmentally friendly approach that promotes sustainable development by reducing energy consumption and material waste. However, the high cost of conventional rejuvenators limits the widespread use of RAP mixtures. In this study, a novel approach is proposed to enhance the performance of RAP mixtures by incorporating a combination of high-penetration asphalt binder and rejuvenators, namely Castor wax and Corn oil. The newly developed rejuvenator consists of 8.5% Castor wax oil, 3% Corn oil, 3% fatty acid amine surfactant, 0.2% additive, and 79.8% water. The test results demonstrate that the modified mixture exhibits superior properties compared with conventional RAP mixtures. The Multiple Stress Creep Recovery test results showed a 20% reduction in cumulative strain rate for the RAP mixture with the new rejuvenators compared with that for the conventional ones. Furthermore, the Tensile Strength Ratio test indicated a notable 9.47% improvement in the rejuvenated RAP mixture’s resistance to moisture-induced damage compared with the conventional mixture. Evaluation of viscoelastic behaviors revealed a slight reduction in dynamic modulus for the rejuvenated binder, but a significant improvement in elastic behavior. In terms of rutting resistance, the Hamburg wheel tracking rut depths of the rejuvenated binder were significantly lower, representing reductions of 21.83% for specific binder compositions. Additionally, the absence of the stripping phenomenon further confirmed the superior moisture resistance of the modified mixture. The rejuvenated binder exhibited a remarkable 28.55% increase in fatigue load cycles to failure compared with the reference RAP binder, demonstrating substantial resistance to fatigue cracking. These quantitative comparisons not only confirm the superior performance of the modified mixture over conventional RAP mixtures, but also highlight the potential cost savings achieved through the utilization of Castor wax and Corn oil rejuvenators.

This study addresses the challenges of overlaying old concrete pavement with asphalt by introducing a new trackless tack coat material containing polymer. The aim is to enhance the durability of asphalt concrete overlay pavement on old cement concrete pavement. It contributes to the development of improved construction techniques for pavement rehabilitation and highlights the need for reliable adhesion performance evaluation based on different spray amounts and surface conditions. Additionally, to evaluate the effect of the adhesion performance based on the spraying amount, a tensile adhesion test was conducted by applying spray amounts of 0.30, 0.45, and 0.60 l/m2 on different surface conditions. The basic and adhesion performances of the polymer-modified tack coat material are evaluated through direct tensile and shear bond strength tests. The test outcomes demonstrated that the newly developed polymer-modified tack coat material had considerably greater adhesion strength compared to the traditional rapid-setting products. Its adhesive strength was 1.68 times higher on concrete and 1.78 times higher on asphalt. The new trackless tack coat material exhibited an adhesion performance of 1.05 MPa in direct tensile strength at 0.45 l/m2, which was 1.21 times higher than the rapid-setting tack coat. Results also confirmed that the new tack coat material exhibits values 1.90 times greater than the conventional rapid-setting tack coat material in shear bond strength, respectively. By simulating the process of separation and re-adhesion of pavement layers caused, the new tack coat material shows a tensile adhesion strength of 63% of the original state, which is advantageous for securing the durability of the pavement. Overall, the newly developed polymer-modified trackless tack coat has been shown to effectively enhance the adhesion performance between pavement layers without process delay, highlighting the potential of the new tack coat material to enhance the durability of asphalt concrete overlay pavement on old cement concrete pavement.

The reemergence of Deep Neural Networks (DNNs) has lead to high-performance supervised learning algorithms for the Electro-Optical (EO) domain classification and detection problems. This success is because generating huge labeled datasets has become possible using modern crowdsourcing labeling platforms such as Amazon’s Mechanical Turk that recruit ordinary people to label data. Unlike the EO domain, labeling the Synthetic Aperture Radar (SAR) domain data can be much more challenging, and for various reasons, using crowdsourcing platforms is not feasible for labeling the SAR domain data. As a result, training deep networks using supervised learning is more challenging in the SAR domain. In the paper, we present a new framework to train a deep neural network for classifying Synthetic Aperture Radar (SAR) images by eliminating the need for a huge labeled dataset. Our idea is based on transferring knowledge from a related EO domain problem, where labeled data are easy to obtain. We transfer knowledge from the EO domain through learning a shared invariant cross-domain embedding space that is also discriminative for classification. To this end, we train two deep encoders that are coupled through their last year to map data points from the EO and the SAR domains to the shared embedding space such that the distance between the distributions of the two domains is minimized in the latent embedding space. We use the Sliced Wasserstein Distance (SWD) to measure and minimize the distance between these two distributions and use a limited number of SAR label data points to match the distributions class-conditionally. As a result of this training procedure, a classifier trained from the embedding space to the label space using mostly the EO data would generalize well on the SAR domain. We provide a theoretical analysis to demonstrate why our approach is effective and validate our algorithm on the problem of ship classification in the SAR domain by comparing against several other competing learning approaches.