The detailed monitoring of jointed plain concrete pavement (JPCP) slab condition is essential for cost-effective JPCP maintenance and rehabilitation. However, existing visual inspection practices for detailed slab condition classification are time-consuming and labor-intensive. In this paper, we proposed an automated JPCP slab condition classification model based on convolutional neural networks (ConvNets), which is the first to perform multi-label classification on the JPCP slab condition based on both crack types and severity levels. To handle the different scales between JPCP slab condition states, the model includes a novel global context block with atrous spatial pyramid pooling, denoted as a GC-ASPP block.The block can be flexibly applied to any ConvNets to effectively model the global context of images with the extraction of multiscale image features. The proposed model was evaluated using real-world 3D JPCP surface data. With the GC-ASPP block, our best model achieved an average precision of 85.42% on multi-label slab condition classification.
Accurate pavement performance forecasting is critical in supporting transportation agencies’ predictive maintenance strategies: programs that prolong pavement service life while using fewer resources. However, because of the complex nature of pavement deterioration, high accuracy for long-term and project-level pavement performance forecasting is challenging to traditional models. Therefore, researchers have taken advantage of machine learning (ML) technology to create more sophisticated models in recent years. However, there are no extant studies that compare different ML models on a singular, real-world, large-scale, and comprehensive pavement data set to evaluate their capability for pavement performance forecasting. Thus, the goal of this study is to critically evaluate ML models, such as multiple linear regression (MLR), fully connected neural network (FCNN), recurrent neural network (RNN), gated recurrent unit (GRU), long short-term memory (LSTM), and a hybrid LSTM-FCNN model, on Florida’s statewide, 31 year historical pavement data set. The results demonstrate that the RNN, GRU, LSTM, and LSTM-FCNN models perform significantly better than MLR and FCNN for predicting time-series pavement condition, with the LSTM-FCNN model performing the best. This result provides a valuable demonstration and recommendation to transportation agencies and researchers that RNN-based ML models are a promising direction to improve the accuracy of pavement performance forecasting.
An accurate pavement performance forecasting model is essential for transportation agencies to perform pavement maintenance, rehabilitation, and reconstruction (MR&R) in a predictive and cost-effective manner. Although some forecasting methods have been successful in forecasting short-term (e.g., 1–2 year) pavement conditions at either the project level or network level, accurately forecasting long-term (e.g., 3–5 year) pavement conditions at both project level and network level under real-world conditions is still challenging. Thus, the goal of this paper is to propose a two-stage machine learning approach based on long short-term memory (LSTM) to achieve not only the short-term, but also the long-term, forecasting accuracy at both the project level and network level. The proposed method involves LSTM in the first stage and an artificial neural network (ANN) in the second stage, resulting into a two-stage model. The LSTM first learns the pattern of pavement deterioration based on sequential data (e.g., historical pavement conditions). Then, the ANN further learns the impacts of roadway factors (e.g., traffic parameter, pavement surface type, working district) to adjust the final forecasting results. The accuracy of the proposed two-stage model has been compared with baseline machine learning methods in 2016 on a large, statewide Florida dataset at both the project level and network level to demonstrate the superior capability of the proposed method. In addition, the proposed method has been tested further to forecast future (5-year) pavement conditions (2016–2020). Results show a promising forecasting accuracy for both the short-term and long-term in comparison with the ground truth.
With the availability of pavement distress information with high granularity, there is a great opportunity to develop and apply new pavement performance indicators, including crack length, width, intersection point, and polygon, derived from crack fundamental elements (CFEs), to study pavement behavior and determine the optimal timing of treatments. Using CFEs and 3D high-resolution pavement surface data, we can study real-world crack deterioration behavior and correlate these new performance indicators to determine optimal maintenance and rehabilitation (M&R) method and timing (e.g., crack filling/sealing) to take full advantage of these 3D pavement surface data. This paper presents a proposed methodology to explore this opportunity. The proposed methodology consists of the following steps: (1) multiple-timestamp 3D pavement data registration, (2) new pavement performance indicators extraction from CFEs, (3) spatial–temporal analysis of new pavement performance indicators, and (4) optimal treatment and timing determination using the proposed spatial–temporal analysis of new pavement performance indicators (e.g., optimal crack filling/sealing timing and location). A case study using 6 years of 3D pavement surface data collected using 3D laser technology on SR-26 in Savannah, Georgia, was conducted to evaluate the feasibility of using the new pavement performance indicators generated by the proposed methodology. The outcomes demonstrate the proposed method is very promising for quantifying and planning M&R treatments (e.g., crack filling/sealing), which has previously been very difficult to achieve. Results also show that multiple-timestamp registration is a very crucial step in ensuring the consistent measurement of regions of interest for different years.
Crack sealing is one of the most commonly used methods to preserve asphalt pavements. However, quantification of crack sealing benefits (or the long-term delaying effects of crack sealing on crack propagation) remains unavailable because field crack lengths could not be measured accurately and efficiently. In this study, 3D laser technology is proposed to measure and compare the growth of crack lengths between sealed and non-sealed pavement sections and, for the first time, to accurately and efficiently quantify the crack sealing benefits. To validate the proposed method and find adequate treatment timing (or conditions), nine field sites in Georgia, U.S., with different pavement pre-treatment conditions and roadway environmental factors were monitored over 3 years from December 2016 to September 2019. The study results showed that crack sealing can retard crack growth by 40%–128%, and such delaying effects are more significant under better pavement pre-treatment conditions. The findings suggest that transportation agencies can prolong the service life of pavements by applying crack sealing before the pavement condition becomes poor. In addition, this work has been proved to be very valuable for transportation agencies to determine the best timing and treatment criteria for crack sealing.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.