Establishment of Prediction Models of Asphalt Pavement Performance based on a Novel Data Calibration Method and Neural Network

Abstract

This paper aims to develop models to forecast the deterioration of pavement conditions including rutting, roughness, skidresistance, transverse cracking, and pavement surface distress. A data quality control method was proposed to rebuild the performance data based on the idea of longest increasing or decreasing subsequences. Neural network (NN) was used to develop the five models, and principal component analysis (PCA) was applied to reduce the dimension of traffic variables. The influence of different input variables on the model outputs was discussed respectively by comparing their mean impact values (MIV). Results show that the proposed NN models demonstrated great potential for accurate prediction of pavement conditions, with an average testing R-square of 0.8692. The results of sensitivity analysis revealed that recent pavement conditions may influence the future pavement conditions significantly. Rutting and roughness were sensitive to pavement age and maintenance type. The materials of original pavement asphalt layer were highly relevant to the prediction of pavement roughness, skid-resistance, and pavement surface distress. Moreover, traffic loads obviously affected the pavement skid-resistance and transverse cracking. Pavement and bridge had different effect on surface distress. The material of the base has a remarkable impact on the initiation and development of transverse cracks. Disease treatment in terms of pavement cracking-such as sticking the cracks, excavating and filling the cracks-shows a high MIV in the prediction model of transverse cracking and pavement surface distress.

A weighted multi-output neural network model for the prediction of rigid pavement deterioration

“…Incorporating all parameters in regression models, on one hand could increase the model complexity and lead to overfitting, on the other hand it prevents us from understanding the role of each parameter. Several studies have conducted sensitivity analysis to explore the significance of input variables (Choi et al 2004, Kargah-Ostadi et al 2010, Karlaftis and Badr 2015, Hossain et al 2019, Yao et al 2019.…”

“…In recent years, feed-forward neural network (NN) models have been widely applied for pavement deterioration prediction due to their superior performance when dealing with strongly nonlinear relationships (Karlaftis and Badr 2015, Mazari and Rodriguez 2016, Heidari et al 2018, Hossain et al 2019, Inkoom et al 2019, Yao et al 2019. A NN model usually consists of an input layer, one or several hidden layers, and an output layer.…”

Deep reinforcement learning for long‐term pavement maintenance planning

“…Therefore, pavement performance prediction models are employed to play the role of the environment, forecasting the future pavement condition. Four neural network prediction models, incorporating 39 factors for each, developed in a recent study (Yao, Dong, Jiang, & Ni, 2019), were used to predict the rutting depth (RD), international roughness index (IRI), side-way force coefficient (SFC), and pavement distress condition index (PDCI). RD, IRI, and SFC are detection indicators speculated in the highway performance assessment standards (JTG H20-2007), while PDCI is a self-defined indicator proposed by Zhou, Ni, and Leng (2014) to better evaluate the severity of the surface distress condition of asphalt pavement.…”

“…The action space is composed of the maintenance treatments involved in the neural network prediction model (Yao et al., 2019). An action contains three features: maintenance types, maintenance materials, and distress treatment.…”

Towards Low-Cost Pavement Condition Health Monitoring and Analysis Using Deep Learning

“…Given the advances of deep learning, there has been significant research using these techniques for Pavement Engineering applications [21][22][23][24]. These applications can be assigned to the following areas: Pavement condition and performance predictions [25][26][27][28], Pavement management systems [29][30][31], pavement performance forecasting [32][33][34], structural evaluations [35][36][37], modelling pavement materials [38][39][40] and pavement image analysis and classification [22,[41][42][43][44]. Pavement Image analysis and classification is the most researched area, where the focus has been split between image classifications, where images are classified based on the distress occurring in the image; and object detection, where distresses are located within bounding boxes or masks within the image.…”