Life-cycle performance prediction for rigid runway pavement using artificial neural network

ABSTRACT

Pavement performance of airport runway plays a key role in the process of aircraft landing and takeoff. To predict runway pavement performance in life cycle, a novel artificial neural network (ANN) has been developed since 2011 by Civil Aviation University of China (CAUC). Evaluation data of 33 runways were used to train, validate and optimize the ANN by a series of heavy weight deflectometer (HWD) tests. By estimating the simplified pavement damage index (ξ) in ANN, investigations on the influences of service life and air traffic on runway pavement performance were analysed. The outcomes from our analysis lead to a novel method of estimating and classifying runway pavement performance in entire service life. Besides ANN analysis, in situ experiments on runway pavement from 2014 to 2018 were also conducted to verify the predicted results. It demonstrates that ANN is an efficient and alternative tool in predicting runway pavement performance. The results show that the service quality of runway pavement decreases in a linear (non-linear) way for regional (hub) airport. In the process of runway pavement deterioration, service life plays a key role in all airports, while air traffic has the greatest contributions to the hub airport. Then runway pavement performance can be classified according to the simplified pavement damage index. In this way, the runway pavement performance in life cycle can be divided into four zones from excellent, good, poor to dangerous. It is possible to help airport agencies to make scientific decisions on runway pavement maintenance, rehabilitation and reconstruction.

KEYWORDS:

• Airport runway
• pavement performance prediction
• simplified pavement damage index
• heavy weight deflectometer
• artificial neural network

Disclosure statement

No potential conflict of interest was reported by the authors.

Correction Statement

This article has been republished with minor changes. These changes do not impact the academic content of the article.

Additional information

Funding

This work is supported by the Science and Technology Service network program (STS) project (No.KFJ-STS-ZDTP-037) of the Chinese Academy of Sciences.