Modeling for pavement roughness using the ANFIS approach

• Published in: Advances in engineering software (1992) Vol. 57; pp. 59 - 64
• Main Author: Terzi, Serdal
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.03.2013
• Subjects: Adaptive neural-based fuzzy inference system; Adaptive systems; Artificial neural networks; Equivalent Single Axle Loads; Flexible highway pavements; Fuzzy; Fuzzy logic; Inference; International Roughness Index (IRI); Pavement performance; Pavements; Roughness; Structure number; International Roughness Index (IRI); Equivalent Single Axle Loads; Pavement performance; Flexible highway pavements; Adaptive neural-based fuzzy inference system; Structure number
• ISSN: 0965-9978
• DOI: 10.1016/j.advengsoft.2012.11.013

The term “present serviceability” was adopted to represent the momentary ability of pavement to serve traffic, and the performance of the pavement was represented by its serviceability history in conjunction with its load application history. Serviceability was found to be influenced by longitudinal and transverse profile as well as the extent of cracking and patching. The amount of weight that should be assigned to each element in the determination of overall serviceability is a matter of subjective opinion. In this study, an Adaptive Neural-Based Fuzzy Inference System (ANFIS) method is used in modeling the International Roughness Index (IRI) of flexible pavements. Data from the LTPP IMS database, namely, age, cumulative Equivalent Single Axle Loads (ESALs), and Structure Number (SN) were used in the modeling. Results showed that the ANFIS model is successful for the estimation of IRI, and this model can be easily applied in different regions. The model can be further developed by combining expert judgment and newly measured data.