PREDICTION OF THE PAVEMENT SERVICEABILITY RATIO OF RIGID HIGHWAY PAVEMENTS BY ADAPTIVE NEURO-FUZZY

Abstract

In this study, an Adaptive Neuro-Fuzzy Inference System (ANFIS) model has been developed in order to predict Present Serviceability Ratio (PSR) which is one of the important parameter used in designing rigid pavements. In modeling Slope Variance (SV), Cracking (C) and Patching (P) were used as input parameters and PSR was used as output parameter ANFIS model compared with experimental (measured) parameters and determined that correlation was perfect between them. It was determined that can be able to use ANFIS model for predicting PSR used practically in designing rigid pavements depending on SV, C and P with low error rates within a short period of time without any experimental study and measurement.

Keywords

• Rigid Pavements, Present Serviceability Ratio, Adaptive Neuro-Fuzzy Inference System

References

1. Terzi, S. 2004. “Highway Pavement Maintenance Management Model Using Geographic Information System Development”, Süleyman Demirel University, Institute of Science and Ph.D. in Civil Engineering Department, Isparta, pp. 21-22
2. AASHO Road Test, 1962, “The AASHO Road, Test Report 5, Pavement Research”, By The Highway Research Board Of The NAS-NRC Division Of The Engineering And Industrial
3. Research, Special Report 61E, No: 954, National Academy Of Sciences-National
4. Öztürk, F., 2006, Modeling of Flexible Road Pavements Design Method with Fuzzy Logic
5. Research Council Washington DC.
6. Technology, Suleyman Demirel University, Department of Civil Engineering Institute
7. of Science and Master of Science Thesis, Isparta, pp. 14.
8. Jang, J.S.R., C.T. Sun, 1997. Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence. Prentice Hall, Englewood Cliffs, NJ

9. Tahmasebi, P., Hezarkhani, A. 2010. Application of Adaptive Neuro-Fuzzy Inference System for Grade Estimation; Case Study, Sarcheshmeh Porphyry Copper Deposit, Kerman, Iran, Australian Journal of Basic and Applied Sciences, Amirkabir University, Hafez Ave. No. 424, Tehran, Iran.
10. Çaydaş, U., Hasçalık A., Ekici S. 2009. An adaptive neuro-fuzzy inference system (ANFIS) model for wire-EDM, Expert Systems with Applications, Vol:36, 3/2, pp. 6135-6139.
11. Madandoust, R., Bungey, J.H., & Ghavidel, R. (2012). Prediction of the concrete compressive strength by means of core testing using GMDH-type neural network and ANFIS models. Computational
12. Materials Science, 51, 261–272.