عنوان مقاله [English]
The stability of bridge piers on rivers or in wide and deep irrigation channels is a major concern for hydraulic structural engineers. Despite development of several empirical equations for determining local scour depth at bridge abutments in hydraulic laboratories, for field data, which is affected by uncontrollable environmental circumstances, no comprehensive relationship has been reported. Gaussian process regression (GPR) is a data mining method consisting of a set of random variables that, according to normal characteristics using kernel functions, have a high ability to solve nonlinear problems. This study evaluated the efficiency of GPR for estimating pier scour depth using field scour data and compared the results with those from eight empirical equations. Of the empirical equations studied, the Froehlich empirical equation showed the best performance and was more accurate than the other experimental equations. When estimating the scour hole depth using dimensional parameters and GPR with a Pearson kernel function, the combination of input parameters of pier form factor, pier width, average particle size of bed sediment, and depth of stream provided the best-case scenario. The results represent the greatest efficiency and highest accuracy of GPR in comparison with empirical equations to estimate scour depth using sets of field data.
Akib, S., Mohammadhassani, M. and Jahangirzadeh, A. 2014. Application of ANFIS and LR in prediction of scour depth in bridges. J. Comput. Fluids. 91, 77-86.
Anon. 1975. Highways in the river environment: hydraulic and environmental design considerations. User Manual. Federal Highway Administration. U. S. Department of Transportation. Colorado State University.
Arvanaghi, H., Hoseinzadeh, D., Farsadizadeh, A. and Fakheri, A. 2008. Time variation of scour around bridge piers and empirical relationship. J. Agric. Knowl. 18(2): 1-10. (in Persian)
Ayubloo, M. K., Azamathulla, H. M., Ahmad, Z., Ghani, A. A., Mahjoobi, J. and Rasekh, A. 2011. Prediction of scour depth in downstream of ski-Jump spillways using soft computing techniques. Int. J. Comput. Appl. 33(1): 92-97.
Chiew, Y, M. 1995. Mechanism of riprap failure at bridge piers. J. Hydraul. Eng-ASCE. 121(9): 635-643.
Froehlich, D. C. 1988. Analysis of on-site measurements of scour at piers. Proceedings of the ASCE Hydraulic Engineering Conference. Aug. 8-12. New York.
Gao, D. G., Posada, L. G. and Nordin, C. F. 1992. Pier scour equations used in the People's Republic of China-review and summary: Fort Collins CO. Colorado State University, Department of Civil Engineering. Draft Report.
Ghazanfari-Hashemi, S. and Shahidi, A. A. 2012. Predicting of the local scour depth around bridge piers using support vector machine. J. Modarres Civil Eng. 12(2): 23-36. (in Persian)
Hosseini, R. and Amini, A. 2015. Scour depth estimation methods around pile groups. KSCE J. Civil Eng. 19(7): 2144-2156.
Jain, S. C. and Fischer, E. E. 1980. Scour around bridge piers at high Froude numbers. Report No.
FHWA-RD-79-104. Federal Highway Administration. Washington D. C. USA.
Kuchekzadeh, S., Liaghat, A. and Sheikh-Shamayel, H. 2002. Estimation local scour depth around piers located in a river main channel using artificial neural networks. J. Iranian Agr. Sci. 33(4): 617-626.
Melville, B.W. 1997. Pier and abutment scour: integrated approach. J. Hydraul. Eng. ASCE.
Mozzammil, M. and Alam, J. 2013. ANFIS-Based approach to scour prediction at the grade control structures. European Int. J. Sci. Technol. 2(6): 123-136.
Muller, D. S. and Wagner, C. R. 2005. Field observations and evaluations of streambed scour at bridges. Federal Highway Administration. U. S. Department of Transportation. Washington D. C. USA.
Najafzadeh, M., Shahidi, A. A. and Yong Lim, S. 2016. Scour prediction in long contractions using ANFIS and SVM. J. Ocean Eng. 111(1): 128-135.
Najafzadeh, M., Barani, G. A. and Hessami-Kermani, M. R. 2015. Evaluation of GMDH networks for prediction of local scour depth at bridge abutments in coarse sediments with thinly armored beds. J. Ocean Eng. 104, 387-396.
Neerukatti, R. K., Kim, I., Yekani-Fard, M. and Chattopadhyay, A. 2013. Prediction of scour depth around bridge piers using Gaussian Process. Proceedings of the Smart Structures and Materials/NDE Conference. SPIE. 8692. March 10-14. San Diego. California. USA.
Pal, M. and Deswal, S. 2010. Modelling pile capacity using Gaussian process regression. Comput. Geotech. 37, 942-947.
Pal, M., Singh, N. K. and Tiwari, N. K. 2011. Support vector regression based modeling of pier scour using field data. Eng. Appl. Artif. Intel. 24, 911-916.
Pal, M., Singh, N. K. and Tiwari, N. k. 2012. M5 model tree for pier scour prediction using field dataset. KSCE J. Civil Eng. 16(6): 1079-1084.
Pasolli, L., Melgani, F., Member, S. and Blanzieri, E. 2010. Gaussian process regression for estimating chlorophyll concentration in subsurface waters from remote sensing data. Geosci. Remote Sensing Letters. IEEE. 7(3): 464-468.
Samadi, M., Jabbari, E. and Azamathulla, H. M. 2014. Assesment of M5 model tree and classification
and regression trees for prediction of scour depth below free overfall spillways. Neural Comput. Appl.
Shafaie-Bejestan, M. 2011. Sediment Hydraulic. Shahid Chamran University Press. (in Persian)
Shen, H. W., Schneider, V. R. and Karaki, S. 1969. Local scour around bridge piers. J. Hydr. Eng. Div.ASCE. 95(5): 1919-1940.
Sheppard, D. M. and Miller, W. 2006. Live-Bed local pier scour experiments. J. Hydraul. Eng. ASCE. 132(7): 635-642.
Simons, B. D. and Senturk, F. 1992. Sediment Transport Technology: Water and Sediment Dynamics. Water Resources Publications. littleton, CO.