Emine AĞAR, Ahmet Burak GÖKTEPE, Abdullah Hilmi LAV

Esnek üstyapılarda mekanik özelliklerin yapay sinir ağları kullanılarak geri hesaplanması

Esnek üstyapıların performans değerlendirmesi için, genel olarak tahribatsız deney metotları tercih edilmektedir. Tahribatsız deney metotları içerisinde en çok tercih edilen, Düşen Ağırlık Deflektometresi (FWD) yöntemidir. Bu yöntem ile, yol üzerindeki çok sayıda yerde, uygulanan yük sebebi ile meydana gelen zamana bağlı defleksiyon değerleri kaydedilir. Uygulamada, FWD deneyi ile elde edilen defleksiyon değerleri ve geri-hesaplama programları kullanılarak, üstyapı tabakalarına ait mekanik özellikler hesaplanır. Fakat, bu programlar, parametre tanımlama algoritmaları kullanmakta ve bu da zaman kaybına neden olmaktadır. Bu çalışmada, FWD testinden elde edilen defleksiyonları kullanarak, esnek üstyapı tabakalarındaki mekanik özellikleri yapay sinir ağları ile geri-hesaplayan bir model geliştirilmiştir. Sonuçlar, modelin hassasiyetinin son derece yüksek olduğunu ve gerçek-zamanlı geri-hesaplama yapılabilmeye olanak sağladığını göstermiştir.

Backcalculation of mechanical properties of flexible pavements using neural networks

Performance evaluation of flexible pavements is usually performed using nondestructive testing methods. Basic advantage of nondestructive testing methods is that it’s possible to obtain pavement performance data by these methods without resulting any damage to the pavement system. Of all nondestructive testing methods, Falling Weight Deflectometer (FWD) is the most popular technique. Falling Weight Deflectometer, measures time-domain deflections from numerous road sections emerging by the applied impulse load. The common way for the evaluation of FWD results is to backcalculate the mechanical properties with the help of backcalculation software. However, these software utilize parameter identification routines, which are quite time consuming and computationally expensive. Under the way of this, in this study, a neural network model was developed to backcalculate mechanical properties of flexible pavement layers in order to shorten the processing time. For the development of optimal neural network model, the effects of network’s architecture and learning parameters were comprehensively examined. The results indicated that, both network’s architecture and learning parameters significantly affect the neural network’s performance. Consequently, the accuracy of developed neural network model is successful and the model enables real-time backcalculation opportunity that is crucial for highway engineers working on pavement evaluation studies and developing pavement maintenance strategies.

PDF

___

Bose, N.K. ve Liang, P., (1996). Neural Network Fundamentals with Graphs, McGraw-Hill Int. Ed., 478.
Bentsen,R.A., Bush, A.J. ve Harrison, J.(1989). Evaluation of NDT Equipment for Airfield Pavements, Technical Record GL-89-3, U.S. AEWES, Vicksburg, MS, 390.
Chang,D.,Kang,Y,Roesset,J ve Stokoe,K (1992) Effect of Depth to Bedrock on Deflection Basins with Dynaflect and FWD Test, Record No: 1355, TRB, 8-16.
Demuth, H., ve Beale, M., (2000). Neural network toolbox for use with MATLAB, User’s Guide, Math Works, Inc., USA, 822.
Flood, I. ve Kartam, N., (1998). Artificial Neural Networks for Civil Engineers ASCE Press, 277.
Fu, L., (1994). Neural Networks in Computer Intelligence, McGraw-Hill Int. Ed., USA, 460.
Haykin, S., (1999). Neural Networks: A Compreh. Foundation. Prentice-Hall NJ, 842.
Hoffman, M.S. ve Thompson, M.R., (1982). Backclc. nonl. resilient moduli from deflection data, Record No: 852, TRB, DC., 42-51.
Huang, Y. H., (1993). Pavement analysis and design, Prentice Hall, NJ, 803.
Jacobs, R.A., (1988). Increased rates of convergence through learning rate adapt., Neural Networks, 1, 295-307.
Kecman, V., (2001). Learning and soft computing, MIT Press, MA, USA, 541.
Kim, Y.R., Xu, B., ve Kim, Y., (2000). A new backcalculation procedure based on dispersion analysis of FWD time history deflect. and surface wave measurements using ANNs, ASTM STP 1375, PA.
Lytton R.L., (1989). Backcalculation of layer moduli- state of the art. ASTM STP 1026., PA., 7-38.
LeCun, Y., (1993). Efficient learning and secondorder methods, A Tutorial at NIPS 93, ATT Bell Labs, Denver, UK, 27.
Meier,R.W., ve Rix, G.J., (1993). An initial study of surface wave ınversion using artificial neural networks, Geotechnical Testing Journal, ASTM , 16, 425-432.
Meier, R. W. ve Rix, G.J., (1994). Backcalc. of flexible pavement moduli using artificial neural networks, Record No: 1448, TRB, DC., 75-82.
Meier,R.W., (1995). Backcalculation of Flexible Pavement Moduli from FWD Data Using ANNs, PhD Dissertation Georgia Institute of Technology, Atlanta, 239.
Meier,R.W. ve Rix, G.J., (1995). Backcalc. of flexible pavement moduli from dynamic deflection basins using ANNs, Record No: 1473, TRB, DC., 72-81.
Nazarian,S. ve Stokoe, K.H., (1989). NDT evaluation of pavements by surface wave method, ASTM STP 1026, PA., 119-137.
Pearl, J., (1988). Probabilistic Reasoning in Intelligent Sys. 2nd Ed, Pearl Press, UK., 552.
Principle, J.C., Euliano, N.R., Lefebvre, W., (2000). Neural and adaptive systems, John Wiley & Sons, Inc., USA, 656.
Roesset, J.M., ve Shao, K., (1985). Dynamic Interpretation of Dynaflect and FWD Tests, Annual Meeting of the TRB, DC., USA.
Rumelhart, D.E. ve McClelland, J.L., (1986). Parallel Distributed Processing, 1, MIT Press, MA.
Saltan, M., Tigdemir, M., Karasahin, M. (2002). ANN application for flexible pavement thickness modeling, Turkish Journal of Engineering and Environmental Science, TÜBİTAK, 26, 243-248.
Sebaaly,B, Davies,T.G, ve Mamlouk,M, (1985). Dynamics of FWD, ASCE, Journal Of Transportation Engineering., 111, 6, 618-632.
Stolle, D. F., (1991). Modeling of dynamic response of pavements to ımpact loading. Computers and Geotechnics, 11, 1, 83-94.
Ross,T.J. (1995). Fuzzy Logic with Engineering Applications, McGraw- Hill Co., USA, 600.
Sagıroglu, S., Besdok, E., ve Erler, M., (2003). Mühendislikte yapay zeka uygulamalari, Ufuk Kitap Yayincilik, Istanbul, 426.
Tawfiq, K., Armaghani, J., Sobanjo, J., (2000). Seismic pavement analyzer and FWD for pavement evaluation, ASTM STP 1375, PA.
Tholen, O., Sharma, J. ve Terrel, R.L., (1985). Comparison of FWD with Other Deflection Testing Devices. Record No: 1007, TRB, DC., 20-26.
Tutumluer, E. ve Seyhan, U., (1998). NN Modeling of Anisotropic Aggregate Behavior from Repeat Load Triaxial Tests, Record No: 1615, TRB, D.C.
Uzan, J., ve Scullion, T., (1990). Verification of Backcalculation Procedures, Proc. 3rd Int. Conf. on Bearing Capacity of Roads and Airfields, Norway, 1, 447-458.
Uzan, J., (1994). Advanced Backcalculation Techniques, ASTM STP 1198, PA, 3-37.
Widrow, B. ve Hoff, M.E., (1960). Adaptive switching circuits, 1960 IRE WESCON Convention Record, New York IRE, 96-100.
Zhou, H., (2000). Comparison of backcalc. and laboratory measured moduli on ac and granular base layer materials, ASTM STP 1375, PA, 161-172.