Innovative model for accurate prediction of the transfer length of prestressing strands based on artificial neural networks: Case study

Abstract This study provides a case study showing the effectiveness of utilizing Artificial Neural Networks (ANNs) in prestressed concrete. The effectiveness of prestressing is crucially linked to the transfer length (TL) of the prestressing strands. The ANN technique was used for accurate prediction of TL based on more than 458 data points collected from various literature works. The ANN technique allowed for investigating the effect of various key parameters classified into major categories including: strand characteristics, concrete properties, geometric details, and manufacturing method. The MATLAB software was utilized to build, train, and test the ANN using 19 input variables and one targeted output. Sensitivity analysis identified the main parameters influencing the TL determination, which lead to the development of ANN-based analytical model with high prediction capability and low mean square error. The effectiveness and accuracy of the proposed model were verified through comparisons with the AASHTO and ACI codes models as well as with some proposed models in literature. The developed ANN-based prediction model combined the effects of most significant parameters influencing the TL with many important parameters never been considered before. For simplicity, the required coefficients for predicting the TL using the developed model were provided in clear and easy to use charts taking into consideration the beam cross-sectional shape.

[1]  박호,et al.  Behavior and analysis of transfer zone in pretensioned prestressed concrete members , 2015 .

[2]  Paul H. Kaar,et al.  Influence of Concrete Strength On Strand Transfer Length , 1963 .

[3]  Tsung-lin Lee,et al.  Assessment of highway slope failure using neural networks , 2009 .

[4]  Mehmet Metin Kose.  Statistical evaluation of transfer and development length of low-relaxation prestressing strands in standard I-shaped pretensioned concrete beams , 1999 .

[5]  W. Micah Hale,et al.  Measured Transfer Lengths of 0.7 in. (17.8 mm) Strands for Pretensioned Beams , 2016 .

[6]  B. Oh,et al.  Analysis and Prediction of Transfer Length in Pretensioned, Prestressed Concrete Members , 2014 .

[7]  B. Oh,et al.  REALISTIC EVALUATION OF TRANSFER LENGTHS IN PRETENSIONED, PRESTRESSED CONCRETE MEMBERS , 2000 .

[8]  S. Gross,et al.  TRANSFER AND DEVELOPMENT LENGTH OF 15.2 MM (0.6 IN.) DIAMETER PRESTRESSING STRAND IN HIGH PERFORMANCE CONCRETE: RESULTS OF THE HOBLITZELL-BUCKNER BEAM TESTS , 1995 .

[9]  T. Cousins,et al.  Transfer length of epoxy-coated prestressing strand , 1990 .

[10]  Bruce W Russell,et al.  Transfer, Development, and Splice Length for Strand/Reinforcement in High-Strength Concrete , 2008 .

[11]  P Zia,et al.  DEVELOPMENT LENGTH OF PRESTRESSING STRANDS , 1977 .

[12]  Ahmed M. Azmy,et al.  Neural networks for predicting compressive strength of structural light weight concrete , 2009 .

[13]  C. A. Arbeláez,et al.  Analytical model for transfer length prediction of 13 mm prestressing strand , 2007 .

[14]  William R. Burkett,et al.  Formulation of new development length equation for 0.6 in. prestressing strand , 2005 .

[15]  Ha-Won Song,et al.  Analysis of carbonation behavior in concrete using neural network algorithm and carbonation modeling , 2010 .

[16]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[17]  Ned H. Burns,et al.  Measured transfer lengths of 0.5 and 0.6 in. strands in pretensioned concrete , 1996 .

[18]  Dooyeol Yoo,et al.  Bond Behavior of Pretensioned Strand Embedded in Ultra-High-Performance Fiber-Reinforced Concrete , 2018, International Journal of Concrete Structures and Materials.

[19]  S. Rizkalla,et al.  Transfer and Development Lengths of Carbon Fiber Reinforced Polymers Prestressing Reinforcement , 1999 .

[20]  Denis Mitchell,et al.  INFLUENCE OF HIGH STRENGTH CONCRETE ON TRANSFER AND DEVELOPMENT LENGTH OF PRETENSIONING STRAND , 1993 .

[21]  François Fleuret,et al.  Not All Samples Are Created Equal: Deep Learning with Importance Sampling , 2018, ICML.

[22]  Francesc J. Ferri,et al.  Prediction of the transfer length of prestressing strands with neural networks , 2013 .

[23]  N H Burns,et al.  DESIGN GUIDELINES FOR TRANSFER, DEVELOPMENT AND DEBONDING OF LARGE DIAMETER SEVEN WIRE STRANDS IN PRETENSIONED CONCRETE GIRDERS. FINAL REPORT , 1993 .

[24]  Łukasz Sadowski,et al.  Prediction of Concrete Compressive Strength by Evolutionary Artificial Neural Networks , 2015 .

[25]  Byung Hwan Oh,et al.  Theoretical Analysis of Transfer Lengths in Pretensioned Prestressed Concrete Members , 2006 .

[26]  Hong Jae Yim,et al.  Experimental Evaluation of Transfer Length in Pretensioned Concrete Beams Using 2,400-MPa Prestressed Strands , 2016 .

[27]  W. Micah Hale,et al.  Analysis of bond stress distribution for prestressing strand by Standard Test for Strand Bond , 2014 .

[28]  Hojjat Adeli,et al.  Optimization of space structures by neural dynamics , 1995, Neural Networks.