Study on Reinforced Concrete Frame with Solid Infill Masonry using Artificial Neural Network (ANN) RC Infill Wall Model in ANSYS (Ajay Gupta)

This document was uploaded by one of our users. The uploader already confirmed that they had the permission to publish it. If you are author/publisher or own the copyright of this documents, please report to us by using this DMCA report form.

Simply click on the Download Book button.

Yes, Book downloads on Ebookily are 100% Free.

Sometimes the book is free on Amazon As well, so go ahead and hit "Search on Amazon"

Author(s): Er Ajay Gupta
Year: 2011

Language: English
Pages: 82

COPYRIGHT ©......Page 3
CERTIFICATE......Page 4
ACKNOWLEDGEMENT......Page 5
ABSTRACT......Page 6
LIST OF TABLES
Table 2-1: Analogy between biological and artificial neural networks 13
Table 3-1: Types and Properties of Bric......Page 9
LIST OF FIGURES......Page 10
LIST OF SYMBOLS......Page 11
1.1 Infilled Frames......Page 12
1.2 Background......Page 13
1.3 Why this Study ?......Page 14
1.5 Methodology......Page 16
1.5.2 Collection of Input Data......Page 17
1.5.5 Result Validation......Page 18
2.2 Experimental Studies......Page 19
Figure 2-1: Single Diagonal Strut Models (Smith and Carter 1969)......Page 20
2.4 About ANN......Page 23
2.4.1 Back-Propagation Neural Network......Page 24
Figure 2-4: Typical Back-Propagation Network......Page 25
3.2 Masonry......Page 27
Table 3-1: Types and Properties of Bricks (Pradhan, P.L., 2009)......Page 28
Figure 3-1: Stress-strain characteristics of different bricks used.......Page 29
Table 3-2: Types and Properties of Mortar (Pradhan, P.L., 2009)......Page 30
Table 3-3: Properties of concrete and rebars used in analysis......Page 31
4.1 About ANSYS......Page 33
4.2.2 Dimensions of the Model......Page 34
Figure 4-1: Plane stress element used for Modeling......Page 35
Figure 4-2: Beam3 element used for Modeling Beam and Column......Page 36
Table 4-1: Material properties used in analysis (Pradhan, P.L., 2009)......Page 37
4.3.5 The Outputs......Page 38
4.4 Preparation of the Training sets......Page 39
5.2 Development of ANN Tool......Page 41
Figure 5-2: Error reduction graph during Back-propagation Neural Network Training......Page 42
Table 6.1: Parameters of Interest......Page 43
6.2 Geometric Parameters......Page 44
6.2.1 Influence of wall thickness......Page 45
6.2.2 Influence of Aspect Ratio......Page 46
Table 6-4: Response variation due to aspect ratio......Page 47
6.2.4 Influence of Mortar......Page 48
6.3 Variation of stiffness......Page 49
Figure 6-2: Variation of displacement with span......Page 50
6.4 Effective width of equivalent diagonal strut......Page 51
Table 6-7: Comparison of strut widths......Page 52
Figure 6-5 : Comparison of actual versus predicted data......Page 53
Table 7-1: Comparison of Results obtained from ANSYS and ANN......Page 54
7.1 General......Page 59
7.2 Conclusions......Page 61
7.3 Recommendations for the future works......Page 62
Figure A-2 : Stress Intensity contour plot......Page 64
Figure A-4 : X-axis Stress contour plot......Page 65
Table A-1: ANSYS Results for Span 3m......Page 66
Table A-1: ANSYS Results for Span 3.5m......Page 69
Table A-1: ANSYS Results for Span 4m......Page 72
Table A-1: ANSYS Results for Span 4.5m......Page 75
Table A-1: ANSYS Results for Span 5m......Page 78
REFERENCES......Page 81