Vol.12, No.3, August 2023. ISSN: 2217-8309 eISSN: 2217-8333
TEM Journal
TECHNOLOGY, EDUCATION, MANAGEMENT, INFORMATICS Association for Information Communication Technology Education and Science |
Neural Networks Applicability for Design of Reinforced Concrete Sections for Bending
Krasimir Boshnakov, Vladimir Yakov
© 2023 Vladimir Yakov, published by UIKTEN. This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. (CC BY-NC-ND 4.0)
Citation Information: TEM Journal. Volume 12, Issue 3, Pages 1294-1299, ISSN 2217-8309, DOI: 10.18421/TEM123-08, August 2023.
Received: 07 April 2023. Revised: 17 July 2023.
Abstract:
Solving engineering design tasks requires the use of analytical formulas and dependencies. The direct inclusion of mathematical expressions in the artificial neural network (ANN) is not possible. This research studies the possibility of applying the neural networks method for designing of single or double-side reinforced concrete sections. A Visual Basic for Applications (VBA) macro was developed in the MS Excel environment to solve the task of determining the required area of the reinforcement by given geometric dimensions and bending moment and applying classical analytical formulas for reinforced concrete sections design. The training of the pre-configured neural network is performed by approximately 34000 sets of matching input parameters. The presented results from the trained ANN are compared and analysed against the exact analytical solutions. The study presents an approach to the application of structural design calculations. The results suggest that the approach is applicable to more complicated structural design problems.
Keywords –Neural networks, reinforced concrete section design. |
----------------------------------------------------------------------------------------------------------- ----------------------------------------------------------------------------------------------------------- |