Title: Rapid design of R/C columns using Machine Learning techniques
Authors:  Papanikolaou VK, Charalampakis AE.
Type: Conference paper
Conference: COMPDYN 2021
Venue: Athens, Greece
Date: 2021
Language: English

[abstract]

The development of Machine Learning, which is deemed to be the path to Artificial Intelligence, has changed tremendously the way many computationally intensive tasks are treated nowadays. Regarding the design of R/C columns and bridge piers, the results of a recent project which proposes a number of design functions are examined and discussed in this work. Both rectangular and circular as well as solid and hollow sections are treated. The proposed design functions are naturally immune to numerical instabilities and achieve more than adequate accuracy for design. They are also, by nature, orders of magnitude faster than any design algorithm based on iterative equilibrium procedures. The error estimation for each function is described in detail based on extensive test sets. Certain method pitfalls, which were encountered and successfully treated, are also discussed.

[cite as]

Papanikolaou VK, Charalampakis AE. Rapid design of R/C columns using Machine Learning techniques. Proc. 8th International Conference on Computational Methods in Structural Dynamics and Earthquake Engineering, COMPDYN 2021, Athens, Greece; 2021.

[ Paper]