Application of Supervised Neural Networks to Classify Failure Modes in Reinforced Concrete Columns Using Basic Structural Data

• Published in: Applied sciences Vol. 15; no. 18; p. 10175
• Main Authors: Megalooikonomou, Konstantinos G., Beligiannis, Grigorios N.
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.09.2025
• Subjects: Algorithms; Artificial intelligence; artificial neural networks; Civil engineering; columns; Concrete; Datasets; Deep learning; Deformation; Ductility; Earthquakes; Failure; failure mode; Forecasts and trends; Load; Machine learning; Neural networks; Optimization; PEER structural performance database; Python; Reinforced concrete; Shear strength; Structural engineering; United States; United States
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app151810175

Reinforced concrete (RC) columns play a vital role in structural integrity, and accurately predicting their failure modes is essential for enhancing seismic safety and performance. This study explores the use of a supervised machine learning approach—specifically, an artificial neural network (ANN) model—to classify failure modes of RC columns. The model is trained using data from the well-established Pacific Earthquake Engineering Research Center (PEER) structural performance database, which contains results from over 400 cyclic lateral-load tests on RC columns. These tests encompass a wide range of column types, including those with spiral or circular hoop confinement, rectangular ties, and varying configurations of longitudinal reinforcement with or without lap splices at critical sections. The ANNs were evaluated using a randomly selected subset from the PEER database, achieving classification accuracies of 94% for rectangular columns and 95% for circular columns. Notably, in certain cases, the model’s predictions aligned with or exceeded the accuracy of traditional building code-based methods. These findings underscore the strong potential of machine learning—particularly ANNs—for reliably postdicting failure modes (even the brittle ones) in RC columns, signaling a promising advancement in the field of earthquake engineering.