| Summary: | Corrosion of embedded steel reinforcement is the prime influencing factor that deteriorates the structural performance and reduces the serviceability of reinforced concrete (RC) structures, especially during earthquakes. In structural elements, RC columns play a vital role in transferring the superstructure’s load to the substructure. The deterioration of RC columns can affect the structures’ overall performance. Hence, it becomes essential to estimate the remaining life of deteriorated RC columns. In the literature, only limited analytical models are available to calculate the remaining life of corroded and eccentrically loaded RC columns. As the number of dependent parameters increases, assessing the residual life of the structural elements and providing a practically applicable suitable model become very complex. Machine learning (ML)-based prediction models are beneficial in dealing with such complex databases. In this article, an ML-based artificial neural network (ANN), Gaussian process regression (GPR), and support vector machine (SVM) algorithms have been applied to estimate the residual strength of corroded and eccentrically loaded RC columns. The performance of the analytical and ML models is accessed using commonly used performance indices, namely, the coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), a-20 index, and Nash–Sutcliffe (NS). The results of the proposed ANN model have been compared with the existing analytical model to identify the suitability of the best model. Based on performance analysis, the precision of the GPR and SVM models is lower than that of the ANN model. The processed results revealed that the R2 value of the ANN model for training, testing, and validation datasets is 0.9908, 0.9757, and 0.9855, respectively. The MAPE, MAE, RMSE, NS, and a-20 index for all the datasets are 8.31%, 48.35 kN, 72.53 kN, 0.9886, and 0.8978, respectively. The precision of the ANN model in terms of the coefficient of determination is 225.77% higher than that of the analytical model. The sensitivity analysis demonstrates that the compressive strength of concrete plays the most significant role in the load-carrying capacity of corroded and eccentrically loaded RC columns. The proposed ANN model is reliable, accurate, fast, and cost effective. This model can also be used as a structural health-monitoring tool to detect the early damages in the RC columns.
|
|---|