Modelling Compressive Strength of Concrete via Teaching–Learning Based Optimization and JAYA Algorithms

In this study, compressive strength tests, ultrasonic wave transmission speed measurements, Schmidt rebound test hammer measurements were made on the cube samples and void ratios were determined by weighing. It is aimed to estimate the concrete strength with these measurements by establishing a regression relation between the wave transmission speed obtained from the ultrasound test, rebound values from Schmidt rebound hammer and void ratio calculated by weighting. Teaching–learning-based optimization (TLBO) and JAYA algorithms were applied to regression functions of the data from the tests. The input parameters are the average wave transmission speed obtained as a result of ultrasound measurements, rebound values from Schmidt rebound hammer and void ratio calculated by weighting. The accuracy of TLBO method is compared with those of the JAYA algorithm. These methods are applied to seven different regression forms: quadratic, exponential, linear, S function, Inverse, Ln function and power. To evaluate the performance of the models, five statistical indices, i.e., sum square error, root mean square error, mean absolute error, average relative error, and determination coefficient, are used