Estimation of reinforced concrete construction costs and effective structural parameters with a smart system at bridge interchange

In this study, 50 bridged intersection projects were examined. Length of underpass structure (m), closed section area (m2), bored pile (m3), engineering structures (m3), precast facade panel (m), pre-tensioned prefabricated beam (m3) and approximate costs based on unit price were calculated, data tables were created and defined as input-output data to Orange program. Decision trees (Tree), support vector machines (SVM), stochastic gradient descent (SGD), random forest (RF) and neural network (YSA) from machine learning algorithms, which are part of artificial intelligence, in order to estimate the concrete construction costs of bridge junction projects and learning and test procedures. The effect of input parameters on the cost of bridged intersection reinforced concrete construction is examined and cost estimation is performed. The results of these algorithms were compared with each other and the performance of artificial neural network method was demonstrated.