PREDICTION OF THE SEISMIC CAPACITY OF RC STRUCTURAL WALLS BY NONPARAMETRIC MULTIDIMENSIONAL REGRESSION

The use of a non-parametric multidimensional regression is suggested f or the prediction of the seismic capacity of reinforced concrete struc tural walls. This capacity is expressed in terms of the shear strength , drift, ductility and failure mode of the walls. For the application of the method a data base is needed which contains data on the results of tests performed on the structural elements under consideration. Th e data base used in the study was compiled from the available literatu re, and includes data from laboratory tests carried out on 262 structu ral walls. The method was validated by comparing the predicted and tes t results. A comparison with some available closed-form empirical pred ictions has been made. The results show that the accuracy of the predi ctions obtained by the proposed method is, on average, higher than tha t provided by existing formulae. The proposed method has several advan tages when compared to closed-form empirical expressions based on stan dard linear regression: (1) The relationship between the input and out put variables is not selected a priori by a prediction law. (2) It tak es into account the current available data base, which can be updated when new information becomes available. (3) An arbitrary number of inp ut and output variables can be taken into account using the same data base. (4) The method can be applied directly to similar problems in st ructural and earthquake engineering, wherever a suitable data base is available.