Concrete mixing performance prediction method based on least squares support vector machine

The invention relates to the field of concrete mixing technology, in particular to a concrete mixing performance prediction method based on a least squares support vector machine. The method comprises the following steps: determining static parameters of concrete material formula performances; sampling to obtain power parameters during mixing; calculating dynamics characteristic parameters of a concrete mixing system; and with the static parameters, the power parameters and the dynamics characteristic parameters of the concrete mixing system as inputs of the least squares support vector machine, and with concrete slumps and strength acquired by experiments as outputs, learning and predicting. The concrete mixing performance prediction method based on the least squares support vector machine has high prediction precision and good generalization performance, can rapidly predict the concrete slumps and the strength simultaneously, and can be expanded to the other fields.