A METHOD OF DATA-DRIVEN MODELING FOR PREDICTING UPLIFTING FORCES OF SUCTION CAISSON ANCHORS

摘要

The present invention relates to a data-driven modeling method to predict pullout capacity of suction caisson anchors, including: a first step of collecting load capacity data of a suction caisson system; a second step of calculating a correlation coefficient of input/output data; a third step of applying a data pre-processing method for load capacity data compression and noise removal; a fourth step of determining a cluster center based on the density of the data applied by the third step; a fifth step of optimizing a consequent part parameter using a weighted least square algorithm; a sixth step of returning to the fourth step in case an error value is larger than an allowed error value, and proceeding a next step in case the error value is smaller than the allowed error value; and a seventh step of testing validity of a model. The data-driven modeling method of the present invention can manage a suction caisson structure efficiently by predicting the pullout capacity of the suction caisson anchors having various variables efficiently.