Author/Authors :
Bhattacharya Sumana نويسنده , Murakonda Pavani نويسنده Indian Institute of Technology, Roorkee , Das Sarat Kumar نويسنده Indian Institute of Technology Kanpur,
Abstract :
Suction caissons are extensively used as anchors for oshore foundation
structures. The uplift capacity of suction caisson is an important factor with respect
to eective design. In this paper, two recently developed AI techniques, i.e. Functional
Network (FN) and Multivariate Adaptive Regression Spline (MARS), have been used to
predict the uplift capacity of suction caisson in clay. The performances of the developed
models are compared with those of other AI techniques: articial neural network, support
vector machine, relevance vector machine, genetic programming, extreme learning machine,
and Group Method of Data Handling with Harmony Search (GMDH-HS). The modelʹs
inputs include the aspect ratio of the caisson, undrained shear strength of soil at the depth of
the caisson tip, relative depth of the lug to which the caisson force is applied, load inclination
angle, and load rate parameter. The results of the above AI techniques are comparatively
analysed via dierent statistical performance criteria: correlation coecient (R), root mean
square error, Nash-Sutclie coecient of eciency, and log-normal distribution of ratio of
the predicted load capacity to observed load capacity, with a ranking system to determine
the best predictive model. The FN and MARS models are found to be comparably ecient
which can outperform other AI techniques.