Prediction of Pull - out capacity of Suction Caissons Using Self - Evolving Neural Networks
نویسنده
چکیده
A self-evolving neural network is developed using a combination of PSO and JPSO algorithms to predict the pull-out capacity of suction caissons in clay. The algorithm is proposed with the aim of reducing the network complexity without compromising accuracy. A database consisting of experiments performed on suction caissons is used to construct and validate the network model. The performance comparisons indicate that the proposed self-evolving neural network predicts more the capacity of suction caissons accurately than neural networks developed using conventional methods.
منابع مشابه
An Investigation into the Pull-out Failure Mechanisms of Suction Caissons
This paper reports results from an investigation into the suction caissons failure mechanisms under vertical pull-out loads. An insight to the failure mechanisms of suction caissons paves the path for developing analytical solutions to their pull-out capacity. The numerical models of suction caissons have first been calibrated by and verified against several experimental data from other researc...
متن کاملEvaluation of Influencing Factors on the Pull-out Behavior of Suction Caissons
Suction caisson is a type of floor foundation for the offshore structures that is also called suction pile, bucket foundation, suction anchor, or sometimes ridge foundation depending on its application. In two past decades, this type of foundation has been widely used around the world as the fixed offshore foundation, anchor of the floating platforms, as well as the foundation of other marine s...
متن کاملارزیابی عوامل تاثیرگذار بر رفتار بیرون کشش صندوقههای مکشی
Suction caisson foundation systems have been successfully used in the past two decades in numerous occasions on a variety of offshore structures in a wide range of environments. The pull-out capacity of suction caissons remains a critical issue in their applications, and reliable methods of predicting the capacity are required in order to produce effective designs. In the current study a numeri...
متن کاملSuction Caisson Anchors - a Better Option for Deep Water Applications
As offshore exploration and development of oil fields reach water depths of 1,000 to 3,000 m, novel methods of anchoring production platforms become attractive due to cost savings associated with installation. Surface production systems that are viable in these water depths include Tension Leg Platforms (TLP), spar platforms, and laterally moored ship-shaped and semisubmersible vessels. Possibl...
متن کاملNeural Prediction of Buckling Capacity of Stiffened Cylindrical Shells
Estimation of the nonlinear buckling capacity of thin walled shells is one of the most important aspects of structural mechanics. In this study the axial buckling load of 132 stiffened shells were numerically calculated. The applicability of artificial neural networks (ANN) in predicting the buckling capacity of vertically stiffened shells was studied. To this end feed forward (FF) multi-layer ...
متن کامل