There exist several options how to treat welds in numerical models. The large deformations make the mechanical analysis more complex and it is possible to use different mesh descriptions, different kinetic and kinematic variables and constitutive models. The different types of geometric 2D and 3D models and thereby finite elements with their applicability for different accuracy levels are generally used. Most often used material model is the common rate-independent plasticity model based on von Mises yield criterion. Two approaches that are used for welds are described. Residual stress and deformation caused by welding are not assumed in the design model.

The load is transmitted through force-deformation constraints based on the Lagrangian formulation to opposite plate. The connection is called multi-point constraint (MPC) and relates the finite element nodes of one plate edge to another. The finite element nodes are not connected directly. The advantage of this approach is the ability to connect meshes with different densities. The constraint allows to model midline surface of the connected plates with the offset, which respects the real weld configuration and throat thickness. The load distribution in the weld is derived from the MPC, so the stresses are calculated in the throat section. This is important for the stress distribution in the plate under the weld and for modeling of T-stubs.

#### Plastic stress redistribution in welds

The model with only multi-point constraints does not respect the stiffness of the weld and the stress distribution is conservative. Stress peaks that appear at the end of plate edges, in corners and rounding, govern the resistance along the whole length of the weld. To eliminate the effect, a special elastoplastic element is added between the plates. The element respects the weld throat thickness, position and orientation. The equivalent weld solid is inserted with the corresponding weld dimensions. The nonlinear material analysis is applied and elastoplastic behavior in equivalent weld solid is determined. The plasticity state is controlled by stresses in the weld throat section. The stress peaks are redistributed along the longer part of the weld length.

The elastoplastic model of welds gives real values of stress and there is no need to average or interpolate the stress. Calculated values at the most stressed weld element are used directly for checks of the weld component. This way, there is no need to reduce the resistance of multi-oriented welds, welds to unstiffened flanges or long welds.

*Constraint between weld element and mesh nodes*

General welds, while using plastic redistribution, can be set as continuous, partial and intermittent. Continuous welds are over the whole length of the edge, partial allows user to set offsets from both sides of the edge, and intermittent welds can be additionally set with a set length and a gap.