Prediction of rolling force in cold rolling by using physical models and neural computing

A new shape change quantification method for estimation of power in shape rolling

“…Neural models are quite suitable for online applications such as mill control [17]. Nylander and coworkers [18] reported another interesting application of neural models in flat rolling. They applied a neural model to make a correlation between measurable rolling parameters such as dimensions and chemical composition and those parameters which are hard to measure but are required for empirical models such as flow stress, friction and lever arm for torque calculations.…”

Representation and control of the cold rolling process through artificial neural networks via sensitivity factors

“…Considering the cold rolling process, the requirements to enhance the quality of the products are typically thickness and shape. The extensive literature shows several strategies to reach these objectives, inclusive through non-conventional techniques as neural networks (Larkiola et al, 1996;Larkiola et al, 1998;Yang et al, 2004a), fuzzy logic (Jung et al, 1995;Zhu et al, 2003) and genetic programming (Son et al, 2004). The only condition for the new strategies is to represent correctly the behavior of the process in a quantitative and qualitative form, for different operation points, so that these can be used in the design of on-line control and supervision systems.…”

Irregularity in Friction Hills during the Cold Rolling of Materials

“…Moreover, it may become more difficult to use mathematical models of the cold rolling process for engineering purposes [1][2][3][4]. In the cold rolling process, friction along the arc of contact at the roll-strip interface is necessary for the transmission of deformation energy from the work rolls to the strip.…”