A new profile-agnostic sequential parametrisation method for extrusion die in transformer-based surrogate model

Aluminium extrusion is widely used in manufacturing engineering components for construction, packaging, and transportation, yet its die design remains heavily dependent on time-consuming and costly trial-and-error methods informed by empirical knowledge. This research aims to expedite the most time-intensive phase, Finite Element (FE) validation phase, by proposing a sequential parametrisation of extrusion die and developing a Transformer-based surrogate model to predict the material flow speed deviation. This work consists of two distinct contributions. First, a novel sequential representation for extrusion dies is introduced, demonstrated using a T-shaped flat extrusion die. This approach eliminates the need for profile-specific parameters while preserving all geometric information of the die. The principle of the method is to decompose an extrusion die into five layers of subsections, each of which is abstracted into top/bottom views. These views are further partitioned into multiple segments arranged in a counterclockwise sequence, producing a comprehensive list of segments without any loss of information. Second, a Transformer-based autoencoder is then employed to capture the intricate interactions among these segments and generate the corresponding flow deviation plot for the current die design. Promising results on T-shaped profile have been achieved using a compact dataset with only 256 samples of FE generated data, including for similar unseen designs that have never been used for training. Comparative analyses reveal that the proposed architecture improves the accuracy of extrusion simulation predictions by 144 % (on an internal benchmark) relative to a traditional scalar-based parametrisation method using a fully connected Neural Network (NN).